ONE SKILL
THE GUIDED EDITIONS
Start with a skill.
Build with a guide.
Focused AI workflows with a clear route from your inputs to a result you can review. Each guided edition adds staged prompts and task-specific acceptance checks to an original starter skill.
108 guided skills. One useful toolkit. One-time purchases · USD
01 / CHOOSE YOUR START
A focused skill.
Or the whole toolkit.
Planned launch prices in USD. One payment for the named edition. Any applicable taxes will be shown at checkout.
CATEGORY COLLECTION
$6.99
17-19 guided skills for one area of work.Choose a category ↓COMPLETE COLLECTION
$19.99
All 108 guided skills. Save $86.93 compared with individual purchases.WHAT CHANGES IN THE GUIDED EDITION
More guidance.
Same open foundation.
3 selected starter samples are free to download. The complete catalog has task previews; full guided packs are delivered with a purchase once sales open. All included files retain the MIT license.
| Included | Free sample | Guided |
|---|---|---|
| Skill instructions & input template | Yes | Yes |
| Synthetic example & worked result | Yes | Yes |
| Task-specific staged prompt runbook | - | Yes |
| Dedicated acceptance-check worksheet | - | Yes |
| MIT license & usage guide | Yes | Yes |
02 / FIND A GUIDED SKILL
Choose the task.
Follow the next steps.
Search the complete collection and preview each task's inputs and outputs. Try a selected free sample before choosing a guided edition.
No guided skills match. Try another phrase or clear the filters.
01Analysis
Feedback Analysis
Turn customer feedback into evidence-backed themes, mixed sentiment, and a clear action list.
- Bring
- Feedback records with stable IDs and the business question you want to answer.
- Build
- Theme and evidence table · Sentiment and limitations · Prioritized actions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
02Analysis
Data to Story
Create a presentation brief from a dataset while keeping calculations, caveats, and narrative connected.
- Bring
- A dataset, its metric definitions, the audience, and the decision to support.
- Build
- Checked metric summary · Slide-by-slide brief · Source and caveat notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
03AI design
AI Evaluation Planner
Plan repeatable evaluations for an AI workflow, including supported answers, refusals, and failure cases.
- Bring
- The AI task, allowed sources, intended users, and the cost of an incorrect answer.
- Build
- Evaluation matrix · Test cases and rubrics · Release criteria
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
04Automation
SQL Report Review
Review reporting queries for join fan-out, data grain, null handling, and reconciliation gaps.
- Bring
- A read-only SQL query, database dialect, table schemas, and expected reporting grain.
- Build
- Prioritized findings · Suggested read-only query · Reconciliation checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
9 files · Guided edition 1.0.0
05Automation
VBA Automation Planner
Turn a recurring spreadsheet process into a scoped automation plan with dry runs, reconciliation, and recovery.
- Bring
- Workbook structure, manual steps, expected outputs, and known exceptions.
- Build
- Automation brief · Validation and dry-run plan · Recovery and handover checklist
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
06AI design
Agent Workflow Designer
Design a bounded agent workflow with clear state transitions, tool contracts, and human handoffs.
- Bring
- The goal, available tools, data sources, and which actions need human decisions.
- Build
- Workflow specification · Tool and state contracts · Failure and handoff scenarios
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
07Analysis
Metric Definition
Turn an ambiguous KPI into a precise, reproducible metric contract.
- Bring
- The business decision, event grain, reporting window, and inclusion rules.
- Build
- Metric contract · Worked reconciliation · Open definition decisions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
08Analysis
Cohort Retention
Compare cohort retention without treating unobserved future periods as churn.
- Bring
- Cohort membership, return events, observation cutoff, and retention definition.
- Build
- Cohort retention table · Eligibility and censoring notes · Interpretation brief
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
09Analysis
Funnel Diagnostics
Find genuine funnel drop-offs while excluding out-of-order events.
- Bring
- Timestamped events, entity keys, ordered funnel stages, and a conversion window.
- Build
- Ordered funnel table · Drop-off evidence · Tracking and investigation notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
10Analysis
Experiment Readout
Produce an experiment readout with effect sizes and release guardrails.
- Bring
- Assignment counts, metric outcomes, analysis plan, and guardrail thresholds.
- Build
- Effect-size readout · Design and validity checks · Decision recommendation
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
11Analysis
Forecast Backtest
Benchmark a forecast against a baseline with auditable error calculations.
- Bring
- Forecast origins, horizons, actuals, model predictions, and a baseline.
- Build
- Aligned error table · Metric and bias comparison · Backtest limitations
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
12Analysis
Anomaly Triage
Separate a real metric incident from partial data or reporting artifacts.
- Bring
- Observed values, expected baseline, completeness evidence, and relevant changes.
- Build
- Triage assessment · Evidence and competing hypotheses · Investigation order
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
13Analysis
Dashboard Brief
Design a dashboard around decisions, denominators, and actionable exceptions.
- Bring
- Audience decisions, available data, metric contracts, and refresh needs.
- Build
- Dashboard specification · Metric and interaction contracts · Acceptance scenarios
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
14Analysis
KPI Reconciliation
Explain KPI disagreements with a signed, evidence-backed reconciliation bridge.
- Bring
- Two reported values, their definitions, and attributable adjustment records.
- Build
- Signed reconciliation bridge · Residual and evidence table · Definition alignment notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
15Analysis
Segment Comparison
Compare like-for-like segment results and expose misleading aggregate rankings.
- Bring
- Segment counts and outcomes, group definitions, and comparison objectives.
- Build
- Within-segment comparison · Aggregate and adjusted results · Mix and inference caveats
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
16Analysis
Missing Data Assessment
Identify how missing observations affect coverage and conclusions.
- Bring
- Field-level missingness, observed values, reasons, and valid value bounds.
- Build
- Missingness profile · Observed-only results · Sensitivity and follow-up plan
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
17Analysis
Trend and Seasonality
Read time trends without confusing recurring seasonality with growth.
- Bring
- A dated series, calendar conventions, complete-period flags, and comparison needs.
- Build
- Comparable-period calculations · Trend and seasonal interpretation · Evidence limitations
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
18Analysis
Pricing Sensitivity
Compare price scenarios while separating margin arithmetic from demand assumptions.
- Bring
- Price, expected units, variable costs, and scenario assumptions.
- Build
- Scenario contribution table · Break-even volume threshold · Assumption and inference notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
19Analysis
Inventory Coverage
Assess stock coverage using available inventory and explicit replenishment timing.
- Bring
- SKU inventory, reservations, demand rates, and replenishment lead times.
- Build
- Coverage and exposure table · Lead-time gap assessment · Inventory assumptions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
20Analysis
Support Capacity
Model support workload and usable capacity with explicit shrinkage assumptions.
- Bring
- Ticket arrivals, handling minutes, staffing hours, shrinkage, and backlog targets.
- Build
- Workload and capacity model · Gap and backlog scenarios · Queueing limitations
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
21Analysis
Scenario Model
Build internally consistent scenarios instead of mixing incompatible assumptions.
- Bring
- Driver definitions, linked assumptions, costs, and the decision threshold.
- Build
- Driver-based scenario table · Break-even calculation · Sensitivity and assumptions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
22Analysis
Chart Selection
Choose visuals that make the analytical comparison accurate and clear.
- Bring
- The audience question, dataset shape, units, and uncertainty information.
- Build
- Chart recommendation · Encoding and annotation specification · Misleading-chart checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
23Analysis
Executive Insight Brief
Turn reconciled findings into a concise executive decision brief.
- Bring
- Verified findings, metric definitions, decision options, and material caveats.
- Build
- Executive brief · Evidence-to-decision mapping · Decision request and caveats
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
24Customer intelligence
Survey Question Review
Improve survey questions so answers measure one clearly defined construct.
- Bring
- Survey questions, target respondents, measurement intent, and answer scales.
- Build
- Item-level findings · Rewritten survey items · Measurement trade-offs
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
25Customer intelligence
NPS Driver Review
Calculate NPS correctly and distinguish observed themes from causal drivers.
- Bring
- Valid 0-10 recommendation scores, linked comments, and sampling context.
- Build
- NPS reconciliation · Score-group theme table · Driver hypotheses and limitations
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
26Customer intelligence
Journey Friction Map
Connect journey-stage friction with affected customers and traceable evidence.
- Bring
- Journey stages, customer-linked touchpoints, outcomes, and observation limits.
- Build
- Stage-level friction map · Customer and touchpoint counts · Investigation priorities
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
27Customer intelligence
Churn Signal Review
Review churn-warning rules without leaking future evidence into decisions.
- Bring
- Customer behavior before a cutoff, an explicit rule, and outcome definitions.
- Build
- Cutoff-valid signal table · Leakage and coverage findings · Validation requirements
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
28Customer intelligence
Contact Reason Taxonomy
Create contact labels that remain consistent when tickets contain several issues.
- Bring
- Representative ticket text, reporting purpose, and existing label rules.
- Build
- Taxonomy and definitions · Labeled case table · Boundary and review rules
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
29Customer intelligence
Ticket Priority Rubric
Assign transparent ticket priority using operational impact and urgency.
- Bring
- Ticket impact, urgency, available workaround, and a stated priority policy.
- Build
- Priority rubric · Ticket decision table · Ambiguity and escalation notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
30Customer intelligence
Service Recovery Plan
Plan an empathetic recovery with a bounded remedy and clear follow-up.
- Bring
- Verified issue, customer impact, remedy policy, and available owner roles.
- Build
- Recovery action plan · Customer response draft · Policy exceptions and follow-up
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
31Customer intelligence
Voice of Customer Brief
Create a customer-voice brief with honest scope and traceable recommendations.
- Bring
- Customer comments, collection context, duplicate rules, and the target decision.
- Build
- Customer voice brief · Evidence and sample accounting · Prioritized investigation proposals
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
32Customer intelligence
Review Comparison
Compare review evidence without treating unequal samples as population rankings.
- Bring
- Review records, rating scales, source populations, and comparison questions.
- Build
- Source-level comparison · Aspect evidence table · Comparability and sampling caveats
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
33Customer intelligence
Feedback Deduplication
Clean feedback without merging independent voices or losing revisions.
- Bring
- Feedback IDs, source keys, revision timestamps or versions, and exclusion rules.
- Build
- Accepted record table · Duplicate and revision ledger · Count reconciliation
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
34Customer intelligence
Aspect Sentiment
Keep positive and negative sentiment attached to the correct aspect.
- Bring
- Text records, aspect definitions, annotation rules, and reporting unit.
- Build
- Aspect-level annotation table · Sentiment count summary · Ambiguity and evidence notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
35Customer intelligence
Complaint Root Cause
Separate repeated complaint symptoms from verified underlying causes.
- Bring
- Complaints, linked logs or process evidence, and candidate explanations.
- Build
- Symptom and cause evidence map · Confirmed versus hypothesized findings · Next diagnostic checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
36Customer intelligence
Interview Synthesis
Synthesize interview evidence without inflating prevalence from repeated quotes.
- Bring
- Interview excerpts, participant IDs, study question, and sampling context.
- Build
- Theme and participant matrix · Evidence-linked synthesis · Divergence and follow-up questions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
37Customer intelligence
Persona Evidence
Create behavior-based personas with explicit evidence and uncertainty.
- Bring
- Participant observations, goals, constraints, and the intended design decision.
- Build
- Provisional persona profiles · Attribute evidence table · Validation and gaps
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
38Customer intelligence
Product Feedback Roadmap
Prioritize product opportunities while keeping constraints and scoring assumptions visible.
- Bring
- Feedback evidence, estimated reach and impact, effort, confidence, and mandatory constraints.
- Build
- Candidate roadmap ranking · Scoring and constraint ledger · Discovery and measurement plan
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
39Customer intelligence
CX Metric Audit
Check CX metrics for denominator errors and misleading comparisons.
- Bring
- Survey questions, response counts, metric definitions, and reporting claims.
- Build
- Metric audit findings · Corrected calculations · Comparability and coverage notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
40Customer intelligence
Escalation Pattern Review
Find escalation patterns without overcounting transfers or treating open tickets as resolved.
- Bring
- Ticket histories, escalation events, resolved times, and a reporting cutoff.
- Build
- Escalation pattern table · Ticket and event reconciliation · Timing and case-mix caveats
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
41AI design
Prompt Contract
Turn a vague prompt into explicit input rules, evidence boundaries, and observable acceptance checks.
- Bring
- The user task, sample inputs, authorized evidence, output consumers, and failure consequences.
- Build
- Prompt contract · Ambiguity register · Boundary acceptance cases
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
42AI design
Structured Output Design
Design response schemas that distinguish unknown values from negative results and invalid output.
- Bring
- Consumer requirements, sample responses, field meanings, and known invalid combinations.
- Build
- Response schema brief · Cross-field invariants · Valid and invalid examples
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
43AI design
Refusal Policy Design
Define when an assistant answers, clarifies, abstains, or hands a request to a person.
- Bring
- Assistant remit, permitted actions, supplied restrictions, and representative boundary requests.
- Build
- Decision policy · Reason codes · Boundary response examples
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
44AI design
Tool Contract Review
Review tool inputs and outcomes so retries and ambiguous failures cannot silently duplicate actions.
- Bring
- Tool specification, examples, authorization model, error cases, and side-effect behavior.
- Build
- Contract findings · Revised specification · Retry and ambiguity cases
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
45AI design
Agent State Machine
Turn an agent workflow into explicit states, guarded transitions, and stale-event handling.
- Bring
- Workflow goal, observable events, action permissions, failure paths, and state persistence assumptions.
- Build
- State transition table · Invariant register · Event trace review
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
46AI design
Agent Memory Plan
Design memory records with provenance, expiry, correction, and clear user-control boundaries.
- Bring
- Memory use cases, proposed fields, source trust, retention requirements, and correction examples.
- Build
- Memory schema · Retention and correction rules · Retrieval boundary cases
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
47AI design
Human Handoff Design
Design handoffs with the decision needed, evidence, ownership, and safe resume conditions.
- Bring
- Escalation triggers, available human roles, workflow state, evidence, and communication permissions.
- Build
- Handoff packet · Ownership and timeout rules · Resume decision cases
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
48AI design
Hallucination Test Suite
Test unsupported details and false certainty with evidence-based expected answers.
- Bring
- Assistant scope, approved source snapshot, candidate answers, and claim severity.
- Build
- Grounding case suite · Claim-level answer keys · Failure severity report
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
49AI design
Prompt Injection Test Plan
Test whether untrusted content can redirect answers, reveal protected instructions, or trigger actions.
- Bring
- Task instructions, untrusted entry points, tool capabilities, and expected trust boundaries.
- Build
- Threat-path matrix · Synthetic injection cases · Expected boundary outcomes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
50AI design
LLM Cost Budget
Calculate token budgets and cost drivers with explicit retry and fallback assumptions.
- Bring
- Expected request volume, token profiles, supplied unit rates, retries, fallbacks, and budget limits.
- Build
- Cost calculation table · Sensitivity scenarios · Budget guardrail proposal
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
51AI design
Model Routing Plan
Route tasks using segment-level evidence and explicit escalation criteria.
- Bring
- Task strata, supplied model results, resource costs, latency limits, and quality floors.
- Build
- Routing decision table · Fallback criteria · Evidence and uncertainty notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
52AI design
AI Incident Triage
Build an evidence-based incident timeline and prioritize containment without premature root-cause claims.
- Bring
- Failure report, supplied traces, affected tasks, recent changes, and operating authority.
- Build
- Impact and timeline brief · Cause hypotheses · Containment and validation plan
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
53AI design
AI Use Case Scope
Turn a broad AI idea into a bounded pilot with measurable benefit and explicit exclusions.
- Bring
- User problem, workflow baseline, candidate tasks, evidence availability, and decision constraints.
- Build
- Pilot scope brief · Benefit hypothesis · Acceptance and exclusion criteria
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
54AI design
AI Release Review
Make a release recommendation that respects critical gates and untested conditions.
- Bring
- Release candidate changes, frozen evaluation results, acceptance gates, and operating constraints.
- Build
- Gate decision · Failed-case priorities · Required evidence before release
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
55AI design
Synthetic Test Data
Create reproducible synthetic cases with constraints, edge labels, and explicit limitations.
- Bring
- Task schema, domain constraints, coverage targets, and permitted synthetic variations.
- Build
- Synthetic fixture specification · Expected outcome labels · Coverage and constraint checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
56AI design
AI Observability Plan
Design traces and metrics that separate pipeline failures while keeping data collection purposeful.
- Bring
- Workflow stages, failure questions, existing telemetry, data sensitivity, and operational thresholds.
- Build
- Trace and metric schema · Failure attribution map · Retention and alert proposal
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
57AI design
Response Quality Rubric
Score answers against observable criteria and critical failures rather than writing style alone.
- Bring
- Task objective, source evidence, candidate responses, consequence levels, and reviewer disagreements.
- Build
- Anchored scoring rubric · Scored examples · Disagreement resolution rules
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
58NLP & retrieval
RAG Source Readiness
Check whether a source collection can support trustworthy retrieval before indexing it.
- Bring
- Source inventory, sample extracted text, authority rules, revision history, and intended questions.
- Build
- Source readiness matrix · Blocking evidence gaps · Indexing preparation plan
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
59NLP & retrieval
Chunking Experiment
Compare chunk designs using answer evidence and boundary coverage rather than chunk size alone.
- Bring
- Document excerpts, question set, answer spans, candidate chunk boundaries, and retrieval budget.
- Build
- Chunk comparison plan · Evidence coverage findings · Boundary and duplication cases
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
60NLP & retrieval
Retrieval Evaluation
Calculate retrieval metrics while keeping answerability and incomplete judgments visible.
- Bring
- Queries, ranked source IDs, judged relevant sets, cutoff k, and label completeness.
- Build
- Per-query retrieval metrics · Aggregate and denominator notes · Error analysis
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
61NLP & retrieval
Citation Check
Audit claim-to-source support beyond whether a citation link exists.
- Bring
- Answer text, cited excerpts, source dates, and claim-level support requirements.
- Build
- Claim-citation matrix · Unsupported claim findings · Corrected answer draft
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
62NLP & retrieval
Query Rewrite Review
Improve search wording while preserving the user's actual constraints and uncertainty.
- Bring
- Original query, candidate rewrites, corpus terminology, and required filters.
- Build
- Rewrite fidelity findings · Suggested query variants · Constraint preservation checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
63NLP & retrieval
Hybrid Search Plan
Plan a hybrid search experiment that protects exact identifiers and semantic intent.
- Bring
- Query classes, sample lexical/dense rankings, corpus metadata, filters, and evaluation labels.
- Build
- Retrieval branch plan · Fusion and filter rules · Comparison cases
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
64NLP & retrieval
Knowledge Base Refresh
Plan source refreshes that retire stale chunks and verify the active evidence snapshot.
- Bring
- Source change manifest, indexed versions, deletion records, freshness requirements, and release controls.
- Build
- Refresh manifest · Reconciliation checks · Activation and recovery plan
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
65NLP & retrieval
Entity Extraction Schema
Extract entities without merging names, roles, or dates beyond what the text supports.
- Bring
- Text corpus sample, target entity types, normalization needs, and ambiguity rules.
- Build
- Entity schema · Span-backed extraction examples · Ambiguity and validation rules
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
66NLP & retrieval
Document Classification
Classify documents using explicit label boundaries and mixed-content rules.
- Bring
- Label definitions, document examples, desired label cardinality, and review costs.
- Build
- Label decision rules · Evidence-backed classifications · Ambiguity review queue
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
67NLP & retrieval
Text Deduplication
Deduplicate repeated records without erasing separate events or contradictory versions.
- Bring
- Records with stable IDs, event keys, text, provenance, and version or timing information.
- Build
- Duplicate group table · Conflict and retention rules · Adjusted counting notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
68NLP & retrieval
Multilingual Evaluation
Review multilingual quality without letting a larger language sample hide a failing segment.
- Bring
- Language-tagged cases, original meanings, candidate outputs, scoring rules, and language-specific gates.
- Build
- Language-level scores · Meaning-error analysis · Coverage gaps
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
69NLP & retrieval
Taxonomy Design
Design theme hierarchies with clear boundaries and evidence-aware rollup rules.
- Bring
- Business questions, sample feedback, proposed themes, hierarchy constraints, and counting grain.
- Build
- Taxonomy and label guide · Assignment examples · Rollup and revision rules
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
70NLP & retrieval
Summarization Fidelity
Summarize evidence while preserving counts, uncertainty, and unresolved outcomes.
- Bring
- Source excerpts, audience, compression target, and required factual details.
- Build
- Faithful summary · Claim-to-source check · Omitted-detail and caveat notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
71NLP & retrieval
PII Redaction Review
Review redaction for direct identifiers and useful context without promising anonymization.
- Bring
- Synthetic or approved text, sharing purpose, sensitive-field policy, and proposed redaction.
- Build
- Redaction findings · Minimized text draft · Linkability and residual-risk notes
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
72NLP & retrieval
Semantic Search Debug
Locate retrieval failures in the pipeline before proposing embedding or ranking changes.
- Bring
- Original queries, rewritten queries, filters, candidate lists, source state, and expected evidence.
- Build
- Failure-stage diagnosis · Discriminating checks · Prioritized repair proposal
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
73NLP & retrieval
Retrieval Ablation
Compare retrieval components with paired cases and explicit configuration controls.
- Bring
- Baseline and ablation configurations, fixed queries, source snapshot, and per-query outcomes.
- Build
- Ablation comparison · Paired regression findings · Follow-up experiment plan
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
74NLP & retrieval
Evidence Conflict Review
Resolve conflicting evidence by authority and scope while preserving unresolved cases.
- Bring
- Contradictory claims, source excerpts, authority hierarchy, dates, and the question's time scope.
- Build
- Conflict matrix · Supported resolution or abstention · Evidence follow-up questions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
75Data engineering
Data Contract
Define the rules a dataset must satisfy before downstream consumers can rely on it.
- Bring
- Dataset purpose, field definitions, consumer needs, and sample records.
- Build
- Dataset contract · Acceptance rules · Change decisions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
76Data engineering
Schema Drift Review
Identify structural and semantic changes before consuming a new schema.
- Bring
- Old/new schemas, sample values, and consumer assumptions.
- Build
- Change classification · Consumer impact map · Compatibility checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
77Data engineering
Incremental Load Plan
Plan incremental loads that account for timestamp ties, corrections, and late arrivals.
- Bring
- Change model, keys, timestamps, and target merge behavior.
- Build
- Load boundaries · Checkpoint rules · Replay cases
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
78Data engineering
Pipeline Reconciliation
Explain mismatches with key-level evidence and conserved counts or amounts.
- Bring
- Source/target extracts, keys, filters, and permitted transformations.
- Build
- Reconciliation table · Mismatch classification · Follow-up checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
79Data engineering
Data Lineage Map
Trace report fields back to source evidence and identify incomplete lineage.
- Bring
- Source schemas, transformations, output fields, and dependency boundaries.
- Build
- Dependency map · Field lineage table · Unresolved provenance questions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
80Data engineering
Data Quality Rules
Build measurable quality checks without double-counting multi-rule failures.
- Bring
- Grain, constraints, sample records, and release policy.
- Build
- Rule catalog · Exception table · Batch acceptance summary
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
81Data engineering
Backfill Plan
Design historical reruns that preserve current data and prove replacement windows.
- Bring
- Historical scope, source availability, target grain, and recovery constraints.
- Build
- Backfill windows · Replacement/checkpoint rules · Reconciliation/recovery checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
82Data engineering
Event Deduplication
Separate repeated delivery from legitimate events and conflicting payloads.
- Bring
- Event IDs, payloads, immutability/version semantics, and retention rules.
- Build
- Duplicate policy · Classified event ledger · Replay/conflict checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
83Data engineering
Slowly Changing Dimensions
Plan dimension history so facts use the right attributes at the right time.
- Bring
- Dimension keys, attributes, effective dates, and correction rules.
- Build
- History strategy · Effective intervals · As-of join checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
84Data engineering
SQL Window Review
Check analytical SQL for tied ordering, wrong frames, and unstable selection.
- Bring
- Dialect, query, partition grain, metric, and tie examples.
- Build
- Window findings · Read-only expressions · Expected row outputs
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
85Data engineering
SQL Performance Triage
Prioritize bottlenecks from evidence without promising untested speedups.
- Bring
- Query, dialect, actual/estimated plan, timings, and correctness constraints.
- Build
- Ranked bottlenecks · Controlled comparison plan · Correctness guardrails
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
86Data engineering
Data Access Matrix
Map the minimum data each role needs for a defined workflow.
- Bring
- Roles, purposes, fields, row scopes, and supplied sensitivity rules.
- Build
- Role/field matrix · Scope/retention notes · Owner decisions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
87Data engineering
Data Migration Checklist
Plan migration proof from source mapping through cutover readiness.
- Bring
- Source/target schemas, scope, transformations, and cutover constraints.
- Build
- Migration checklist · Expected reconciliations · Cutover/recovery criteria
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
88Data engineering
API Data Mapping
Translate nested API samples without accidental row multiplication.
- Bring
- Responses, target grain, semantics, and known pagination/status rules.
- Build
- Field mapping · Array/grain decisions · Sample target rows
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
89Data engineering
Batch Failure Triage
Identify whether a failed batch can retry safely from committed-state evidence.
- Bring
- Manifest, logs, stage boundaries, commit evidence, and retry semantics.
- Build
- Failure timeline · Recovery options · Missing evidence/stop conditions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
90Data engineering
Timestamp Normalization
Align timestamps consistently while exposing missing timezone or format assumptions.
- Bring
- Timestamp values, locale, offset rules, and reporting boundary.
- Build
- Normalized table · Ambiguity exceptions · Boundary checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
91Data engineering
Analytics Table Grain
Make grain explicit so reports count each intended fact once.
- Bring
- Table samples, analytical questions, keys, and measure definitions.
- Build
- Grain/key statement · Aggregation rules · Join-risk examples
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
92Automation
Spreadsheet Reconciliation
Reconcile spreadsheet exports without hiding missing rows behind matching totals.
- Bring
- Two sheet extracts, stable keys, formula/value rules, and rounding policy.
- Build
- Matched/exception table · Adjustment bridge · Workbook review checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
93Automation
Workbook Input Validation
Validate workbook inputs before a reporting or automation process uses them.
- Bring
- Sheet/table layout, field rules, locale, and representative rows.
- Build
- Input contract · Row exceptions · Acceptance criteria
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
94Automation
Report Scheduling Plan
Schedule reports by data readiness and business deadlines rather than clock time alone.
- Bring
- Refresh deadlines, timezone, upstream readiness, recipients, and failure rules.
- Build
- Scheduling design · Dependency gates · Failure/delivery scenarios
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
95Automation
Automation Opportunity Review
Choose automation candidates using evidence of effort and process stability.
- Bring
- Candidate processes, frequencies, effort, exceptions, and constraints.
- Build
- Candidate comparison · Priority rationale · Pilot acceptance criteria
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
96Automation
Process Mapping
Make process handoffs and exception paths explicit before changing them.
- Bring
- Current steps, actors, inputs, handoffs, timings, and exceptions.
- Build
- Current-state map · Exception paths · Bottleneck questions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
97Automation
Exception Routing
Route failed or ambiguous records to the right decision owner.
- Bring
- Exception types, evidence, impact, owners, and resumption rules.
- Build
- Routing table · Exception payload · Resolution/resumption cases
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
98Automation
Idempotency Review
Identify repeated-run effects and define stable operation identities.
- Bring
- Workflow steps, target effects, key/version rules, and failure boundaries.
- Build
- Repeatability findings · Operation identity design · Crash/replay scenarios
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
99Automation
Automation Handover
Create an operating handover that another owner can use without hidden assumptions.
- Bring
- Workflow design, operational evidence, dependencies, owners, and known limits.
- Build
- Handover brief · Run interpretation guide · Open ownership questions
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
100Automation
File Ingestion Plan
Plan reliable file intake with visible completeness and replay rules.
- Bring
- File naming, manifest/schema rules, versions, targets, and failure behavior.
- Build
- Ingestion contract · File classification · Commit/replay checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
101Automation
Email Draft Workflow
Prepare repeatable email drafts with verified context and review boundaries.
- Bring
- Purpose, recipients, approved source facts, tone, and review rules.
- Build
- Draft workflow · Message draft · Recipient/fact checks
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
102Automation
Approval Workflow
Design clear approval transitions and prevent stale decisions from authorizing revised work.
- Bring
- Approval purpose, authority rules, versions, and deadlines.
- Build
- State-transition table · Approval evidence contract · Revision/expiry scenarios
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
103Automation
Document Template Plan
Specify reusable documents without fragile find-and-replace assumptions.
- Bring
- Document purpose, fields, sample records, conditions, and presentation rules.
- Build
- Template specification · Binding/conditional rules · Sample document outline
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
104Automation
Automation Regression Plan
Plan regression checks that protect observable behavior across automation changes.
- Bring
- Previous behavior, proposed change, input cases, and failure boundaries.
- Build
- Risk-based test matrix · Expected observable results · Release evidence gaps
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
105Automation
Recurring Report Pack
Create repeatable reporting packs whose numbers, narrative, and caveats agree.
- Bring
- Audience, reporting period, metrics, sources, and recurring sections.
- Build
- Report-pack outline · Metric/commentary consistency · Correction/version rules
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
106Automation
Workflow Retry Review
Bound retries to recoverable failures and avoid repeating uncertain external effects.
- Bring
- Stages, error classes, attempt limits, effects, and commit evidence.
- Build
- Retry decision table · Attempt timeline · Stop/reconciliation rules
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
107Automation
Automation Value Estimate
Calculate net time potential and break-even assumptions transparently.
- Bring
- Frequency, time measurements, review/maintenance estimates, setup effort, and value basis.
- Build
- Effort model · Break-even calculation · Sensitivity and evidence gaps
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
108Automation
Operating Procedure Draft
Write a usable procedure with clear inputs, stop conditions, and completion evidence.
- Bring
- Process facts, roles, prerequisites, approved steps, and exception rules.
- Build
- Procedure draft · Decision/exception checkpoints · Completion evidence checklist
What you get
- Original skill, templates, and synthetic worked example
- Task-specific runbook with staged assistant prompts
- Acceptance checks for the supplied case
- Guided usage guide and MIT license
8 files · Guided edition 1.0.0
03 / BUILD AROUND YOUR WORK
A collection for
each area of work.
Category collections include every guided skill in that category. Choose the complete collection if your work spans several areas.
Analysis
19 guided skills
Follow a category from focused input to checked output. Every individual pack in this category is included.
$6.99Save $11.82
AI design
19 guided skills
Follow a category from focused input to checked output. Every individual pack in this category is included.
$6.99Save $11.82
Automation
19 guided skills
Follow a category from focused input to checked output. Every individual pack in this category is included.
$6.99Save $11.82
Customer intelligence
17 guided skills
Follow a category from focused input to checked output. Every individual pack in this category is included.
$6.99Save $9.84
NLP & retrieval
17 guided skills
Follow a category from focused input to checked output. Every individual pack in this category is included.
$6.99Save $9.84
Data engineering
17 guided skills
Follow a category from focused input to checked output. Every individual pack in this category is included.
$6.99Save $9.84
BEFORE YOU CHOOSE
Know what you’re getting.
How do I use a guided edition?
Unzip the pack, open TASK-RUNBOOK.md, and gather the named inputs. Use the instructions and relevant files with your assistant, then check its result against ACCEPTANCE-CHECKS.md. Start with the included synthetic case. An assistant that supports Agent Skills can load the SKILL.md entry point; installation and file support vary.
Does a purchase include an AI service or working integration?
These are AI-assisted instructional packs with templates and synthetic examples. They do not include model access, automatic integrations, or one-to-one support. You supply your assistant and review its output. Compatibility with every assistant has not been tested.
Can I try a sample for free?
Selected starter samples are free to download. The rest of the catalog provides task previews, with full files included in the guided editions offered through this store. Each guided edition adds a task-specific prompt runbook and acceptance checks. All included material uses the MIT license, which permits adaptation and redistribution with the required notices; a purchase does not provide exclusive rights. Rights in previously released MIT copies remain unchanged.
Is this a subscription? Are future updates included?
A guided edition uses a one-time payment for the named version. There is no recurring charge or promise of lifetime updates. The listing and receipt will identify what you purchased.
When can I buy and download the guided files?
Sales have not opened yet. Selected free starter samples are available today. Once checkout opens, the payment provider will deliver the purchased files and a receipt. Questions about the collection? Email Sanjaay.