facilitate-example-mapping
Skill4 starsChanged 3 months agoMITView on GitHub
WHEN/WHERE/WHO: [Scheduling: Business analysts, Product Owners, or agents leading a Backlog Refinement or "Three Amigos" session.] HOW: [Structural: Use this SKILL to decompose a User Story into Business Rules (Blue), Concrete Examples (Green), and Open Questions (Pink).] WHY: [Scheduling: Example Mapping provides a visual breadth-first constraint to flush out unknowns before coding starts.]
In this repository61 other files it gives its agents.
- activate-personalSkill
- analyze-with-tactics-questionnairesSkill
- apply-agile-testing-quadrantsSkill
- apply-architectural-tacticsSkill
- apply-attribute-driven-designSkill
- apply-fundamentals-of-data-visualizationSkill
- apply-oopsi-modelSkill
- apply-screenplay-patternSkill
- apply-specification-by-exampleSkill
- blog-topic-discoverSkill
- build-agent-memory-systemsSkill
- build-business-objectives-modelSkill
- build-data-dictionarySkill
- build-feature-treeSkill
- comment-alive-test-driven-developmentSkill
- conduct-event-stormingSkill
- create-ecosystem-mapSkill
- create-living-documentationSkill
- create-skill-from-bookSkill
- CREATING-SKILL-TEMPLATESkill
- define-architectural-driversSkill
- define-bounded-contextsSkill
- define-ubiquitous-languageSkill
- design-agentic-screenplay-modelSkill
- design-agent-perception-layersSkill
- design-agent-planningSkill
- design-agent-reward-functionsSkill
- design-agents-using-patternsSkill
- design-architecture-viewpointsSkill
- design-autonomous-ai-interfacesSkill
- design-ddd-aggregatesSkill
- design-tool-use-sandboxingSkill
- document-architectural-decisionsSkill
- document-legacy-codebaseSkill
- doc-with-usage-exampleSkill
- draft-srs-documentSkill
- elicit-requirements-modelsSkill
- evolve-skill-with-wikiSkill
- extract-business-rulesSkill
- facilitate-user-story-mappingSkill
- implement-agent-observabilitySkill
- implement-agent-reflectionSkill
- improve-existing-skillSkill
- improve-user-storySkill
- managing-ai-projectsSkill
- orchestrate-multi-agent-collaborationSkill
- prioritize-requirementsSkill
- review-c4-modelSkill
- review-data-engineeringSkill
- save-as-skillSkill
- scaffold-cmake-cxx-sanitize-gtest-envSkill
- skill-commonSkill
- task-commit-triggerSkill
- test-case-with-demoSkill
- test-case-with-readmeSkill
- test-driven-developmentSkill
- UnitTesting-convert2CaTDDSkill
- update-my-resumeSkill
- update-spec-contextSkill
- validate-requirements-criteriaSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
When this skill is activated, first load skill-common and apply the shared conventions it defines: canonical section order, frontmatter …
- Distinctive: line 46
Transfer Check: Verify the workflow still works for both simple stories and larger stories with multiple hidden rules.
- Distinctive: line 47
Stop Rule: If the input is a technical chore rather than business behavior, stop and redirect before building the map.
- Very specific: line 50
Keep it fast. Do not spend time debating the precise Given/When/Then Gherkin syntax during Example Mapping.
- Distinctive: line 51
If there are unresolved Pink cards, the story cannot be moved to development.
- Distinctive: line 54
If the input text is a technical task (e.g., "Upgrade database to Postgres 13"), stop and inform the user that Example Mapping is for …
- Distinctive: line 58
Place the User Story (Yellow) at the top of the map.
- Distinctive: line 84
Verify that every Rule has at least one Example.
- Distinctive: line 85
Verify that the Examples are concrete (using real data/personas) rather than abstract.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Facilitate Example Mapping
Common Contract (Load First)
When this skill is activated, first load skill-common and apply the shared conventions it defines: canonical section order, frontmatter rules, anti-pattern guidance, and the Review In Mind loop in review-in-mind. This skill adds only domain-specific rules below.
Who
Business Analysts, Product Owners, Scrum Masters, and AI Agents. The agent uses this skill to facilitate structured requirements discovery.
What
This skill implements the Example Mapping technique created by Matt Wynne. It is a timeboxed (usually 25-30 minute) workshop where the team breaks a User Story (Yellow card) down into:
- Business Rules (Blue): Known constraints or acceptance criteria.
- Examples (Green): Concrete scenarios that illustrate the rule.
- Questions (Pink): Ambiguities or unknowns that prevent development.
When
Invoke this skill during Backlog Refinement, Sprint Planning, or whenever a new User Story is introduced to the development team. Trigger phrases include: "let's map this story," "do an example mapping," "what are the edge cases," or "break down this user story."
Where
Applies to JIRA User Stories, planning meetings, and PRD reviews.
Why
Traditional requirements sessions often dive too deep into a single edge case, ignoring the rest of the story. Example Mapping forces a breadth-first approach. If you have too many Pink (Question) cards, the story isn't ready. If you have too many Blue (Rule) cards, the story is too big and should be sliced.
Inputs
- A User Story or a high-level feature request.
Output (Logical Evidence)
- A visual or structured text map of the Rules, Examples, and Questions.
- A decision on whether the story is "Ready" for development.
Optimization Readiness
- Failure Signals: The map drifts into technical tasks, examples are abstract, unresolved questions are ignored, or the readiness decision is made before the rule/example balance is understood.
- Evidence To Collect: Rule/example/question cards, readiness decisions, ambiguity notes, and examples showing how counter-examples exposed hidden rules.
- Safe Mutation Boundaries: Refine facilitation prompts, card-color guidance, readiness criteria, and question-handling rules without changing the core breadth-first discovery workflow.
- Acceptance Criteria: Accept revisions only if every rule has concrete examples, uncertainty is surfaced as questions instead of debate, and the final readiness decision follows from the mapped cards.
- Rejected Revision Handling: Record abstract examples, technical-task inputs, and ignored pink-card questions so they are not repeated.
- Transfer Check: Verify the workflow still works for both simple stories and larger stories with multiple hidden rules.
- Stop Rule: If the input is a technical chore rather than business behavior, stop and redirect before building the map.
Constraints (Logical Boundaries)
- Keep it fast. Do not spend time debating the precise Given/When/Then Gherkin syntax during Example Mapping. Use "Friends episode" titles (e.g., "The one where the credit card is expired").
- If there are unresolved Pink cards, the story cannot be moved to development.
One More Thing
If the input text is a technical task (e.g., "Upgrade database to Postgres 13"), stop and inform the user that Example Mapping is for exploring business behavior, not technical chores.
How (Structural Workflow)
Phase 1: The Story
- Place the User Story (Yellow) at the top of the map.
Phase 2: Rules and Examples
- Identify the first Business Rule (Blue) and place it under the story.
- For that rule, ask the team for a concrete Example (Green). Then ask for a counter-example (e.g., a failure case).
- Repeat this process to discover more rules. Often, an attempt to find an example will uncover a hidden rule.
Phase 3: Surfacing Uncertainty
- Whenever the team disagrees, or an assumption cannot be immediately verified, write it down as a Question (Pink) card. Do not debate it.
Phase 4: Review and Slice
- Review the map. If there are too many Rules, propose slicing the story into smaller stories. If there are critical Questions, assign someone to answer them before the next session.
Resources
- Example Mapping Rules
Review In Mind (ReviewInMindGenie)
Execute the common review loop in review-in-mind before delivering.
Review lens for this skill:
- Does the output separate rules, examples, and questions into the correct card types?
- Is every rule supported by at least one concrete example, with open questions explicit?
- Could the team start development without hidden ambiguity?
Validation
- Verify that every Rule has at least one Example.
- Verify that the Examples are concrete (using real data/personas) rather than abstract.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

