user-story-generator
Skill3 starsChanged 4 months agoMITView on GitHub
Generate INVEST-compliant user stories from epics or requirements with clear value statements and story point guidance. Use when working on product discovery, PRDs, user stories, OKRs, or backlog planning.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- imohammadfaraz/claude-skills-for-product-managertheir own version, first seen Nov 1, 2026
- nek1987/auto-agent-harnesstheir own version, first seen Oct 11, 2026
- CreativeActtech/llm-skillstheir own version, first seen Oct 8, 2026
- SajidRahman-BS/Project-Initiation-Assistanttheir own version, first seen Jul 7, 2026
- lenar-amirov/product-pipeline-publictheir own version, first seen Jul 4, 2026
- vbrevik/claude_code_skillstheir own version, first seen Mar 14, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- imohammadfaraz/claude-skills-for-product-manager★ 19same name
- lenar-amirov/product-pipeline-public★ 13same name
- nek1987/auto-agent-harness★ 4same name
- CreativeActtech/llm-skills★ 2same name
- SajidRahman-BS/Project-Initiation-Assistant★ 0same name
- vbrevik/claude_code_skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository59 other files it gives its agents.
- agent-memory-designerSkill
- ai-cost-optimizerSkill
- ai-evaluation-builderSkill
- ai-latency-optimizerSkill
- ai-solution-architectSkill
- ai-workflow-builderSkill
- context-engineeringSkill
- human-in-the-loop-designerSkill
- multi-agent-plannerSkill
- prompt-engineerSkill
- prompt-optimizerSkill
- prompt-reviewerSkill
- adr-generatorSkill
- api-designerSkill
- architecture-reviewSkill
- component-diagram-builderSkill
- container-diagram-builderSkill
- data-flow-analyzerSkill
- integration-plannerSkill
- observability-plannerSkill
- scalability-advisorSkill
- solution-architectureSkill
- system-context-builderSkill
- experiment-designerSkill
- go-to-market-plannerSkill
- pricing-strategy-advisorSkill
- mcp-best-practicesSkill
- mcp-client-generatorSkill
- mcp-security-reviewSkill
- mcp-server-generatorSkill
- mcp-tool-generatorSkill
- acceptance-criteria-generatorSkill
- analytics-instrumentation-plannerSkill
- competitive-analysisSkill
- epic-generatorSkill
- feature-prioritizationSkill
- idea-validatorSkill
- north-star-metric-advisorSkill
- okr-builderSkill
- persona-generatorSkill
- prd-generatorSkill
- problem-statement-builderSkill
- product-discovery-assistantSkill
- product-vision-builderSkill
- sprint-plannerSkill
- story-mappingSkill
- value-proposition-designerSkill
- chunking-strategy-advisorSkill
- embedding-strategy-advisorSkill
- hybrid-search-advisorSkill
- knowledge-ingestion-plannerSkill
- rag-architecture-designerSkill
- retriever-optimizerSkill
- ai-governance-advisorSkill
- ai-threat-modelingSkill
- guardrails-builderSkill
- owasp-llm-reviewerSkill
- prompt-injection-detectorSkill
- skill-nameSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 110
Leave acceptance criteria to acceptance-criteria-generator.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
User Story Generator
Purpose
Generate INVEST-compliant user stories from epics or requirements with clear value statements and story point guidance.
Input: Epic description, story themes, or FR list; persona (optional)
Output: User story set with IDs, INVEST validation, and dependency notes
Examples: See examples.md for worked input/output.
Workflow
Step 1: Identify story sources
Extract story candidates from:
- Epic story themes
- PRD functional requirements
- User flows (one story per flow step if appropriate)
Step 2: Write stories in standard format
As a [persona] I want [action] so that [benefit]
Each story must:
- Reference a specific persona (not "user")
- Describe desired behavior, not implementation
- State measurable benefit in "so that" clause
Step 3: Apply INVEST criteria
| Criterion | Check |
| Independent | Can be developed without other stories |
| Negotiable | Details open for discussion |
| Valuable | Delivers user or business value |
| Estimable | Team can estimate size |
| Small | Completable in one sprint |
| Testable | Acceptance criteria can be written |
Flag stories failing any criterion with fix recommendation.
Step 4: Assign metadata
For each story:
- ID: US-001, US-002...
- Epic reference
- Priority: Must / Should / Could
- Size hint: S / M / L (not hours)
- Dependencies: other story IDs
Step 5: Validate
Run Validation checklist.
Decision Rules
| Condition | Action |
| Story describes implementation | Rewrite as user behavior |
| Story too large (fails Small) | Split into multiple stories |
| Story has no persona | Use persona from input or request one |
| "So that" is vague | Rewrite with measurable outcome |
| Stories are not independent | Document dependency; consider merge or reorder |
Validation
- All stories follow As/Want/So format
- INVEST check completed for each story
- Each story has unique ID and epic reference
- No implementation details in story text
- Dependencies explicitly documented
- Size hints provided (S/M/L)
- Stories failing INVEST have fix notes
Anti-patterns
- Technical stories as user stories — "As a developer I want to set up Redis."
- Epic-sized stories — "As a user I want the entire dashboard."
- No benefit clause — missing or generic "so that I can use the app."
- Generic persona — "As a user" without specificity.
- Untestable stories — no observable behavior to verify.
Best Practices
- One story = one testable behavior change.
- Split by workflow step, not by technical layer.
- Align stories with epic goal; reject orphan stories.
- Leave acceptance criteria to acceptance-criteria-generator.
- Group related stories under epic headers in output.
Output Structure
# User Stories: [Epic Name]
## Epic Reference
[Epic goal and ID]
## Stories
### US-001: [Short title]
**As a** [persona] **I want** [action] **so that** [benefit]
| Attribute | Value |
|-----------|-------|
| Priority | Must |
| Size | M |
| Dependencies | none |
| INVEST | Pass / Fail (note) |
[Repeat for each story]
## Dependency Map
US-001 → US-003
## Stories Needing Split
| Story | Issue | Suggested split |
|-------|-------|-----------------|Next Skills
| Outcome | Recommended Skill |
| Add acceptance criteria | product/acceptance-criteria-generator |
| Visualize story sequence | product/story-mapping |
| Need epics first | product/epic-generator |
| Sprint planning | product/acceptance-criteria-generator |
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.

