create-stories
Skill40 starsChanged 7 months agoMITView on GitHub
Decomposes a single epic into implementable story files. Each story embeds its TR-ID, governing ADR, acceptance criteria, story type, and test-evidence path. Run after /create-epics for each epic, in dependency order. Stories are what developers pick up — epics are what architects define.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Oct 19, 2026
- venus2099/codex-game-studiostheir own version, first seen Oct 17, 2026
- ShiningPlague/shiningplague-studiotheir own version, first seen Oct 11, 2026
- HunLuanZhiZhu/Game-Studios-Plugintheir own version, first seen Oct 5, 2026
- gonimar/claude-web-studiotheir own version, first seen Sep 27, 2026
Used with
Projects with it also use vertical-slice.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
hongyuancSkillvertical-slice
Build and evaluate a production-quality vertical slice before advancing from Pre-Production to Production.
Also in 4 projects that use this
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- striderZA/OpenCodeGameStudios★ 118same name
- dawn840705/codex-code-studios★ 17same name
- lilangMax/ClaudeCodeGameStudios★ 8same name
- hongyuanc/codex-game-studios★ 5same name
- gonimar/claude-web-studio★ 4same name
- dawn840705/claude-code-studios★ 1same name
- HunLuanZhiZhu/Game-Studios-Plugin★ 1same name
- venus2099/codex-game-studios★ 1same name
- ShiningPlague/shiningplague-studio★ 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 repository77 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- design/CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- src/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- adoptSkill
- architecture-decisionSkill
- architecture-reviewSkill
- asset-auditSkill
- asset-specSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- bug-triageSkill
- changelogSkill
- code-reviewSkill
- consistency-checkSkill
- content-auditSkill
- create-architectureSkill
- create-control-manifestSkill
- create-epicsSkill
- day-one-patchSkill
- design-bibleSkill
- design-reviewSkill
- design-systemSkill
- dev-storySkill
- estimateSkill
- extractSkill
- gate-checkSkill
- helpSkill
- hotfixSkill
- launch-checklistSkill
- localizeSkill
- map-systemsSkill
- milestone-reviewSkill
- onboardSkill
- patch-notesSkill
- perf-profileSkill
- prd-reviewSkill
- project-stage-detectSkill
- propagate-design-changeSkill
- prototypeSkill
- qa-planSkill
- quick-designSkill
- regression-suiteSkill
- release-checklistSkill
- retrospectiveSkill
- reverse-documentSkill
- review-all-prdsSkill
- scope-checkSkill
- security-auditSkill
- setup-frameworkSkill
- skill-improveSkill
- skill-testSkill
- smoke-checkSkill
- soak-testSkill
- sprint-planSkill
- sprint-statusSkill
- startSkill
- story-doneSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
If no epics exist, stop and recommend /create-epics.
- Very specific: line 86
If review mode is full, spawn qa-lead (Task) to validate that decomposed stories' acceptance criteria are testable.
- Very specific: line 88
If review mode is lean or solo, skip and proceed.
- Very specific: line 234
Update Section 5 of the epic (Requirements Covered) — fill in the Story slug column.
- Distinctive: line 253
Every story has Status, Type, Manifest Version, TR-ID, ADR reference, Acceptance Criteria, Test Evidence Path
- Distinctive: line 256
Every story's ADR is verified Accepted (else Status: Blocked)
“Common” is measured: kept by at least 6 in 10 of the 10 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
Create Stories
A story is a single implementable behavior — small enough for one focused session, traceable to a TR-ID and an ADR. This skill produces story files that /dev-story and /story-readiness (in the second skill set) will read.
Output: production/epics/<epic-slug>/story-NNN-<slug>.md
Phase 1: Parse Argument
Resolve review mode (--review or production/review-mode.txt, default lean).
Acceptable arg forms:
<epic-slug>(e.g.,auth-sign-in)- Full path to
EPIC.md - Empty — list available epics and ask which
If no epics exist, stop and recommend /create-epics.
Phase 2: Load the Epic & Its World
Read in full:
production/epics/<slug>/EPIC.md- The PRD listed in EPIC Section 2
- Each ADR listed in EPIC Section 3
docs/architecture/control-manifest.md(note Manifest Version)
ADR existence check: confirm every governing ADR file exists on disk. If any is missing, halt:
"Epic references ADR-NNNN but
docs/architecture/ADR-NNNN-...mddoes not exist. Cannot decompose stories until that file is in place. Run/architecture-decisionto create it."
Report: "Loaded epic <name>, PRD <file>, <N> governing ADRs, manifest version <date>."
Phase 3: Classify Story Types
Mobile-app story types:
| Type | Use when criteria reference… |
| Logic | Calculations, validation rules, state transitions, business decisions |
| Integration | Two systems interacting (e.g., auth → push token registration) |
| Visual / Feel | Animation, transitions, motion, "feels responsive", micro-interactions |
| UI | Static screens, menus, settings forms, modals |
| Config / Data | Token / threshold / copy changes only — no new code logic |
| Platform | Framework-specific glue (push setup, biometrics, IAP plumbing) |
Mixed stories: pick the type that carries the highest implementation risk. The type determines the test-evidence requirement.
Phase 4: Decompose
For each PRD Acceptance Criterion in scope:
- Group related criteria that share a single implementation
- Each group = one story
- Order: Foundation behavior → Core → Edge cases → UI polish
Sizing rule: one story = ~2-4 hours. Larger groups split.
For each story, determine:
- Title (action-oriented, e.g., "Implement OAuth login network call")
- TR-ID(s) covered (from
tr-registry.yamlif present, elseTR-<system>-NNN) - Governing ADR:
- Accepted → embed
- Proposed → set Status: Blocked with note "BLOCKED: ADR-NNNN is Proposed. Run
/architecture-decisionto advance."
- Story type (Phase 3)
- Framework risk from the ADR's Framework Compatibility table
- Test evidence path based on type
Phase 5: QA Gate (Review Mode Dependent)
If review mode is full, spawn qa-lead (Task) to validate that decomposed stories' acceptance criteria are testable. Surface findings; iterate until all stories are ADEQUATE.
If review mode is lean or solo, skip and proceed.
For Logic and Integration stories, ask the qa-lead to produce concrete test specs in this format:
Test: <criterion text>
Given: <precondition>
When: <action>
Then: <expected>
Edge cases: <boundary values>For Visual/Feel and UI, produce manual checks:
Manual check: <criterion>
Setup: <how to reach state>
Verify: <what to look for>
Pass: <unambiguous pass>These specs embed in each story's ## QA Test Cases section.
Phase 6: Present Stories Before Writing
## Stories for Epic: <name>
Story 001: Implement OAuth network call — Logic — ADR-0003
Covers: TR-auth-001, TR-auth-002
Test required: tests/unit/auth/oauth-call_test.<ext>
Story 002: Persist refresh token securely — Integration — ADR-0003 + ADR-0007
Covers: TR-auth-003
Test required: tests/integration/auth/token-storage_test.<ext>
Story 003: Login screen layout — UI — ADR-0009
Covers: TR-auth-005, TR-auth-006
UX spec: design/ux/login.md
Evidence required: production/qa/evidence/login-walkthrough.md
[N stories total: <count by type>]Ask AskUserQuestion:
Yes — write all <N> storiesNot yet — review or adjust first
Phase 7: Write Story Files
For each, write production/epics/<slug>/story-NNN-<title>.md:
# Story NNN: <title>
> **Epic**: <epic name>
> **Status**: Ready
> **Layer**: <Foundation / Core / Feature / Polish>
> **Type**: <Logic | Integration | Visual/Feel | UI | Config/Data | Platform>
> **Manifest Version**: <date>
## Context
**PRD**: `design/prd/<system>.md`
**Requirement**: `TR-<system>-NNN`
*(Requirement text in `docs/architecture/tr-registry.yaml` — re-read at review time.)*
**ADR Governing Implementation**: ADR-NNNN: <title>
**ADR Decision Summary**: <1-2 sentence summary>
**Framework**: <name + version> | **Risk**: <LOW / MEDIUM / HIGH>
**Framework Verification Required**: <from ADR Framework Compatibility section>
**Control Manifest Rules (this layer)**:
- Required: <relevant required pattern>
- Forbidden: <relevant forbidden pattern>
- Guardrail: <relevant performance guardrail>
**UX Spec (UI stories)**: `design/ux/<screen>.md` — pinned to commit at story creation
## Acceptance Criteria
*From `design/prd/<system>.md`, scoped to this story:*
- **GIVEN** <state> **WHEN** <action> **THEN** <observable result>
- ...
## QA Test Cases
*Pre-written by `qa-lead` (in `full` review) or by you before implementing.*
[Logic / Integration: GIVEN-WHEN-THEN test specs]
[Visual/Feel / UI: manual verification steps]
## Test Evidence Path
- Type: <Logic | Integration | Visual/Feel | UI | Config/Data | Platform>
- Required path: <e.g., `tests/unit/auth/oauth-call_test.ts`>
- Pass condition: <what passing looks like>
## Mobile-Specific Considerations
- iOS: <if any platform-specific behavior>
- Android: <if any>
- Min OS: <floor>
- Permissions touched: <list or none>
- Analytics events emitted: <list or none>
- Feature flag gating: <flag name or none>
## Out of Scope (this story)
- <items deferred to other stories — link the story numbers when known>
## Definition of Done
- [ ] Implementation matches Acceptance Criteria
- [ ] Test evidence at the specified path passes
- [ ] No control-manifest violations introduced
- [ ] Code review passed (if applicable per review mode)
- [ ] Story status updated to Complete via `/story-done`
## Open Questions
- <any — should be resolved before starting>Phase 8: Update the Epic
Append to the epic's ## 13. Story Backlog section:
## 13. Story Backlog
| Story | Title | Type | Status |
|-------|-------|------|--------|
| 001 | Implement OAuth network call | Logic | Ready |
| 002 | Persist refresh token securely | Integration | Ready |
| 003 | Login screen layout | UI | Ready |
| ... | | | |Update Section 5 of the epic (Requirements Covered) — fill in the Story slug column.
Phase 9: Hand Off
Print:
"
<N>stories written. Update sprint plan via/sprint-planto assign these to a sprint, then start implementation with/dev-story <story-path>."
Use AskUserQuestion:
Run /sprint-plan nowRun /create-stories for the next epicRun /story-readiness <first story>to validate readinessStop here
Quality Gates
- Every story has Status, Type, Manifest Version, TR-ID, ADR reference, Acceptance Criteria, Test Evidence Path
- For UI stories with a UX spec, the UX path is pinned in the story
- Stories sized to ~2-4 hours; warn loudly if any story has 6+ acceptance criteria
- Every story's ADR is verified Accepted (else Status: Blocked)
- The epic's Story Backlog is updated atomically with the story writes
Examples
/create-stories auth-sign-in
- 12 TR-IDs in epic
- 8 stories: 3 Logic, 2 Integration, 2 UI, 1 Platform
- Story 005 references ADR-0007 (biometric) which is Proposed → marked Blocked
- Output: 8 story files + updated EPIC.md
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.

