story-done
Skill40 starsChanged 7 months agoMITView on GitHub
End-of-story completion review. Verifies each acceptance criterion against the implementation, surfaces deviations, prompts code review if not yet done, marks the story Complete, and surfaces the next ready story. Use after /code-review.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Nov 9, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 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
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 versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- Donchitos/Claude-Code-Game-Studios★ 39ksame 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
- chuanglibs/Claude-Code-Game-Studios-Codex★ 1same name
- dawn840705/claude-code-studios★ 1same name
- HunLuanZhiZhu/Game-Studios-Plugin★ 1same name
- venus2099/codex-game-studios★ 1same name
1 more not listed
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
- create-storiesSkill
- 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
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 4 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
If a path is supplied, use it.
- Distinctive: line 25
Stop and warn if the story file does not exist.
- Distinctive: line 45
If a Test Evidence path is specified, read the test file.
- Very specific: line 81
Look for evidence of /code-review having run on the changed files.
- Distinctive: line 85
If no review is recorded, use AskUserQuestion:
- Very specific: line 91
If [A], run /code-review against the modified files and incorporate the verdict into Phase 6.
- Distinctive: line 135
If verdict is COMPLETE, ask the user:
- Very specific: line 163
If verdict is NEEDS FIXES or BLOCKED, leave the story Status untouched and write a ## Open Issues section into the story file (with user …
- Very specific: line 171
Read the active sprint file (production/sprints/[current-sprint].md or the parent epic).
- Very specific: line 184
If no Ready story exists in the sprint, suggest /sprint-status to inspect sprint state, or /create-stories [next-epic] if the epic is still …
- Very specific: line 208
No automated test required.
“Common” is measured: kept by at least 6 in 10 of the 11 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
Story Done
The closing gate of the per-story loop. Reads the story, audits each acceptance criterion against the actual implementation, ensures evidence is in place, prompts a code review if one is missing, then transitions Status to Complete and points the user at the next ready story.
Phase 1: Resolve the Story
If a path is supplied, use it. Otherwise consult
production/session-state/active.md for an active story, or glob
production/epics/**/*.md and ask the user which one.
Stop and warn if the story file does not exist.
Phase 2: Read Story + Implementation Files
Pull these from the story:
- Story ID, Title, Layer, Type
- TR-ID and Governing ADR
- Acceptance Criteria (every checkbox)
- Implementation Notes
- Test Evidence path
- Out of Scope list
- Status (must be
In ProgressorIn Review; if alreadyComplete, ask the user whether to re-verify)
Glob the most recent edits to src/ to find files modified for this story.
Cross-reference with the session state file. Read each modified file.
If a Test Evidence path is specified, read the test file. If absent for a Logic or Integration story, this is a hard blocker (see Phase 5).
Phase 3: Verify Each Acceptance Criterion
Walk every AC checkbox in order. For each:
| Story Type | Verification method |
| Logic | Locate test function(s) covering the AC; confirm assertions match the AC text; confirm CI run was green. |
| Integration | Locate integration test or documented playtest evidence; confirm the cross-system interaction is exercised. |
| Visual/Feel | Ask the user via AskUserQuestion for sign-off; require an attached screenshot or screen recording in production/qa/evidence/. |
| UI | Ask the user to walk through the flow on a device; require an evidence note or attached screenshot. |
| Config/Data | Confirm a smoke check report exists (production/qa/smoke-[date].md) and the values shipped match the story. |
Mark each AC one of: VERIFIED, DEFERRED (Visual/Feel awaiting user
confirmation), MISSING EVIDENCE, or FAILED.
Phase 4: Check for Deviations
- Out of Scope check: list every modified file. Flag any file outside the Out of Scope boundary as a Deviation. Ask the user to confirm whether it was intentional.
- ADR check: re-read the governing ADR's Implementation Guidelines. Spot any obvious divergence in the diff and surface it.
- Manifest check: confirm the story's Manifest Version stamp still matches the manifest header date.
Phase 5: Code Review Gate
Look for evidence of /code-review having run on the changed files. Look
in the session state file, conversation transcript, or any cached review
artifact.
If no review is recorded, use AskUserQuestion:
[A] Run /code-review now and resume /story-done after[B] Skip the review — accept the risk (NOT recommended)[C] Cancel — I'll come back later
If [A], run /code-review against the modified files and incorporate the
verdict into Phase 6.
Phase 6: Build the Verdict
Compose:
## Story Closing Review: [Story Title] ([Story ID])
### AC Verification
- [x] [AC1 text] — VERIFIED — covered by [test or evidence]
- [x] [AC2 text] — VERIFIED — implemented in [file:function]
- [ ] [AC3 text] — DEFERRED — awaiting Visual/Feel sign-off
- [ ] [AC4 text] — MISSING EVIDENCE — [what's missing]
### Deviations
[None | list with rationale and user confirmation]
### Code Review
[Reference + verdict, or "Not run".]
### Test Evidence
[Path | "Not required for Type: [type]"]
### Verdict: [COMPLETE | NEEDS FIXES | BLOCKED]Verdict rules:
- COMPLETE — every AC is VERIFIED or has user-approved DEFERRED status, no MISSING EVIDENCE, code review APPROVED (or APPROVED WITH SUGGESTIONS), no unresolved out-of-scope changes.
- NEEDS FIXES — one or more ACs FAILED or have MISSING EVIDENCE that the user wants to resolve.
- BLOCKED — fundamental gap (no test for Logic story, ADR violation, scope blowout the user has not acknowledged).
Phase 7: Update Story Status
If verdict is COMPLETE, ask the user:
"May I update [story path] Status to
Completeand stamp the Closed date?"
On approval, edit the story file:
- Set
Status: Complete - Add
Closed: [today's date] Append a closing note section if there were Deviations:
## Closing Notes - [Deviation summary] - Code review verdict: [verdict] - Test evidence: [path]
Append to production/session-state/active.md:
## Story Closed — [date]
- [story path] -> Complete
- ACs verified: [N/M]
- Code review: [verdict]
- Next: [next ready story slug]If verdict is NEEDS FIXES or BLOCKED, leave the story Status untouched
and write a ## Open Issues section into the story file (with user
approval) listing what remains.
Phase 8: Surface the Next Story
Read the active sprint file (production/sprints/[current-sprint].md or
the parent epic). Find the next story whose Status is Ready and whose
Dependencies are all Complete.
Render:
Next ready story: [title] ([path])
- Type: [type]
- Estimated effort: [estimate from story file]
- Run /story-readiness [path] to validate, then /dev-story [path] to start.If no Ready story exists in the sprint, suggest /sprint-status to inspect
sprint state, or /create-stories [next-epic] if the epic is still open.
Quality Gates / PASS-FAIL
- COMPLETE — story passes every gate; Status flipped, session state updated, next story surfaced.
- NEEDS FIXES — at least one AC unverified; story stays open; specific remaining work is documented.
- BLOCKED — fundamental gap; story stays open; user is told exactly which skill to run next.
Examples
Example 1 — A formula change story (Logic):
Reads tests, confirms the unit test file exists and tests the AC's
boundary values, runs /code-review, both pass. Updates Status to
Complete. Surfaces the next Ready story.
Example 2 — A new onboarding screen (UI):
No automated test required. Asks the user to walk through the flow on a
device, requires a screenshot in production/qa/evidence/. The user
confirms two of three ACs and reports a small layout regression on the
third. Verdict: NEEDS FIXES. Story stays open with an Open Issues note.
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.

