## New Skills (9) - /quick-design: lightweight spec path for small changes (bypasses full GDD pipeline) - /story-readiness: validates stories are implementation-ready before pickup - /story-done: end-of-story completion review (criteria verification, deviation check, status update) - /sprint-status: fast 30-line sprint snapshot, read-only - /ux-design: guided section-by-section UX spec authoring (screen/flow/HUD/patterns) - /ux-review: UX spec validation with APPROVED/NEEDS REVISION/MAJOR REVISION verdict - /architecture-review, /create-architecture, /create-control-manifest, /create-epics-stories, /propagate-design-change, /review-all-gdds (pipeline completion) ## New Templates (7) - player-journey.md: 6-phase emotional arc, critical moments, retention hooks - difficulty-curve.md: difficulty axes, onboarding ramp, cross-system interactions - ux-spec.md: per-screen UX spec with states, interaction map, data requirements, events - hud-design.md: whole-game HUD with philosophy, info architecture, element specs - accessibility-requirements.md: project-wide accessibility tier commitment and audit - interaction-pattern-library.md: 26 standard + game-specific patterns with full state specs - architecture-traceability.md: GDD requirements to ADR coverage matrix ## Updated Skills & Templates - gate-check: Vertical Slice hard gate, playtesting strengthened, UX artifacts required - team-ui: full UX pipeline integration (/ux-design + /ux-review + accessibility-specialist) - game-design-document: Game Feel section (input latency, animation frames, impact moments) - implementation-agent-protocol: /story-done as explicit final step of every story - architecture-decision, design-system: pipeline completion updates Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
8.3 KiB
name, description, argument-hint, user-invocable, allowed-tools
| name | description | argument-hint | user-invocable | allowed-tools |
|---|---|---|---|---|
| story-done | End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint. | [story-file-path] | true | Read, Glob, Grep, Bash, Edit |
Story Done
This skill closes the loop between design and implementation. Run it at the end of implementing any story. It ensures every acceptance criterion is verified before the story is marked done, GDD and ADR deviations are explicitly documented rather than silently introduced, code review is prompted rather than forgotten, and the story file reflects actual completion status.
Output: Updated story file (Status: Complete) + surfaced next story.
Phase 1: Find the Story
If a file path is provided (e.g., /story-done production/epics/core/story-damage-calculator.md):
read that file directly.
If no argument is provided:
- Check
production/session-state/active.mdfor the currently active story. - If not found there, read the most recent file in
production/sprints/and look for stories marked IN PROGRESS. - If multiple in-progress stories are found, use
AskUserQuestion:- "Which story are we completing?"
- Options: list the in-progress story file names.
- If no story can be found, ask the user to provide the path.
Phase 2: Read the Story
Read the full story file. Extract and hold in context:
- Story name and ID
- GDD Requirement ID(s) referenced
- ADR reference(s) referenced
- Acceptance Criteria — the complete list (every checkbox item)
- Implementation files — files listed under "files to create/modify"
- Engine notes — any engine-specific constraints noted
- Definition of Done — if present, the story-level DoD
- Estimated vs actual scope — if an estimate was noted
Also read:
- The referenced GDD section — just the acceptance criteria and key rules, not the full document
- The referenced ADR(s) — just the Decision and Consequences sections
Phase 3: Verify Acceptance Criteria
For each acceptance criterion in the story, attempt verification using one of three methods:
Automatic verification (run without asking)
- File existence check:
Globfor files the story said would be created. - Test pass check: if a test file path is mentioned, run it via
Bash. - No hardcoded values check:
Grepfor numeric literals in gameplay code paths that should be in config files. - No hardcoded strings check:
Grepfor player-facing strings insrc/that should be in localization files. - Dependency check: if a criterion says "depends on X", check that X exists.
Manual verification with confirmation (use AskUserQuestion)
- Criteria about subjective qualities ("feels responsive", "animations play correctly")
- Criteria about gameplay behaviour ("player takes damage when...", "enemy responds to...")
- Performance criteria ("completes within Xms") — ask if profiled or accept as assumed
Batch up to 4 manual verification questions into a single AskUserQuestion call:
question: "Does [criterion]?"
options: "Yes — passes", "No — fails", "Not tested yet"
Unverifiable (flag without blocking)
- Criteria that require a full game build to test (end-to-end gameplay scenarios)
- Mark as:
DEFERRED — requires playtest session
Phase 4: Check for Deviations
Compare the implementation against the design documents.
Run these checks automatically:
-
GDD rules check: Read the GDD section referenced in the story.
Grepthe implemented files for key function names, data structures, or class names mentioned in the GDD. If the GDD specifies a formula, check for recognizable variable names from that formula. -
ADR constraints check: Read the referenced ADR's Decision section. Check for forbidden patterns from
docs/architecture/control-manifest.md(if it exists).Grepfor patterns explicitly forbidden in the ADR. -
Hardcoded values check:
Grepthe implemented files for numeric literals in gameplay logic that should be in data files. -
Scope check: Did the implementation touch files outside the story's stated scope? (files not listed in "files to create/modify")
For each deviation found, categorize:
- BLOCKING — implementation contradicts the GDD or ADR (must fix before marking complete)
- ADVISORY — implementation drifts slightly from spec but is functionally equivalent (document, user decides)
- OUT OF SCOPE — additional files were touched beyond the story's stated boundary (flag for awareness — may be valid or scope creep)
Phase 5: Code Review Prompt
After criteria verification and deviation check, use AskUserQuestion:
question: "Implementation verified. Run /code-review on the changed files?"
options:
- "Yes — run /code-review now"
- "Skip — I'll review manually"
- "Skip — already reviewed"
If "Yes": list the files to review and say:
"Run /code-review [file1] [file2] to review the implementation before
marking complete."
Do not run code-review inline — surface it and let the developer decide when to invoke it.
Phase 6: Present the Completion Report
Before updating any files, present the full report:
## Story Done: [Story Name]
**Story**: [file path]
**Date**: [today]
### Acceptance Criteria: [X/Y passing]
- [x] [Criterion 1] — auto-verified (test passes)
- [x] [Criterion 2] — confirmed
- [ ] [Criterion 3] — FAILS: [reason]
- [?] [Criterion 4] — DEFERRED: requires playtest
### Deviations
[NONE] OR:
- BLOCKING: [description] — [GDD/ADR reference]
- ADVISORY: [description] — user accepted / flagged for tech debt
### Scope
[All changes within stated scope] OR:
- Extra files touched: [list] — [note whether valid or scope creep]
### Verdict: COMPLETE / COMPLETE WITH NOTES / BLOCKED
Verdict definitions:
- COMPLETE: all criteria pass, no blocking deviations
- COMPLETE WITH NOTES: all criteria pass, advisory deviations documented
- BLOCKED: failing criteria or blocking deviations must be resolved first
If the verdict is BLOCKED: do not proceed to Phase 7. List what must be fixed. Offer to help fix the blocking items.
Phase 7: Update Story Status
Ask before writing: "May I update the story file to mark it Complete and log the completion notes?"
If yes, edit the story file:
- Update the status field:
Status: Complete - Add a
## Completion Notessection at the bottom:
## Completion Notes
**Completed**: [date]
**Criteria**: [X/Y passing] ([any deferred items listed])
**Deviations**: [None] or [list of advisory deviations]
**Code Review**: [Pending / Complete / Skipped]
- If advisory deviations exist, ask: "Should I log these as tech debt in
docs/tech-debt-register.md?"
Phase 8: Surface the Next Story
After completion, help the developer keep momentum:
- Read the current sprint plan from
production/sprints/. - Find stories that are:
- Status: READY or NOT STARTED
- Not blocked by other incomplete stories
- In the Must Have or Should Have tier
Present:
### Next Up
The following stories are ready to pick up:
1. [Story name] — [1-line description] — Est: [X hrs]
2. [Story name] — [1-line description] — Est: [X hrs]
Run `/story-readiness [path]` to confirm a story is implementation-ready
before starting.
If no more stories are ready in this sprint:
"No more stories ready in this sprint. Consider running /sprint-status to
assess sprint health."
If all Must Have stories are complete:
"All Must Have stories are complete. Consider running /milestone-review or
pulling from the Should Have list."
Collaborative Protocol
- Never mark a story complete without user approval — Phase 7 requires an explicit "yes" before any file is edited.
- Never auto-fix failing criteria — report them and ask what to do.
- Deviations are facts, not judgments — present them neutrally; the user decides if they are acceptable.
- BLOCKED verdict is advisory — the user can override and mark complete anyway; document the risk explicitly if they do.
- Use
AskUserQuestionfor the code review prompt and for batching manual criteria confirmations.