Elgato_dark/Claude-Code-Game-Studios
1
0
Fork 0
mirror of https://github.com/Donchitos/Claude-Code-Game-Studios synced 2026-04-21 21:37:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
Claude-Code-Game-Studios/CCGS Skill Testing Framework/templates/skill-test-spec.md
Donchitos a73ff759c9 Add v0.5.0: CCGS Skill Testing Framework, skill-improve, 4 new skills, director gate path fixes 
- Add CCGS Skill Testing Framework: self-contained QA layer with 72 skill specs,
  49 agent specs, catalog.yaml, quality-rubric.md, templates, README, CLAUDE.md
- Add /skill-improve: test-fix-retest loop covering static + category checks
- Add 4 missing skills: /art-bible, /asset-spec, /day-one-patch, /security-audit
- Add /skill-test category mode (Phase 2D) with quality rubric evaluation
- Extend /skill-test audit to cover agent specs alongside skill specs
- Update all skill-test and skill-improve path refs to CCGS Skill Testing Framework/
- Remove stale tests/skills/ directory (superseded by CCGS Skill Testing Framework)
- Add director gate intensity modes (full/lean/solo) to gate-check and related skills

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-06 17:42:32 +10:00

3.5 KiB
Raw Blame History

Skill Spec: /[skill-name]

Category: [gate | review | authoring | readiness | pipeline | analysis | team | sprint | utility] Priority: [critical | high | medium | low] Spec written: [YYYY-MM-DD]

Skill Summary

[One paragraph describing what this skill does, what inputs it takes, and what outputs it produces.]

Static Assertions

These should pass before any behavioral testing:

  • Frontmatter has all required fields (name, description, argument-hint, user-invocable, allowed-tools)
  • 2+ phase headings found
  • At least one verdict keyword present (PASS, FAIL, CONCERNS, APPROVED, BLOCKED, COMPLETE, READY)
  • If allowed-tools includes Write/Edit: "May I write" language present
  • Next-step handoff section present at end

Director Gate Checks

[Describe which director gates this skill triggers (if any), and under what review mode conditions.]

  • Full mode: [gates triggered — e.g., CD-PHASE-GATE, TD-PHASE-GATE, PR-PHASE-GATE, AD-PHASE-GATE]
  • Lean mode: [phase gates only — e.g., CD-PHASE-GATE only, or none]
  • Solo mode: [no gates — skill runs without director review]
  • N/A: [if this skill never triggers gates, explain why]

Test Cases

Case 1: Happy Path — [brief name]

Fixture (assumed project state):

  • [file/condition 1]
  • [file/condition 2]

Expected behavior:

  1. [Step 1]
  2. [Step 2]
  3. [Step 3]

Assertions:

  • [Assertion 1]
  • [Assertion 2]
  • [Assertion 3]

Case Verdict: PASS / FAIL / PARTIAL

Case 2: Failure / Blocked — [brief name]

Fixture:

  • [missing or invalid condition]

Expected behavior:

  1. [Skill detects the problem]
  2. [Skill reports FAIL/BLOCKED]
  3. [Skill does NOT proceed]

Assertions:

  • Skill stops early and does not produce output
  • Correct error/block message displayed
  • No files written without user approval

Case Verdict: PASS / FAIL / PARTIAL

Case 3: Mode Variant — [brief name]

Fixture:

  • [standard project state]
  • [specific mode or flag set]

Expected behavior:

  1. [Behavior differs from happy path because of mode]

Assertions:

  • [Mode-specific assertion]
  • [Output differs correctly from Case 1]

Case Verdict: PASS / FAIL / PARTIAL

Case 4: Edge Case — [brief name]

Fixture:

  • [unusual or boundary condition]

Expected behavior:

  1. [Skill handles gracefully]

Assertions:

  • [Edge case handled without crash or silent failure]
  • [Correct output or message]

Case Verdict: PASS / FAIL / PARTIAL

Case 5: Director Gate — [brief name]

Fixture:

  • [project state that triggers a gate check]
  • Review mode: [full | lean | solo]

Expected behavior:

  1. [Gate fires / does not fire based on mode]
  2. [Correct director agents spawned or skipped]

Assertions:

  • In full mode: [specific gates spawn]
  • In lean mode: [phase gates only, or skip]
  • In solo mode: no director gates spawn
  • Skill does not auto-advance past a CONCERNS or FAIL verdict

Case Verdict: PASS / FAIL / PARTIAL

Protocol Compliance

  • Uses "May I write" before any file writes (or is read-only and skips this)
  • Presents findings/draft to user before requesting approval
  • Ends with a recommended next step or follow-up action
  • Does not auto-create files without user approval

Coverage Notes

[Any gaps in coverage, known edge cases not tested, or conditions that would require a live skill run to verify.]