mirror of
https://github.com/Donchitos/Claude-Code-Game-Studios.git
synced 2026-06-27 04:51:46 +00:00
Add v0.6.0: full skill/agent QA pass, 3 new agents tested, template cleanup
Skills fixed: sprint-status (stale escalation, threshold), retrospective (existing file detection, missing data fallback), changelog (misc category, task-ref count), patch-notes (BLOCKED on missing changelog, tone/template paths), story-readiness (Phase 0 mode resolution, QL-STORY-READY gate), art-bible, brainstorm, design-system, ux-design, dev-story, story-done, create-architecture, create-control-manifest, map-systems, propagate-design-change, quick-design, prototype, asset-spec. Agents fixed: all 4 directors (gate verdict token format), engine-programmer, ui-programmer, tools-programmer, technical-artist (engine version safety), gameplay-programmer (ADR compliance), godot-gdextension-specialist (ABI warning), systems-designer (escalation path to creative-director), accessibility-specialist (model, tools, WCAG criterion format, findings template), live-ops-designer (escalation paths, battle pass value language), qa-tester (model, test case format, evidence routing, ambiguous criteria, regression scope). Specs updated: smoke-check and adopt specs rewritten to match actual skill behavior. catalog.yaml reset to blank template state. Removed session-state marketing research file, removed session-state from gitignore. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -3,7 +3,7 @@ name: create-control-manifest
|
||||
description: "After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why)."
|
||||
argument-hint: "[update — regenerate from current ADRs]"
|
||||
user-invocable: true
|
||||
allowed-tools: Read, Glob, Grep, Write
|
||||
allowed-tools: Read, Glob, Grep, Write, Task
|
||||
agent: technical-director
|
||||
---
|
||||
|
||||
@@ -116,6 +116,30 @@ Ask: "Does this look complete? Any rules to add or remove before I write the man
|
||||
|
||||
---
|
||||
|
||||
## 4b. Director Gate — Technical Review
|
||||
|
||||
**Review mode check** — apply before spawning TD-MANIFEST:
|
||||
- `solo` → skip. Note: "TD-MANIFEST skipped — Solo mode." Proceed to Phase 5.
|
||||
- `lean` → skip. Note: "TD-MANIFEST skipped — Lean mode." Proceed to Phase 5.
|
||||
- `full` → spawn as normal.
|
||||
|
||||
Spawn `technical-director` via Task using gate **TD-MANIFEST** (`.claude/docs/director-gates.md`).
|
||||
|
||||
Pass: the Control Manifest Preview from Phase 4 (rule counts per layer, full extracted rule list), the list of ADRs covered, engine version, and any rules sourced from technical-preferences.md or engine reference docs.
|
||||
|
||||
The technical-director reviews whether:
|
||||
- All mandatory ADR patterns are captured and accurately stated
|
||||
- Forbidden approaches are complete and correctly attributed
|
||||
- No rules were added that lack a source ADR or preference document
|
||||
- Performance guardrails are consistent with the ADR constraints
|
||||
|
||||
Apply the verdict:
|
||||
- **APPROVE** → proceed to Phase 5
|
||||
- **CONCERNS** → surface via `AskUserQuestion` with options: `Revise flagged rules` / `Accept and proceed` / `Discuss further`
|
||||
- **REJECT** → do not write the manifest; fix the flagged rules and re-present the summary
|
||||
|
||||
---
|
||||
|
||||
## 5. Write the Control Manifest
|
||||
|
||||
Ask: "May I write this to `docs/architecture/control-manifest.md`?"
|
||||
|
||||
Reference in New Issue
Block a user