Removes the deprecated skill entirely and updates every reference across: - README.md, UPGRADING.md (skill count + file lists) - docs/WORKFLOW-GUIDE.md (pipeline diagrams, step descriptions, command reference) - docs/examples/skill-flow-diagrams.md, session-*.md - docs/architecture/tr-registry.yaml - tests/skills/catalog.yaml - .claude/skills: adopt, content-audit, create-control-manifest, skill-test, story-readiness - .claude/docs: skills-reference.md, quick-start.md Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
8.8 KiB
Example Session: /adopt — Brownfield Project Onboarding
Context: Developer has been building a game for 3 months before discovering this agent system. They have code, some design docs, and rough notes — but nothing in the right format for the skills to use.
Starting State:
src/gameplay/— ~4000 lines of Godot 4.6 GDScriptdesign/— 3 markdown files with rough design notes (not in GDD template format)- No
design/gdd/directory - No
docs/architecture/directory - No
production/directory - No
design/gdd/systems-index.md - CLAUDE.md exists (engine configured: Godot 4.6)
Session Duration: ~30 minutes Turns: 8 Outcome: Adoption plan written, most urgent gap (missing system index) fixed immediately
Turn 1: User Invokes /adopt
User:
/adopt
Turn 2: Agent Detects Project State
Agent (technical-director, via /adopt, context: fork):
Running brownfield audit...
Phase 1: Project State Detection
Artifact Category Found Notes Engine configuration ✅ Godot 4.6 in CLAUDE.md Source code ✅ ~4000 lines in src/gameplay/Design docs ⚠️ 3 files in design/, not in GDD formatArchitecture docs ❌ docs/architecture/missingSystems index ❌ design/gdd/systems-index.mdmissingProduction tracking ❌ production/directory missingSprint/story files ❌ None Phase 2: Format Audit (existing files)
Checking internal structure of the 3 design files...
design/combat-notes.md:
- Has informal notes, no GDD template sections
- Contains: some rule descriptions, a damage formula, rough balance numbers
- Missing from GDD template: Overview, Player Fantasy, Edge Cases, Dependencies, Tuning Knobs, Acceptance Criteria (6 of 8 sections)
design/crafting-ideas.md:
- Brainstorm-style notes, no structure
- No formulas, no acceptance criteria
- Represents early concept thinking — useful as input for a GDD, not yet a GDD
design/inventory.md:
- Closest to a GDD — has Overview and Rules sections
- Missing: Player Fantasy, Formulas, Edge Cases, Tuning Knobs, Acceptance Criteria (5 of 8 sections)
Phase 3: Gap Classification
Gap Severity Reason No systems index BLOCKING /design-system,/create-stories,/gate-checkall require itGDD files not in template format HIGH Skills cannot reference TR-IDs from malformed GDDs No architecture docs HIGH Cannot run /architecture-reviewor/create-control-manifestNo production tracking MEDIUM Sprint and story skills won't work, but not needed until production phase design/crafting-ideas.md— pre-GDD contentLOW Useful as input; needs full GDD authoring before it blocks anything
Turn 3: Agent Presents the Migration Plan
Agent:
Phase 4: Migration Plan
7 ordered steps to bring your project into full alignment. NEVER overwrites your existing content — each step fills gaps only.
# Step Skill Priority Notes 1 Create design/gdd/systems-index.md/map-systemsor/adoptinlineBLOCKING Unblocks all downstream skills 2 Retrofit design/inventory.md→ GDD format/design-system retrofit design/inventory.mdHIGH Adds 5 missing sections, keeps your existing content 3 Retrofit design/combat-notes.md→ GDD format/design-system retrofit design/combat-notes.mdHIGH Adds 6 missing sections 4 Convert design/crafting-ideas.md→ full GDD/design-system crafting(new authoring, uses ideas as input)MEDIUM Not a retrofit — too informal to retrofit 5 Create architecture ADRs from existing code /reverse-document+/architecture-decisionHIGH Captures decisions already made in code 6 Create master architecture document /create-architectureHIGH After ADRs 7 Set up production tracking /sprint-plan newMEDIUM After architecture phase Important: Step 1 must happen before any other step. Everything else can be done in parallel or reordered based on your priorities.
May I write this plan to
docs/adoption-plan-2026-03-12.md?
User:
Yes. Write it.
Agent writes adoption plan.
Turn 4: Agent Offers to Fix the Most Urgent Gap
Agent:
The BLOCKING gap is the missing
design/gdd/systems-index.md.I can create one now by reading your existing code and design docs to infer what systems you've built. This is faster than running
/map-systemsfrom scratch — I'll populate it based on what already exists, then you confirm or adjust.Would you like me to do that now?
User:
Yes, do it.
Turn 5: Agent Reads Codebase and Drafts Systems Index
Agent:
Reading
src/gameplay/to infer systems...Found these system boundaries in the code:
src/gameplay/combat/— damage calculation, hit detection, status effectssrc/gameplay/inventory/— item management, weight, stackssrc/gameplay/crafting/— recipe lookup, result generation (references inventory)src/gameplay/movement/— CharacterBody2D, terrain modifiers (referenced by combat for positioning)src/gameplay/ui/— HUD, inventory screen, dialogue boxsrc/gameplay/world/— tile map, terrain types, chunk loadingDraft systems index:
System Category Priority Dependencies GDD Status Movement Foundation MVP None ❌ Missing World/Terrain Foundation MVP Movement ❌ Missing Combat Core MVP Movement ⚠️ Needs retrofit Inventory Core MVP None ⚠️ Needs retrofit Crafting Feature MVP Inventory ❌ Pre-GDD only UI / HUD Presentation MVP Combat, Inventory, Movement ❌ Missing Does this look right? Anything I missed or miscategorized?
User:
Looks right. Add a Stamina system — it's in combat/ but should be its own system.
Agent:
Added Stamina as a Core / MVP system:
| Stamina | Core | MVP | Movement, Combat | ❌ Missing |
Updated dependency: Movement depends on Stamina (movement drains it).
May I write this to
design/gdd/systems-index.md?
Turn 6: User Approves
User:
Yes
Agent writes design/gdd/systems-index.md.
Turn 7: Agent Shows What's Now Unlocked
Agent:
design/gdd/systems-index.mdcreated.BLOCKING gap resolved. The following skills can now run:
- ✅
/design-system [name]— guided GDD authoring for any system- ✅
/design-system retrofit [path]— fill missing sections in existing docs- ✅
/gate-check— now has a systems index to validate- ✅
/help— can now show correct phase workflowRecommended next steps (from adoption plan):
- Run
/design-system retrofit design/inventory.md— your most complete existing doc, easiest win- Run
/design-system retrofit design/combat-notes.md- Run
/design-system crafting— author crafting GDD using your ideas file as inputAfter those 3, you'll have 5 of 7 systems with complete GDDs. Then run
/review-all-gddsto catch cross-system consistency issues before architecture work.
Turn 8: User Confirms Plan
User:
Perfect. I'll start with the inventory retrofit.
Agent:
Run:
/design-system retrofit design/inventory.mdThe skill will detect your existing Overview and Rules sections, show you which of the 8 sections are missing, and run the section cycle only for the gaps. Your existing content won't be touched.
What This Example Demonstrates
- FORMAT audit, not existence audit:
/adoptdoesn't just check whether files exist — it checks whether their internal structure matches what skills expect. A file namedgdd.mdwith no template sections is flagged as a gap. - Migration, not replacement: existing content is never overwritten. The plan fills gaps only.
- BLOCKING gaps surface first: the missing systems index is identified as BLOCKING because it prevents the most skills from functioning.
- Inline creation of the urgent gap: rather than just reporting the gap, the agent offers to fix it immediately in the same session.
- Inferred from code: the systems index is bootstrapped from the codebase structure, not written from scratch — brownfield code already contains the answer.
- Retrofit vs. new authoring:
/design-system retrofithandles existing-but-incomplete docs; full/design-systemhandles net-new docs. The adoption plan distinguishes which applies to each file. - Context: fork:
/adoptruns in a forked context to avoid polluting the main session with large file reads across the whole codebase.