* Add /vertical-slice skill, prototype overhaul, and workflow integration - Add /vertical-slice skill for pre-production validation (Phase 4 gate) - Overhaul /prototype skill with two-mode design: concept prototype (Phase 1) vs vertical slice (Phase 4), with clearer differentiation and higher standards for VS - Update prototyper agent to own both prototype and vertical-slice workflows - Add prototype-report.md and vertical-slice-report.md output templates - Update WORKFLOW-GUIDE, quick-start, skills-reference, agent-coordination-map, and skill-flow-diagrams to fully integrate both skills into the 7-phase pipeline - Remove orphaned empty quick-prototype/ directory Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * sync v1 counts + polish Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add entity inventory flow, relax vertical-slice gate, improve UX authoring prompts - /asset-spec: new Phase 0b entity & screen inventory when no argument and no existing inventory — reads GDDs/art-bible, proposes categorized list, writes design/assets/entity-inventory.md collaboratively - /asset-spec: entity/character target falls back to inline user description when no source doc exists, rather than failing - /gate-check: vertical slice changed from blocking to CONCERNS-only when absent; built-but-broken slice still fails; adds entity inventory as gate artifact - /ux-design: convert inline approval prompts to AskUserQuestion for structured option capture at key authoring decision points - workflow-catalog.yaml: entity-inventory step added to pre-production; UX spec min_count raised to 3; vertical-slice and prototype marked required: false with updated descriptions - .gitignore: exclude marrow/ eval tooling directory Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * Add missing AskUserQuestion widgets to 7 skills Audit found 11 decision points across 7 skills where structured option prompts were missing — using plain text, auto-selection, or no gate at all. Skills patched: - create-epics: per-epic approval + producer CONCERNS verdict - sprint-plan: producer CONCERNS verdict with scope/timeline options - milestone-review: AT RISK / OFF TRACK producer verdicts require acknowledgement - retrospective: existing-retro handling converted from plain text [A]/[B] - quick-design: classification confirmation + draft approve/revise/redirect - tech-debt add mode: category (6 options) + effort (S/M/L/XL) structured capture - regression-suite: no-arg mode selection instead of silent auto-detect - hotfix: severity confirmation gate before workflow begins Also added AskUserQuestion to allowed-tools headers for retrospective, quick-design, tech-debt, regression-suite, and hotfix. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * Prep v1 stable: fix WORKFLOW-GUIDE counts, stale agent names, and skill model fields - WORKFLOW-GUIDE.md: correct agent count (48→49), skill count (66/68→73), add 6 missing skills to Appendix B, fix Creative category count (2→4), replace 3 non-existent agent names with correct ue-*/unity-* specialists, add missing godot-csharp/gdextension specialists to hierarchy, fix production/stories/ paths → production/epics/ - coordination-rules.md: replace "not yet used" with opt-in env var note - quick-start.md: rename duplicate "Validate the concept" label → "Prototype the mechanic" - skill-flow-diagrams.md: remove duplicate legacy UX pipeline section - All 62 skills missing model: field now have explicit model: sonnet Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: comprehensive skill audit — consistency, UX, and flow gaps Two-pass audit fixing ~35 bugs across 41 files. Pre-production flow: - Brainstorm next-steps split into Path A (design-first) and Path B (prototype-first) — eliminates "prototype after architecture" confusion - /architecture-review added to pre-production flow in brainstorm and create-architecture handoffs - gate-check traceability check corrected to requirements-traceability.md - dev-story TR registry error now points to /architecture-review (not /create-epics) - start now writes production/stage.txt on first onboarding AskUserQuestion gaps filled: - balance-check, code-review, hotfix, day-one-patch, consistency-check all gain closing widgets and/or missing allowed-tools declarations - hotfix git branch creation now requires user confirmation - sprint-plan review-mode setup moved to Phase 0 (before gates run) - team-combat gains architecture→implementation approval gate - design-review APPROVED path consolidated from 3 widgets to 1 multiSelect All 9 team-* skills: - Phase 0 review-mode resolution added (solo/lean/full now respected) - team-audio output path fixed (design/gdd/ → design/audio/) - team-level final doc compilation delegated to level-designer subagent - team-narrative localization-lead added to composition list - team-qa sprint path fixed (flat files, not directories) - team-release NO-GO override captures written justification - team-live-ops Cancel verdict now explicitly BLOCKED Other fixes: - Art bible path standardized to design/art/art-bible.md (3 wrong refs) - AD-PHASE-GATE added to lean-mode skip list in director-gates.md - design-system duplicate 5d heading fixed; skeleton decline path added; mandatory agent spawns now respect review mode - story-readiness acceptance criteria thresholds now type-aware - create-stories gains multi-ADR and no-ADR handling guidance - consistency-check creates docs/consistency-failures.md on first run - retrospective frontmatter bash injection replaced with explicit Bash call - smoke-check ls -t gains PowerShell fallback - Conventional Commits format documented in coding-standards.md - gate-check: ADR acceptance gate, QA plan check, chain-of-verification tool-action requirement all added Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: expose --review flag in argument-hints for all team-* skills All 9 team-* skills already implement Phase 0 review-mode resolution internally (full/lean/solo), but none advertised [--review full|lean|solo] in their argument-hint. Users had no way to discover the per-run override. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs: add SECURITY.md with coordinated disclosure policy Defines scope, reporting process (GitHub private vulnerability reporting), contributor security guidelines for hooks/skills/agents, and 90-day coordinated disclosure timeline. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs: add CONTRIBUTING.md with framework contribution guidelines Covers what PRs are welcome, skill/hook/agent technical requirements, the collaborative principle, testing expectations, commit format, and platform compatibility requirements. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs: add v1.0.0-beta → v1.0 upgrade section to UPGRADING.md Documents the 17 commits since the beta tag: new /vertical-slice gate, entity inventory flow in /map-systems, AskUserQuestion widgets across 7 skills, --review flag exposure on team-* skills, bug fixes (#21, #36, #42, #43, #45), and the new CONTRIBUTING.md and SECURITY.md. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
10 KiB
name, description, argument-hint, user-invocable, allowed-tools, model
| name | description | argument-hint | user-invocable | allowed-tools | model |
|---|---|---|---|---|---|
| consistency-check | Scan all GDDs against the entity registry to detect cross-document inconsistencies: same entity with different stats, same item with different values, same formula with different variables. Grep-first approach — reads registry then targets only conflicting GDD sections rather than full document reads. | [full | since-last-review | entity:<name> | item:<name>] | true | Read, Glob, Grep, Write, Edit, Bash, AskUserQuestion | sonnet |
Consistency Check
Detects cross-document inconsistencies by comparing all GDDs against the
entity registry (design/registry/entities.yaml). Uses a grep-first approach:
reads the registry once, then targets only the GDD sections that mention
registered names — no full document reads unless a conflict needs investigation.
This skill is the write-time safety net. It catches what /design-system's
per-section checks may have missed and what /review-all-gdds's holistic review
catches too late.
When to run:
- After writing each new GDD (before moving to the next system)
- Before
/review-all-gdds(so that skill starts with a clean baseline) - Before
/create-architecture(inconsistencies poison downstream ADRs) - On demand:
/consistency-check entity:[name]to check one entity specifically
Output: Conflict report + optional registry corrections
Phase 1: Parse Arguments and Load Registry
Modes:
- No argument /
full— check all registered entries against all GDDs since-last-review— check only GDDs modified since the last review reportentity:<name>— check one specific entity across all GDDsitem:<name>— check one specific item across all GDDs
Load the registry:
Read path="design/registry/entities.yaml"
If the file does not exist or has no entries:
"Entity registry is empty. Run
/design-systemto write GDDs — the registry is populated automatically after each GDD is completed. Nothing to check yet."
Stop and exit.
Build four lookup tables from the registry:
- entity_map:
{ name → { source, attributes, referenced_by } } - item_map:
{ name → { source, value_gold, weight, ... } } - formula_map:
{ name → { source, variables, output_range } } - constant_map:
{ name → { source, value, unit } }
Count total registered entries. Report:
Registry loaded: [N] entities, [N] items, [N] formulas, [N] constants
Scope: [full | since-last-review | entity:name]
Phase 2: Locate In-Scope GDDs
Glob pattern="design/gdd/*.md"
Exclude: game-concept.md, systems-index.md, game-pillars.md — these are
not system GDDs.
For since-last-review mode:
git log --name-only --pretty=format: -- design/gdd/ | grep "\.md$" | sort -u
Limit to GDDs modified since the most recent design/gdd/gdd-cross-review-*.md
file's creation date.
Report the in-scope GDD list before scanning.
Phase 3: Grep-First Conflict Scan
For each registered entry, grep every in-scope GDD for the entry's name. Do NOT do full reads — extract only the matching lines and their immediate context (-C 3 lines).
This is the core optimization: instead of reading 10 GDDs × 400 lines each (4,000 lines), you grep 50 entity names × 10 GDDs (50 targeted searches, each returning ~10 lines on a hit).
3a: Entity Scan
For each entity in entity_map:
Grep pattern="[entity_name]" glob="design/gdd/*.md" output_mode="content" -C 3
For each GDD hit, extract the values mentioned near the entity name:
- any numeric attributes (counts, costs, durations, ranges, rates)
- any categorical attributes (types, tiers, categories)
- any derived values (totals, outputs, results)
- any other attributes registered in entity_map
Compare extracted values against the registry entry.
Conflict detection:
- Registry says
[entity_name].[attribute] = [value_A]. GDD says[entity_name] has [value_B]. → CONFLICT - Registry says
[item_name].[attribute] = [value_A]. GDD says[item_name] is [value_B]. → CONFLICT - GDD mentions
[entity_name]but doesn't specify the attribute. → NOTE (no conflict, just unverifiable)
3b: Item Scan
For each item in item_map, grep all GDDs for the item name. Extract:
- sell price / value / gold value
- weight
- stack rules (stackable / non-stackable)
- category
Compare against registry entry values.
3c: Formula Scan
For each formula in formula_map, grep all GDDs for the formula name. Extract:
- variable names mentioned near the formula
- output range or cap values mentioned
Compare against registry entry:
- Different variable names → CONFLICT
- Output range stated differently → CONFLICT
3d: Constant Scan
For each constant in constant_map, grep all GDDs for the constant name. Extract:
- Any numeric value mentioned near the constant name
Compare against registry value:
- Different number → CONFLICT
Phase 4: Deep Investigation (Conflicts Only)
For each conflict found in Phase 3, do a targeted full-section read of the conflicting GDD to get precise context:
Read path="design/gdd/[conflicting_gdd].md"
(Or use Grep with wider context if the file is large)
Confirm the conflict with full context. Determine:
- Which GDD is correct? Check the
source:field in the registry — the source GDD is the authoritative owner. Any other GDD that contradicts it is the one that needs updating. - Is the registry itself out of date? If the source GDD was updated after the registry entry was written (check git log), the registry may be stale.
- Is this a genuine design change? If the conflict represents an intentional design decision, the resolution is: update the source GDD, update the registry, then fix all other GDDs.
For each conflict, classify:
- 🔴 CONFLICT — same named entity/item/formula/constant with different values in different GDDs. Must resolve before architecture begins.
- ⚠️ STALE REGISTRY — source GDD value changed but registry not updated. Registry needs updating; other GDDs may be correct already.
- ℹ️ UNVERIFIABLE — entity mentioned but no comparable attribute stated. Not a conflict; just noting the reference.
Phase 5: Output Report
## Consistency Check Report
Date: [date]
Registry entries checked: [N entities, N items, N formulas, N constants]
GDDs scanned: [N] ([list names])
---
### Conflicts Found (must resolve before architecture)
🔴 [Entity/Item/Formula/Constant Name]
Registry (source: [gdd]): [attribute] = [value]
Conflict in [other_gdd].md: [attribute] = [different_value]
→ Resolution needed: [which doc to change and to what]
---
### Stale Registry Entries (registry behind the GDD)
⚠️ [Entry Name]
Registry says: [value] (written [date])
Source GDD now says: [new value]
→ Update registry entry to match source GDD, then check referenced_by docs.
---
### Unverifiable References (no conflict, informational)
ℹ️ [gdd].md mentions [entity_name] but states no comparable attributes.
No conflict detected. No action required.
---
### Clean Entries (no issues found)
✅ [N] registry entries verified across all GDDs with no conflicts.
---
Verdict: PASS | CONFLICTS FOUND
Verdict:
- PASS — no conflicts. Registry and GDDs agree on all checked values.
- CONFLICTS FOUND — one or more conflicts detected. List resolution steps.
Phase 6: Registry Corrections
If stale registry entries were found, ask:
"May I update
design/registry/entities.yamlto fix the [N] stale entries?"
For each stale entry:
- Update the
value/ attribute field - Set
revised:to today's date - Add a YAML comment with the old value:
# was: [old_value] before [date]
If new entries were found in GDDs that are not in the registry, ask:
"Found [N] entities/items mentioned in GDDs that aren't in the registry yet. May I add them to
design/registry/entities.yaml?"
Only add entries that appear in more than one GDD (true cross-system facts).
Never delete registry entries. Set status: deprecated if an entry is removed
from all GDDs.
After writing: Verdict: COMPLETE — consistency check finished. If conflicts remain unresolved: Verdict: BLOCKED — [N] conflicts need manual resolution before architecture begins.
6b: Append to Reflexion Log
If any 🔴 CONFLICT entries were found (regardless of whether they were resolved),
append an entry to docs/consistency-failures.md for each conflict:
### [YYYY-MM-DD] — /consistency-check — 🔴 CONFLICT
**Domain**: [system domain(s) involved]
**Documents involved**: [source GDD] vs [conflicting GDD]
**What happened**: [specific conflict — entity name, attribute, differing values]
**Resolution**: [how it was fixed, or "Unresolved — manual action needed"]
**Pattern**: [generalised lesson, e.g. "Item values defined in combat GDD were not
referenced in economy GDD before authoring — always check entities.yaml first"]
If docs/consistency-failures.md does not exist, create it with this header before appending:
# Consistency Failure Log
<!-- Auto-maintained by /consistency-check. Do not edit manually. -->
<!-- One entry per detected conflict, in chronological order. -->
| Date | GDD A | GDD B | Conflict Type | Status |
|------|-------|-------|---------------|--------|
Then append the new conflict entries. Never skip logging — a missing file is not a reason to lose conflict history.
Phase 7: Session State and Closing
Silently append to production/session-state/active.md (create the file if it does not exist):
<!-- CONSISTENCY-CHECK: [date] | GDDs checked: [N] | Conflicts found: [N] | Report: docs/consistency-report-[date].md -->
Then close with an AskUserQuestion widget:
- Prompt: "Consistency check complete — [N] conflicts found. What next?"
- Options:
[A] Fix the highest-priority conflict now[B] Save full report and stop[C] Run /design-review on the most conflicted GDD[D] Stop here
Never end the skill with plain text. Always close with this widget.
Recovery / Reference
- If PASS: Run
/review-all-gddsfor holistic design-theory review, or/create-architectureif all MVP GDDs are complete. - If CONFLICTS FOUND: Fix the flagged GDDs, then re-run
/consistency-checkto confirm resolution. - If STALE REGISTRY: Update the registry (Phase 6), then re-run to verify.
- Run
/consistency-checkafter writing each new GDD to catch issues early, not at architecture time.