maestro-flow 0.3.14 → 0.3.16

package/.claude/commands/{manage-memory.md → manage-knowhow.md}

@@ -1,88 +1,77 @@
----
-name: manage-memory
-description: Manage memory entries — workflow memory (.workflow/memory/) and system memory (~/.claude/projects/*/memory/)
-argument-hint: "[list|search|view|edit|delete|prune] [query|id|file] [--store workflow|system|all] [--tag tag] [--type compact|tip]"
-allowed-tools:
-  - Read
-  - Write
-  - Edit
-  - Bash
-  - Glob
-  - Grep
-  - AskUserQuestion
----
-<purpose>
-Unified memory management across two stores:
-1. **Workflow memory** (`.workflow/memory/`) — Session compacts and tips with JSON index, created by `manage-memory-capture`
-2. **System memory** (`~/.claude/projects/{project}/memory/`) — Claude Code auto-memory (MEMORY.md + topic files), persists across conversations
-
-Provides list/search/view/edit/delete/prune operations. Default store is `all` (show both).
-</purpose>
-
-<required_reading>
-@~/.maestro/workflows/memory.md
-</required_reading>
-
-<context>
-Arguments: $ARGUMENTS
-
-**Stores:**
-
-| Store | Path | Format | Index |
-|-------|------|--------|-------|
-| `workflow` | `.workflow/memory/` | `MEM-*.md`, `TIP-*.md` (legacy only — new tips go to `manage-learn tip`) | `.workflow/wiki-index.json` (unified) |
-| `system` | `~/.claude/projects/{project}/memory/` | `MEMORY.md` + topic `.md` files | None (flat files) |
-
-**System memory path detection:**
-```bash
-# Derive from project root — replace path separators with '--', prefix drive letter
-# e.g., D:\maestro2 → ~/.claude/projects/D--maestro2/memory/
-```
-
-**Subcommands:**
-- `list` — List entries from both stores (default if no arguments)
-- `search <query>` — Full-text search across both stores
-- `view <id|file>` — Display a workflow entry by ID or system file by name
-- `edit <file>` — Edit a system memory file (MEMORY.md or topic file)
-- `delete <id|file>` — Remove an entry/file (with confirmation)
-- `prune` — Bulk cleanup by criteria
-
-**Flags:**
-- `--store <workflow|system|all>` — Target store (default: `all` for list/search, inferred for other ops)
-- `--tag <tag>` — Filter by tag (workflow store)
-- `--type <compact|tip>` — Filter by entry type (workflow store)
-- `--before <YYYY-MM-DD>` — Entries before date
-- `--after <YYYY-MM-DD>` — Entries after date
-- `--dry-run` — Preview destructive ops without executing
-- `--confirm` — Skip confirmation prompt
-</context>
-
-<execution>
-Follow '~/.maestro/workflows/memory.md' Part A (Memory Management) completely.
-</execution>
-
-<error_codes>
-| Code | Severity | Description | Stage |
-|------|----------|-------------|-------|
-| E001 | error | No memory stores found — run `/manage-memory-capture` or create MEMORY.md | resolve_paths |
-| E002 | error | Entry ID or filename not found | execute_view, execute_delete |
-| E003 | error | Prune requires at least one filter (--tag, --type, --before, --after) | execute_prune |
-| E004 | error | Cannot delete MEMORY.md — use `edit` subcommand instead | execute_delete |
-| W001 | warning | Workflow index has orphaned files or dangling references | integrity_check |
-| W002 | warning | MEMORY.md references non-existent topic file | integrity_check |
-| W003 | warning | MEMORY.md exceeds 200 lines — content will be truncated at load | execute_edit |
-</error_codes>
-
-<success_criteria>
-- [ ] Both store paths correctly resolved
-- [ ] Subcommand correctly detected from arguments
-- [ ] Store auto-detected from argument format (MEM-*/TIP-* vs filename)
-- [ ] List: both stores displayed with appropriate formatting
-- [ ] Search: results from both stores, ranked by relevance
-- [ ] View: correct store selected, full content displayed
-- [ ] Edit: system memory files editable, MEMORY.md kept under 200 lines
-- [ ] Delete: MEMORY.md protected, confirmation required, references checked
-- [ ] Prune: workflow-only, filters validated, index updated
-- [ ] Integrity check catches orphans and broken links
-- [ ] Next step: `/manage-memory-capture compact` to save new memory, or `/manage-status` to continue workflow
-</success_criteria>
+---
+name: manage-knowhow
+description: Manage memory entries — workflow memory (.workflow/knowhow/) and system memory (~/.claude/projects/*/memory/)
+argument-hint: "[list|search|view|edit|delete|prune] [query|id|file] [--store workflow|system|all] [--tag tag] [--type compact|tip]"
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - Glob
+  - Grep
+  - AskUserQuestion
+---
+<purpose>
+Unified memory management across two stores:
+1. **Workflow knowhow** (`.workflow/knowhow/`) — Session compacts and tips with JSON index, created by `manage-knowhow-capture`
+2. **System memory** (`~/.claude/projects/{project}/memory/`) — Claude Code auto-memory (MEMORY.md + topic files), persists across conversations
+
+Provides list/search/view/edit/delete/prune operations. Default store is `all` (show both).
+</purpose>
+
+<required_reading>
+@~/.maestro/workflows/knowhow.md
+</required_reading>
+
+<context>
+Arguments: $ARGUMENTS
+
+Dual store architecture (paths, formats, index) defined in workflow knowhow.md.
+
+**Subcommands:**
+- `list` — List entries from both stores (default if no arguments)
+- `search <query>` — Full-text search across both stores
+- `view <id|file>` — Display a workflow entry by ID or system file by name
+- `edit <file>` — Edit a system memory file (MEMORY.md or topic file)
+- `delete <id|file>` — Remove an entry/file (with confirmation)
+- `prune` — Bulk cleanup by criteria
+
+**Flags:**
+- `--store <workflow|system|all>` — Target store (default: `all` for list/search, inferred for other ops)
+- `--tag <tag>` — Filter by tag (workflow store)
+- `--type <compact|tip>` — Filter by entry type (workflow store)
+- `--before <YYYY-MM-DD>` — Entries before date
+- `--after <YYYY-MM-DD>` — Entries after date
+- `--dry-run` — Preview destructive ops without executing
+- `--confirm` — Skip confirmation prompt
+</context>
+
+<execution>
+Follow '~/.maestro/workflows/knowhow.md' Part A (KnowHow Management) completely.
+</execution>
+
+<error_codes>
+| Code | Severity | Description | Stage |
+|------|----------|-------------|-------|
+| E001 | error | No memory stores found — run `/manage-knowhow-capture` or create MEMORY.md | resolve_paths |
+| E002 | error | Entry ID or filename not found | execute_view, execute_delete |
+| E003 | error | Prune requires at least one filter (--tag, --type, --before, --after) | execute_prune |
+| E004 | error | Cannot delete MEMORY.md — use `edit` subcommand instead | execute_delete |
+| W001 | warning | Workflow index has orphaned files or dangling references | integrity_check |
+| W002 | warning | MEMORY.md references non-existent topic file | integrity_check |
+| W003 | warning | MEMORY.md exceeds 200 lines — content will be truncated at load | execute_edit |
+</error_codes>
+
+<success_criteria>
+- [ ] Both store paths correctly resolved
+- [ ] Subcommand correctly detected from arguments
+- [ ] Store auto-detected from argument format (KNW-*/TIP-* vs filename)
+- [ ] List: both stores displayed with appropriate formatting
+- [ ] Search: results from both stores, ranked by relevance
+- [ ] View: correct store selected, full content displayed
+- [ ] Edit: system memory files editable, MEMORY.md kept under 200 lines
+- [ ] Delete: MEMORY.md protected, confirmation required, references checked
+- [ ] Prune: workflow-only, filters validated, index updated
+- [ ] Integrity check catches orphans and broken links
+- [ ] Next step: `/manage-knowhow-capture compact` to save new knowhow, or `/manage-status` to continue workflow
+</success_criteria>

package/.claude/commands/manage-learn.md

@@ -14,7 +14,7 @@ allowed-tools:
 <purpose>
 Unified atomic knowledge capture for the workflow learning library. Captures two types of knowledge:
 - **Insights**: Timeless "eureka moment" entries (patterns, gotchas, techniques) — the default mode
-- **Tips**: Quick contextual notes for cross-session recovery (formerly in `manage-memory-capture tip`)
+- **Tips**: Quick contextual notes for cross-session recovery (formerly in `manage-knowhow-capture tip`)
 
 Both types are stored in `.workflow/learning/lessons.jsonl` with auto-detected phase linkage and keyword-based category inference. Tips are distinguished by `source: "tip"` and implicitly tagged `tip`. Same store as retrospective output, so search and list see the entire knowledge corpus.
 </purpose>
@@ -34,36 +34,11 @@ Arguments: $ARGUMENTS
 - `show <INS-id>` → full detail with phase context
 - empty → AskUserQuestion to prompt for text
 
-**Capture flags (both insight and tip modes):**
-- `--category <name>` — pattern | antipattern | decision | tool | gotcha | technique | tip. Default: inferred from text via keyword heuristics. Tip mode defaults to `tip`.
-- `--tag t1,t2` — comma-separated tags. Insight mode implicitly adds `manual`, tip mode implicitly adds `tip`.
-- `--phase <N>` — override auto-detected current phase. Use `--phase 0` to force "no phase".
-- `--confidence <level>` — high | medium | low. Default: medium (insight), low (tip).
-
-**List/search flags:**
-- `--tag t1,t2` — filter by tag
-- `--category <name>` — filter by category
-- `--phase <N>` — filter by phase
-- `--lens <name>` — filter by retrospective lens (technical | process | quality | decision | git). Note: `git` matches `source: "retro-git"` from learn-retro; others match `lens` field from quality-retrospective.
-- `--limit <N>` — list mode row limit (default 20)
-
-**Storage:**
-- `.workflow/learning/lessons.jsonl` — append-only JSONL row per insight (shared with `quality-retrospective` output)
-- `.workflow/learning/learning-index.json` — searchable index
-
-**Shared store rationale:** Manual captures (`source: "manual"`), tips (`source: "tip"`), retrospective-distilled insights (`source: "retrospective"`, `lens: <name>` from `quality-retrospective`), and learn-retro insights (`source: "retro-git"` or `source: "retro-decision"` from `learn-retro`) all live in the same store so search and list see the entire knowledge corpus. The `source` field disambiguates origin.
+Flags, storage paths, and shared store rationale defined in workflow learn.md.
 </context>
 
 <execution>
-Follow `~/.maestro/workflows/learn.md` Stages 1–5 in order. Key invariants:
-
-1. **No agent or CLI calls** — this is a pure file operation: parse → infer → append → confirm. Category inference is keyword-based, not LLM-based.
-2. **Auto-link phase** — read `.workflow/state.json` for `current_phase` and derive phase context from artifact registry (`state.json.artifacts[]`). `--phase 0` forces no link.
-3. **Index schema** — `learning-index.json` entries[] with id, type, timestamp, file, summary, tags, plus learn-specific fields: lens, category, confidence, routed_to, routed_id.
-4. **Stable INS ids** — `INS-{8 lowercase hex}` from `hash(insight_text + category + phase)`. Deterministic: same content in same context always produces the same ID.
-5. **Append-only lessons.jsonl** — never rewrite existing rows; duplicate detection is the user's job at search time.
-6. **Bootstrap on demand** — create `.workflow/learning/`, `lessons.jsonl`, `learning-index.json` on first use; do not require them to exist upfront.
-7. **Tip mode** — when first token is `tip`, set `source: "tip"`, `category: "tip"`, `confidence: "low"`, and implicitly add `tip` tag. Everything else follows the same pipeline as insight capture. This replaces the former `manage-memory-capture tip` mode.
+Follow `~/.maestro/workflows/learn.md` Stages 1–5 in order.
 </execution>
 
 <error_codes>

package/.claude/commands/manage-status.md

@@ -30,26 +30,7 @@ $ARGUMENTS (no arguments required)
 <execution>
 Follow '~/.maestro/workflows/status.md' completely.
 
-**Next-step decision table:**
-| Current state | Suggested command | Reason |
-|---------------|-------------------|--------|
-| No phases planned | `/maestro-brainstorm 1` or `/maestro-plan 1` | Explore ideas or start planning first phase |
-| Phase pending, needs analysis | `/maestro-analyze <N>` | Evaluate feasibility before planning |
-| Phase pending, needs decisions | `/maestro-analyze <N> -q` | Quick decision extraction |
-| Phase planned, not executed | `/maestro-execute <N>` | Execute the planned phase |
-| Phase executing, tasks blocked | `/quality-debug <N>` | Unblock stuck tasks |
-| Phase executed, not verified | `/maestro-verify <N>` | Verify execution results |
-| Phase verified with gaps | `/maestro-plan <N> --gaps` | Plan gap fixes |
-| Phase verified, not reviewed | `/quality-review <N>` | Code quality review before UAT |
-| Phase reviewed, verdict BLOCK | `/maestro-plan <N> --gaps` | Fix critical review findings first |
-| Phase reviewed, verdict PASS/WARN | `/quality-test <N>` | Proceed to UAT testing |
-| Phase verified, low test coverage | `/quality-test-gen <N>` | Generate missing automated tests |
-| UAT passed, all phases done | `/maestro-milestone-audit` | Cross-phase integration check |
-| UAT has failures | `/quality-debug --from-uat <N>` | Debug UAT gaps with parallel agents |
-| Need integration test cycle | `/quality-integration-test <N>` | Self-iterating integration tests |
-| All phases in milestone complete | `/maestro-milestone-audit` | Cross-phase integration check |
-| Milestone audit passed | `/maestro-milestone-complete` | Archive milestone, advance |
-| Ad-hoc small task | `/maestro-quick <task>` | Quick execute without full pipeline |
+Next-step decision table defined in workflow status.md Step 5.
 </execution>
 
 <error_codes>

package/.claude/commands/manage-wiki.md

@@ -34,7 +34,7 @@ $ARGUMENTS — subcommand and optional flags.
 | No args | Same as `health` |
 
 **Flags:**
-- `--type <type>` — Filter by wiki type: spec, memory, note, lesson, issue
+- `--type <type>` — Filter by wiki type: spec, knowhow, note, lesson, issue
 - `--fix` — Auto-fix issues found during cleanup (remove broken links, suggest connections)
 - `--json` — Output in JSON format
 </context>

package/.claude/commands/quality-business-test.md

@@ -70,7 +70,7 @@ Context files:
 Follow '~/.maestro/workflows/business-test.md' completely.
 
 **Next-step routing on completion:**
-- All requirements verified → `/maestro-phase-transition {phase}`
+- All requirements verified → `/maestro-milestone-audit`
 - Failures found → `/quality-debug --from-business-test {phase}`
 - Re-run all pass → `/maestro-verify {phase}`
 - Low coverage → `/quality-test-gen {phase}`

package/.claude/commands/quality-debug.md

@@ -13,19 +13,7 @@ allowed-tools:
   - AskUserQuestion
 ---
 <purpose>
-Debug issues using scientific method with subagent isolation and persistent debug state. Supports three entry modes:
-
-1. **Standalone**: User describes an issue, gather symptoms interactively
-2. **From UAT**: `--from-uat` reads uat.md gaps as pre-filled symptoms (skip gathering)
-3. **Parallel**: `--parallel` spawns one debug agent per gap cluster concurrently
-
-When root causes are found, updates the originating uat.md with diagnosis artifacts (root_cause, fix_direction, affected_files) so the UAT -> debug -> fix pipeline stays connected.
-
-Key mechanisms from GSD diagnose-issues:
-- **Pre-filled symptoms from UAT**: Skip 5-question gathering when gaps already documented
-- **Parallel debug agents**: One agent per gap cluster for concurrent investigation
-- **Structured root cause collection**: Standardized output format across all agents
-- **UAT feedback loop**: Auto-update uat.md gaps with diagnosis results
+Debug issues using scientific method with subagent isolation and persistent debug state. Three entry modes (standalone, from-UAT, parallel) and structured root cause collection with UAT feedback loop. Full algorithm defined in workflow debug.md.
 </purpose>
 
 <required_reading>
@@ -55,15 +43,12 @@ Each artifact's type determines its outputs at `.workflow/{a.path}/`:
 
 Extract conclusions from related artifacts that may affect this debug session — review findings guide investigation direction, prior debug avoids redundant work.
 
-**Output**: `DEBUG_DIR = .workflow/scratch/{YYYYMMDD}-debug-P{N}-{slug}/` (P{N} = phase number when phase-scoped; omit for standalone)
+**Output**: `DEBUG_DIR = .workflow/scratch/{YYYYMMDD}-debug-P{N}-{slug}/` (P{N} = phase number when phase-scoped; omit for standalone). Output directory rules defined in workflow debug.md Step 4.
 </context>
 
 <execution>
 Follow '~/.maestro/workflows/debug.md' completely.
 
-**Output writes to DEBUG_DIR** (`scratch/{YYYYMMDD}-debug-P{N}-{slug}/`):
-- understanding.md, evidence.ndjson, diagnosis-summary.json
-
 **Register artifact on completion (phase-scoped only):**
 ```
 Append to state.json.artifacts[]:
@@ -73,7 +58,7 @@ Append to state.json.artifacts[]:
   milestone: current_milestone,
   phase: target_phase,
   scope: "phase",
-  path: "scratch/{YYYYMMDD}-debug-P{N}-{slug}",  // or {YYYYMMDD}-debug-{slug} for standalone
+  path: "scratch/{YYYYMMDD}-debug-P{N}-{slug}",
   status: all_diagnosed ? "completed" : "failed",
   depends_on: triggering_review_id || exec_art.id,
   harvested: false,

package/.claude/commands/quality-integration-test.md

@@ -13,15 +13,7 @@ allowed-tools:
   - AskUserQuestion
 ---
 <purpose>
-Run a self-iterating integration test cycle that combines exploration, test design, test execution, reflection, and adaptive strategy adjustment. Unlike quality-test (UAT with user) or quality-test-gen (generate missing tests), this command runs automated integration tests in a closed loop that self-corrects until convergence.
-
-Key mechanisms from DMS3 integration-test-cycle:
-- **6-phase cycle**: Explore -> Design -> Develop -> Test -> Reflect -> Adjust
-- **Reflection-driven**: After each iteration, reflect on what worked/failed and adjust strategy
-- **Adaptive strategy engine**: Conservative (iter 1-2) -> Aggressive (>80% similar) -> Surgical (regression) -> Reflective (stuck 3+)
-- **L0-L3 progressive layers**: Static Analysis -> Unit -> Integration -> E2E
-- **Self-iterating**: Loop continues until pass rate threshold met or max iterations reached
-- **State persistence**: state.json + reflection-log.md survive context resets
+Run a self-iterating integration test cycle that combines exploration, test design, test execution, reflection, and adaptive strategy adjustment. Unlike quality-test (UAT with user) or quality-test-gen (generate missing tests), this command runs automated integration tests in a closed loop that self-corrects until convergence. Full 6-phase cycle, adaptive strategy engine, and L0-L3 progressive layers defined in workflow integration-test.md.
 </purpose>
 
 <required_reading>
@@ -35,26 +27,14 @@ Phase: $ARGUMENTS (required -- phase number)
 - `--max-iter <N>` -- Maximum iterations (default: 5)
 - `--layer <L0|L1|L2|L3>` -- Start from specific layer (default: auto-detect)
 
-**L0-L3 Progressive Test Layers:**
-
-| Layer | Name | What | Tools |
-|-------|------|------|-------|
-| L0 | Static Analysis | Type checking, lint, dead code | `tsc --noEmit`, `eslint`, `ruff` |
-| L1 | Unit Tests | Function-level isolation tests | jest, vitest, pytest |
-| L2 | Integration Tests | Cross-module, API, DB tests | supertest, pytest + fixtures |
-| L3 | E2E Tests | Full user flow tests | playwright, cypress, selenium |
-
-**State files (in `.tests/integration/`):**
-- `state.json` -- iteration state, pass rates, strategy
-- `reflection-log.md` -- per-iteration reflections
-- `test-results-iter-{N}.json` -- results per iteration
+L0-L3 layer definitions, state file formats, and strategy engine rules defined in workflow integration-test.md.
 </context>
 
 <execution>
 Follow '~/.maestro/workflows/integration-test.md' completely.
 
 **Next-step routing on completion:**
-- Converged (pass rate met) → `/maestro-phase-transition {phase}`
+- Converged (pass rate met) → `/maestro-milestone-audit`
 - Max iterations, pass rate close → `/quality-debug {phase}` (investigate remaining failures)
 - Regressions detected → `/quality-debug {phase}`
 - Stuck 3+ iterations → `/maestro-analyze {phase} -q` (reassess approach)

package/.claude/commands/quality-retrospective.md

@@ -30,34 +30,7 @@ Post-execution multi-perspective retrospective (复盘) for completed phases. Co
 <context>
 Arguments: $ARGUMENTS
 
-**Modes (auto-detected from first non-flag token):**
-- No phase argument → `scan` mode: report unreviewed completed phases, prompt selection
-- `<N>` → `single` mode: retrospect phase N
-- `<N>..<M>` → `range` mode: retrospect phases N through M (inclusive)
-- `--all` → batch mode: re-run for every completed phase (archives existing retrospective.json)
-
-**Flags:**
-- `--lens <name>` — restrict to one lens; allowed: technical, process, quality, decision (repeatable)
-- `--no-route` — produce retrospective.{md,json} only; skip auto-creation of spec/note/issue
-- `--compare <M>` — emit a delta section vs phase M's prior retrospective
-- `--auto-yes` — accept all routing recommendations without prompting
-
-**Storage written:**
-- Retrospective output (resolve via `state.json.artifacts[]` → `.workflow/scratch/` path):
-  - retrospective.md — human-readable record
-  - retrospective.json — structured record
-- `.workflow/specs/{category-file}.md` — `<spec-entry>` entries appended to matching category files (one per spec-routed insight)
-- `.workflow/issues/issues.jsonl` — appended issue rows (`source: "retrospective"`)
-- `.workflow/learning/lessons.jsonl` — tips routed via `manage-learn tip` (formerly manage-memory-capture)
-- `.workflow/learning/lessons.jsonl` — append-only insight log
-- `.workflow/learning/learning-index.json` — searchable index
-
-**Storage read (never modified):**
-- Phase artifacts (resolve via `state.json.artifacts[]` → scratch paths):
-  - index.json, plan.json, verification.json, review.json, uat.md
-  - .task/TASK-*.json, .summaries/TASK-*-summary.md
-- `.workflow/issues/issues.jsonl`, `.workflow/issues/issue-history.jsonl`
-- `.workflow/state.json`
+Modes (scan/single/range/all), flags (--lens, --no-route, --compare, --auto-yes), and storage paths defined in workflow retrospective.md Argument Shape and Stages 1-7.
 </context>
 
 <execution>

package/.claude/commands/quality-review.md

@@ -13,28 +13,7 @@ allowed-tools:
   - AskUserQuestion
 ---
 <purpose>
-Run multi-dimensional code review on a completed phase's changed files. Answers the question "is this code good?" — complementing maestro-verify ("is the goal met?") and quality-test ("does it work for users?").
-
-Supports three review levels that scale with task depth:
-
-**Quick** — Single-pass inline scan, no agents. For small changes (≤3 files) or scratch tasks.
-  - Dimensions: correctness + security only
-  - No deep-dive, issues created for critical only
-
-**Standard** — Parallel agent review across all dimensions. Default for most phases.
-  - Dimensions: all 6 (correctness, security, performance, architecture, maintainability, best-practices)
-  - Auto deep-dive if critical findings > 0
-  - Issues created for critical + high
-
-**Deep** — Full agent review with forced multi-iteration deep-dive and cross-file impact analysis. For complex/critical phases.
-  - Dimensions: all 6
-  - Forced deep-dive (max 3 iterations) with impact radius analysis
-  - Issues created for critical + high + medium
-
-Level auto-detection when not specified:
-  - ≤3 changed files → quick
-  - 4-19 changed files → standard
-  - ≥20 changed files OR phase marked critical in index.json → deep
+Run multi-dimensional code review on a completed phase's changed files. Answers the question "is this code good?" -- complementing maestro-verify ("is the goal met?") and quality-test ("does it work for users?"). Three review levels (quick/standard/deep) scale with task depth, auto-detected from file count. Level definitions, dimension lists, deep-dive rules, and issue creation thresholds defined in workflow review.md.
 </purpose>
 
 <required_reading>
@@ -96,38 +75,10 @@ Append to state.json.artifacts[]:
 }
 ```
 
-**Report format on completion:**
-
-```
-=== CODE REVIEW RESULTS ===
-Phase:     {phase_name}
-Level:     {quick | standard | deep}
-Files:     {files_reviewed} files across {dimensions_count} dimensions
-Duration:  {duration}
-
-Severity Distribution:
-  Critical: {critical_count}
-  High:     {high_count}
-  Medium:   {medium_count}
-  Low:      {low_count}
-
-Top Issues:
-  1. [{severity}] {finding_id}: {title} ({file}:{line})
-  2. ...
-
-Verdict: {PASS | WARN | BLOCK}
-Issues Created: {issue_count}
-
-Files:
-  {REVIEW_DIR}/review.json
-
-Next steps:
-  {verdict_based_routing}
-```
+Report format and next-step routing by verdict defined in workflow review.md Report Format and Next Step Routing sections.
 
-**Next-step routing by verdict:**
+**Next-step routing summary:**
 - PASS → `/quality-test {phase}`
-- PASS + low test coverage → `/quality-test-gen {phase}`
 - WARN → `/quality-test {phase}` (proceed with caveats)
 - BLOCK → `/maestro-plan {phase} --gaps` (fix critical findings first)
 </execution>

package/.claude/commands/quality-test-gen.md

@@ -13,16 +13,7 @@ allowed-tools:
   - AskUserQuestion
 ---
 <purpose>
-Generate missing automated tests for a phase based on gap analysis from maestro-verify (Nyquist audit) and quality-test (UAT coverage gaps). Classifies changed files into unit test vs E2E vs skip categories, discovers existing test infrastructure, generates a test plan for user approval, then writes tests using RED-GREEN methodology.
-
-Key mechanisms from GSD add-tests:
-- **TDD/E2E/Skip classification**: Categorize changed files by appropriate test type
-- **Test structure discovery**: Find existing test patterns, frameworks, conventions
-- **Test plan with user approval**: Present plan before writing any tests
-- **RED-GREEN generation**: Write failing test first, verify it targets the right behavior
-- **Bug discovery, not fix**: Tests expose bugs; fixing is for quality-debug or maestro-execute
-
-This command is the "test gap filler" -- it bridges the gap between verification (maestro-verify finds MISSING coverage) and testing (quality-test runs UAT). It produces the automated tests that make Nyquist coverage pass.
+Generate missing automated tests for a phase based on gap analysis from maestro-verify (Nyquist audit) and quality-test (UAT coverage gaps). Bridges verification (finds MISSING coverage) and testing (runs UAT) by producing the automated tests that make Nyquist coverage pass. TDD/E2E classification, test discovery, plan approval, and RED-GREEN methodology defined in workflow test-gen.md.
 </purpose>
 
 <required_reading>

package/.claude/commands/quality-test.md

@@ -32,35 +32,13 @@ Key mechanisms from GSD verify-work:
 <context>
 Phase or task: $ARGUMENTS (optional)
 
-**Flags:**
-- `--smoke` -- Run cold-start smoke tests before UAT (basic sanity: app starts, routes respond, no crash)
-- `--auto-fix` -- After diagnosis, auto-trigger gap-fix loop instead of asking user
-
-**All context via state.json.artifacts[]:**
-
-```
-related = artifacts.filter(a =>
-  a.phase === target_phase && a.milestone === current_milestone
-).sort_by(completed_at asc)
-```
-
-Each artifact's type determines its outputs at `.workflow/{a.path}/`:
-- **execute** → .summaries/, .task/, verification.json, plan.json (test target source)
-- **verify** → verification.json (must_haves, gaps)
-- **review** → review.json (findings become additional test scenarios)
-- **debug** → understanding.md (confirmed root causes become regression tests)
-- **test** → uat.md (existing session, resumable)
-
-Extract conclusions from related artifacts that may affect this test session — review findings generate additional scenarios, debug root causes generate regression tests.
-
-**Output**: `TEST_DIR = .workflow/scratch/{YYYYMMDD}-test-P{N}-{slug}/` (P{N} = phase number, enables directory-level identification as state.json fallback)
+Flags, artifact context resolution, and output directory format defined in workflow test.md.
 </context>
 
 <execution>
 Follow '~/.maestro/workflows/test.md' completely.
 
-**Output writes to TEST_DIR** (`scratch/{YYYYMMDD}-test-P{N}-{slug}/`):
-- uat.md, test-plan.json, .tests/test-results.json, .tests/coverage-report.json
+**Command-specific extensions (not in workflow):**
 
 **Review findings integration** (from related review artifacts):
 - Extract critical/high findings as additional test scenarios, marked `source: "review_finding"`
@@ -88,7 +66,7 @@ Append to state.json.artifacts[]:
 ```
 
 **Next-step routing on completion:**
-- All tests pass → `/maestro-phase-transition {phase}`
+- All tests pass → `/maestro-milestone-audit`
 - Issues found, --auto-fix ran and succeeded → `/maestro-verify {phase}`
 - Issues found, --auto-fix ran but gaps remain → `/quality-debug --from-uat {phase}`
 - Issues found, manual fix needed → `/quality-debug --from-uat {phase}`

package/.claude/commands/spec-add.md

@@ -21,27 +21,7 @@ Each category maps 1:1 to a single target file — no dual-write.
 <context>
 $ARGUMENTS -- expects `<category> <content>`
 
-**Category-to-file mapping (1:1, same as spec-load):**
-| Category | Target file |
-|----------|------------|
-| `coding` | `coding-conventions.md` |
-| `arch` | `architecture-constraints.md` |
-| `quality` | `quality-rules.md` |
-| `debug` | `debug-notes.md` |
-| `test` | `test-conventions.md` |
-| `review` | `review-standards.md` |
-| `learning` | `learnings.md` |
-
-**Entry format (closed-tag):**
-```markdown
-<spec-entry category="{category}" keywords="{auto-extracted}" date="{YYYY-MM-DD}">
-
-### {title}
-
-{content}
-
-</spec-entry>
-```
+Category-to-file mapping (1:1) and entry format defined in workflow specs-add.md.
 </context>
 
 <execution>

package/.claude/commands/spec-load.md

@@ -20,22 +20,7 @@ Supports filtering by category (file-level) and keyword (entry-level via `<spec-
 <context>
 $ARGUMENTS -- optional flags and keyword
 
-**Category-to-file mapping (1:1, same as spec-add):**
-| Category | File loaded |
-|----------|------------|
-| `coding` | `coding-conventions.md` |
-| `arch` | `architecture-constraints.md` |
-| `quality` | `quality-rules.md` |
-| `debug` | `debug-notes.md` |
-| `test` | `test-conventions.md` |
-| `review` | `review-standards.md` |
-| `learning` | `learnings.md` |
-| `all` (default) | All spec files |
-
-**Flags:**
-- `--category <type>` — Filter by file category (loads one file)
-- `--keyword <word>` — Filter entries by keyword attribute in `<spec-entry>` tags. Searches across all files (or within category if combined)
-- `--with-lessons` — Also search `.workflow/learning/lessons.jsonl`
+Category-to-file mapping (1:1) and flag details defined in workflow specs-load.md.
 
 **Examples:**
 ```