maestro-flow 0.3.10 → 0.3.12

package/.codex/skills/manage-memory-capture/SKILL.md

@@ -1,86 +1,99 @@
----
-name: manage-memory-capture
-description: Capture session memory (compact or tip) into .workflow/memory/ with JSON index
-argument-hint: "[compact|tip] [description] [--tag tag1,tag2]"
-allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
----
-
-# Memory Capture
-
-## Usage
-
-```bash
-$manage-memory-capture
-$manage-memory-capture "compact"
-$manage-memory-capture "tip Always check state.json before phase operations --tag workflow,state"
-$manage-memory-capture "compact Full auth implementation session"
-```
-
-**Modes**: `compact` (full session compression) or `tip` (quick note with tags).
-No arguments: auto-detect or ask user.
-
----
-
-## Implementation
-
-### Step 1: Validate
-
-```bash
-test -d .workflow || exit 1  # E001: not initialized
-```
-
-Create `.workflow/memory/` if it does not exist.
-
-### Step 2: Detect Mode
-
-Parse first token as mode (`compact` or `tip`).
-If absent or ambiguous, ask user via AskUserQuestion.
-
-### Step 3: Capture Content
-
-**Compact mode**:
-1. Analyze current conversation for: objective, key decisions, modified files, current plan state, pending work
-2. Generate entry ID: `MEM-{YYYYMMDD}-{NNN}`
-3. Write `.workflow/memory/MEM-{id}.md` with sections:
-   - Objective, Key Decisions, Files Modified (absolute paths), Execution Plan (verbatim), Pending Work, Context Notes
-
-**Tip mode**:
-1. Extract content (everything after `tip`) and parse `--tag` flag
-2. Generate entry ID: `TIP-{YYYYMMDD}-{NNN}`
-3. Write `.workflow/memory/TIP-{id}.md` with: content, tags, timestamp, context
-
-### Step 4: Update Index
-
-Read or create `.workflow/memory/memory-index.json`.
-Append new entry metadata:
-
-```json
-{
-  "id": "{entry_id}",
-  "type": "compact|tip",
-  "date": "{ISO}",
-  "title": "{short title}",
-  "tags": ["tag1", "tag2"],
-  "file": "{filename}"
-}
-```
-
-### Step 5: Confirm
-
-```
-=== MEMORY CAPTURED ===
-ID: {entry_id}
-Type: {compact|tip}
-File: .workflow/memory/{filename}
-```
-
----
-
-## Error Handling
-
-| Code | Severity | Description |
-|------|----------|-------------|
-| E001 | error | `.workflow/` not initialized -- run `Skill({ skill: "maestro-init" })` first |
-| E002 | error | Empty note content in tip mode |
-| W001 | warning | No active workflow session -- compact captures conversation only |
-| W002 | warning | No explicit plan found -- using inferred plan |
+---
+name: manage-memory-capture
+description: Capture session memory (compact or tip) into .workflow/memory/ with JSON index
+argument-hint: "[compact|tip] [description] [--tag tag1,tag2]"
+allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
+---
+
+<purpose>
+Capture session memory into `.workflow/memory/` with JSON index. Two modes: `compact` (full session compression) or `tip` (quick note with tags). Auto-detects mode or asks user when ambiguous.
+</purpose>
+
+<context>
+$ARGUMENTS — mode token followed by description and optional flags.
+
+```bash
+$manage-memory-capture
+$manage-memory-capture "compact"
+$manage-memory-capture "tip Always check state.json before phase operations --tag workflow,state"
+$manage-memory-capture "compact Full auth implementation session"
+```
+
+**Modes**: `compact` (full session compression) or `tip` (quick note with tags).
+No arguments: auto-detect or ask user.
+
+**Flags**:
+- `--tag tag1,tag2` — Comma-separated tags for the entry
+</context>
+
+<execution>
+
+### Step 1: Validate
+
+```bash
+test -d .workflow || exit 1  # E001: not initialized
+```
+
+Create `.workflow/memory/` if it does not exist.
+
+### Step 2: Detect Mode
+
+Parse first token as mode (`compact` or `tip`).
+If absent or ambiguous, ask user via AskUserQuestion.
+
+### Step 3: Capture Content
+
+**Compact mode**:
+1. Analyze current conversation for: objective, key decisions, modified files, current plan state, pending work
+2. Generate entry ID: `MEM-{YYYYMMDD}-{NNN}`
+3. Write `.workflow/memory/MEM-{id}.md` with sections:
+   - Objective, Key Decisions, Files Modified (absolute paths), Execution Plan (verbatim), Pending Work, Context Notes
+
+**Tip mode**:
+1. Extract content (everything after `tip`) and parse `--tag` flag
+2. Generate entry ID: `TIP-{YYYYMMDD}-{NNN}`
+3. Write `.workflow/memory/TIP-{id}.md` with: content, tags, timestamp, context
+
+### Step 4: Update Index
+
+Read or create `.workflow/memory/memory-index.json`.
+Append new entry metadata:
+
+```json
+{
+  "id": "{entry_id}",
+  "type": "compact|tip",
+  "date": "{ISO}",
+  "title": "{short title}",
+  "tags": ["tag1", "tag2"],
+  "file": "{filename}"
+}
+```
+
+### Step 5: Confirm
+
+```
+=== MEMORY CAPTURED ===
+ID: {entry_id}
+Type: {compact|tip}
+File: .workflow/memory/{filename}
+```
+</execution>
+
+<error_codes>
+| Code | Severity | Description |
+|------|----------|-------------|
+| E001 | error | `.workflow/` not initialized -- run `Skill({ skill: "maestro-init" })` first |
+| E002 | error | Empty note content in tip mode |
+| W001 | warning | No active workflow session -- compact captures conversation only |
+| W002 | warning | No explicit plan found -- using inferred plan |
+</error_codes>
+
+<success_criteria>
+- [ ] `.workflow/` existence validated; `.workflow/memory/` created if missing
+- [ ] Mode detected or prompted (compact vs tip)
+- [ ] Compact: conversation analyzed, MEM-id generated, markdown file written with all sections
+- [ ] Tip: content extracted, TIP-id generated, markdown file written
+- [ ] Index updated with new entry metadata
+- [ ] Confirmation displayed with ID, type, and file path
+</success_criteria>

package/.codex/skills/manage-status/SKILL.md

@@ -1,89 +1,102 @@
----
-name: manage-status
-description: Display project dashboard with phase progress, active tasks, and next steps
-argument-hint: ""
-allowed-tools: Read, Bash, Glob, Grep
----
-
-# Status Dashboard
-
-## Usage
-
-```bash
-$manage-status
-```
-
-No arguments required. Reads `.workflow/` state files and renders a formatted project overview.
-
----
-
-## Implementation
-
-### Step 1: Validate Project
-
-```bash
-# Verify .workflow/ exists
-test -d .workflow || exit 1  # E001: not initialized
-test -f .workflow/state.json || exit 1  # E002: state missing
-```
-
-### Step 2: Load State Files
-
-Read all state sources:
-- `.workflow/state.json` -- project-level state machine
-- `.workflow/roadmap.md` -- milestone and phase structure
-- `.workflow/phases/*/index.json` -- per-phase metadata and progress
-- `.workflow/phases/*/.task/TASK-*.json` -- individual task statuses
-
-### Step 3: Calculate Progress
-
-For each phase directory found:
-1. Count total tasks, completed, failed, blocked, pending
-2. Calculate completion percentage
-3. Determine phase status from index.json
-
-### Step 4: Render Dashboard
-
-Display formatted output:
-
-```
-=== PROJECT DASHBOARD ===
-Project: {name} | Status: {state}
-
---- Milestones & Phases ---
-{For each milestone}
-  M{N}: {title}
-  {For each phase}
-    Phase {N}: {title} [{status}] {progress_bar} {completed}/{total} ({pct}%)
-
---- Active Work ---
-Phase {N}: {title}
-  In-progress: {list}
-  Blocked: {list}
-
---- Next Steps ---
-Based on current state: {suggestion with Skill() reference}
-```
-
-### Step 5: Suggest Next Steps
-
-Use this decision table to suggest the next action:
-
-| Current State | Suggestion |
-|---------------|------------|
-| No phases planned | `Skill({ skill: "maestro-brainstorm" })` or `Skill({ skill: "maestro-plan" })` |
-| Phase planned, not executed | `Skill({ skill: "maestro-execute", args: "<N>" })` |
-| Phase executed, not verified | `Skill({ skill: "maestro-verify", args: "<N>" })` |
-| Phase verified with gaps | `Skill({ skill: "maestro-plan", args: "<N> --gaps" })` |
-| Phase reviewed PASS/WARN | `Skill({ skill: "quality-test", args: "<N>" })` |
-| UAT passed | `Skill({ skill: "maestro-phase-transition" })` |
-| All milestone phases done | `Skill({ skill: "maestro-milestone-audit" })` |
-
----
-
-## Error Handling
-
-| Code | Severity | Description |
-|------|----------|-------------|
-| E001 | fatal | `.workflow/` not initialized -- run `Skill({ skill: "maestro-init" })` first |
-| E002 | fatal | `state.json` missing or corrupt |
+---
+name: manage-status
+description: Display project dashboard with phase progress, active tasks, and next steps
+argument-hint: ""
+allowed-tools: Read, Bash, Glob, Grep
+---
+
+<purpose>
+Display project dashboard with phase progress, active tasks, and suggested next steps. Reads `.workflow/` state files and renders a formatted project overview. No arguments required.
+</purpose>
+
+<context>
+$ARGUMENTS — none required.
+
+```bash
+$manage-status
+```
+
+Reads from:
+- `.workflow/state.json` — project-level state machine
+- `.workflow/roadmap.md` — milestone and phase structure
+- `.workflow/scratch/*/index.json` — per-phase metadata and progress (resolved via state.json artifact registry; legacy fallback: `.workflow/phases/*/index.json`)
+- `.workflow/scratch/*/.task/TASK-*.json` — individual task statuses (legacy fallback: `.workflow/phases/*/.task/TASK-*.json`)
+</context>
+
+<execution>
+
+### Step 1: Validate Project
+
+```bash
+# Verify .workflow/ exists
+test -d .workflow || exit 1  # E001: not initialized
+test -f .workflow/state.json || exit 1  # E002: state missing
+```
+
+### Step 2: Load State Files
+
+Read all state sources:
+- `.workflow/state.json` -- project-level state machine
+- `.workflow/roadmap.md` -- milestone and phase structure
+- `.workflow/scratch/*/index.json` -- per-phase metadata and progress (resolved via state.json artifact registry; legacy fallback: `.workflow/phases/*/index.json`)
+- `.workflow/scratch/*/.task/TASK-*.json` -- individual task statuses (legacy fallback: `.workflow/phases/*/.task/TASK-*.json`)
+
+### Step 3: Calculate Progress
+
+For each phase directory found:
+1. Count total tasks, completed, failed, blocked, pending
+2. Calculate completion percentage
+3. Determine phase status from index.json
+
+### Step 4: Render Dashboard
+
+Display formatted output:
+
+```
+=== PROJECT DASHBOARD ===
+Project: {name} | Status: {state}
+
+--- Milestones & Phases ---
+{For each milestone}
+  M{N}: {title}
+  {For each phase}
+    Phase {N}: {title} [{status}] {progress_bar} {completed}/{total} ({pct}%)
+
+--- Active Work ---
+Phase {N}: {title}
+  In-progress: {list}
+  Blocked: {list}
+
+--- Next Steps ---
+Based on current state: {suggestion with Skill() reference}
+```
+
+### Step 5: Suggest Next Steps
+
+Use this decision table to suggest the next action:
+
+| Current State | Suggestion |
+|---------------|------------|
+| No phases planned | `Skill({ skill: "maestro-brainstorm" })` or `Skill({ skill: "maestro-plan" })` |
+| Phase planned, not executed | `Skill({ skill: "maestro-execute", args: "<N>" })` |
+| Phase executed, not verified | `Skill({ skill: "maestro-verify", args: "<N>" })` |
+| Phase verified with gaps | `Skill({ skill: "maestro-plan", args: "<N> --gaps" })` |
+| Phase reviewed PASS/WARN | `Skill({ skill: "quality-test", args: "<N>" })` |
+| UAT passed | `Skill({ skill: "maestro-phase-transition" })` |
+| All milestone phases done | `Skill({ skill: "maestro-milestone-audit" })` |
+</execution>
+
+<error_codes>
+| Code | Severity | Description |
+|------|----------|-------------|
+| E001 | fatal | `.workflow/` not initialized -- run `Skill({ skill: "maestro-init" })` first |
+| E002 | fatal | `state.json` missing or corrupt |
+</error_codes>
+
+<success_criteria>
+- [ ] `.workflow/` and `state.json` validated
+- [ ] All state sources loaded (state.json, roadmap, phase indexes, task files)
+- [ ] Progress calculated per phase (total, completed, failed, blocked, pending, percentage)
+- [ ] Dashboard rendered with milestones, phases, active work, and next steps
+- [ ] Next step suggestion matches current project state via decision table
+</success_criteria>