pi-maestro-flow 0.2.0 → 0.3.1

package/skills/odyssey-improve/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: odyssey-improve
 description: "Long-running codebase improvement cycle — multi-dimensional audit, deep diagnosis, targeted fix, verify, generalize, and engineering knowledge persistence Arguments: <target> [--dimensions <list>] [--fix-threshold <severity>] [--skip-fix] [--skip-generalize] [--auto] [-y] [-c] [--heartbeat]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
-<base>@~/.maestro/workflows/odyssey-base.md</base>
+<base>~/.pi/agent/packages/pi-maestro-flow/workflows/odyssey-base.md</base>
 
 <purpose>
 survey → 6-dimension audit → diagnose → fix → verify → generalize → discover → persist.
@@ -154,7 +154,7 @@ S_INTAKE → S_SURVEY → S_AUDIT → S_DIAGNOSE → S_FIX → S_VERIFY → S_GE
 <transitions>
 S_INTAKE → S_INTAKE      : -c + session found → A_RESUME
 S_INTAKE → S_SURVEY      : target resolved → A_INTAKE
-S_INTAKE → S_INTAKE      : no target → AskUserQuestion
+S_INTAKE → S_INTAKE      : no target → user prompt
 
 S_SURVEY   → S_AUDIT       : complete
 
@@ -222,19 +222,19 @@ Commit: `"odyssey-improve({slug}): AUDIT — multi-dimension review"`
 Root cause analysis for critical/high findings — don't fix symptoms.
 
 1. Group by dimension, prioritize by severity. For each: hypothesis → trace code path + git history → evidence phase=diagnosis
-2. Ambiguity → evidence phase=decision; Normal: AskUserQuestion | `-y`: defer
+2. Ambiguity → evidence phase=decision; Normal: user prompt | `-y`: defer
 3. CLI-assisted for complex findings: `maestro delegate --role analyze --mode analysis` (`run_in_background: true`)
 4. Write `session.json.diagnoses[]`. Update §4. Mark G3.
 
 Commit: `"odyssey-improve({slug}): DIAGNOSE — root cause analysis"`
 
 ### A_ESCALATE_DIAGNOSIS
-`retries++`. < 3: `maestro delegate --role analyze`, new hypotheses, → S_DIAGNOSE. >= 3: Normal → AskUserQuestion | `-y` → INCONCLUSIVE → S_RECORD.
+`retries++`. < 3: `maestro delegate --role analyze`, new hypotheses, → S_DIAGNOSE. >= 3: Normal → user prompt | `-y` → INCONCLUSIVE → S_RECORD.
 
 ### A_FIX
 1. Exhaustive fix: ALL diagnosed issues by severity tier (critical → high → medium → low within fix_threshold), one dimension at a time. After each tier, re-verify **current tier's dimension only** (not all dimensions) — new findings at same or higher severity append to current tier. Cross-dimension regression checks run once at S_VERIFY after all tiers complete.
 2. For each fix: implement → evidence phase=fix
-3. Normal: AskUserQuestion per-fix confirmation | `-y`: auto-proceed, record `deferred`
+3. Normal: user prompt per-fix confirmation | `-y`: auto-proceed, record `deferred`
 
 Commit: `"odyssey-improve({slug}): FIX — improvements applied"`
 
@@ -306,7 +306,7 @@ Commit: `"odyssey-improve({slug}): GENERALIZE — generalization scan complete"`
    | risk + complex | Create issue |
    | safe | Skip with logged per-item reason |
 
-   Normal: AskUserQuestion per hit | `-y`: auto-fix bugs with fix_template, create issue for rest
+   Normal: user prompt per hit | `-y`: auto-fix bugs with fix_template, create issue for rest
 
 3. **Cross-phase loops:** `cross_phase_loops++` on fix/diagnose return. `loops >= max_loops` → must log per-item reasons.
 
@@ -324,12 +324,12 @@ Commit: `"odyssey-improve({slug}): DISCOVER — discovery triage complete"`
    - Reliability pattern → `/spec-add coding`
    Completion summary lists suggested `/spec-add` commands.
 
-3. Mark G7 done. Pending decisions: Normal → AskUserQuestion | `-y` → skip (show deferred count).
+3. Mark G7 done. Pending decisions: Normal → user prompt | `-y` → skip (show deferred count).
 
 4. **Goal audit (hardened):**
    - `done` → confirmed
    - `skipped` → confirmed ONLY if corresponding `skip_when` flag is true
-   - **Hard rule:** G5 and G6 CANNOT be `skipped` unless `skip_generalize == true`. Pending without flag → `failed` (Normal: AskUserQuestion | `-y`: record `failed`)
+   - **Hard rule:** G5 and G6 CANNOT be `skipped` unless `skip_generalize == true`. Pending without flag → `failed` (Normal: user prompt | `-y`: record `failed`)
    - `phase_goals_all_done = true` only when all goals pass this audit
 
 5. `current_state = "COMPLETED"`, emit completion summary.
@@ -364,11 +364,11 @@ Commit: `"odyssey-improve({slug}): RECORD — summary and knowledge persistence"
 
 | Decision Point | Normal | `-y` |
 |---------------|--------|------|
-| A_FIX improvement confirmation | AskUserQuestion | auto-proceed, `deferred` |
-| A_DIAGNOSE ambiguity | AskUserQuestion | best-effort, `deferred` |
-| A_ESCALATE 3-strike | AskUserQuestion 3-way | auto INCONCLUSIVE |
-| A_DISCOVER hit routing | AskUserQuestion | auto create issue |
-| A_DISCOVER ambiguous items | AskUserQuestion | all `deferred` |
+| A_FIX improvement confirmation | user prompt | auto-proceed, `deferred` |
+| A_DIAGNOSE ambiguity | user prompt | best-effort, `deferred` |
+| A_ESCALATE 3-strike | user prompt 3-way | auto INCONCLUSIVE |
+| A_DISCOVER hit routing | user prompt | auto create issue |
+| A_DISCOVER ambiguous items | user prompt | all `deferred` |
 
 `deferred` items shown in completion summary; recoverable via `-c`.
 
@@ -379,7 +379,7 @@ Exhaust iteration until all findings actioned (fix/issue/decision)
 and phase_goals_all_done=true.
 Fix by severity tiers, re-verify after each tier.
 Baseline captured before fix, compared after to confirm improvement.
-Pending decisions must AskUserQuestion — no silent resolve.
+Pending decisions must user prompt — no silent resolve.
 ```
 
 </appendix>

package/skills/odyssey-planex/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: odyssey-planex
 description: "Requirement-driven iterative cycle — plan, execute, strict verify, fix loop until acceptance criteria met Arguments: <requirement> [--template <name>] [--max-iterations N] [--skip-generalize] [--auto] [--method agent|cli|auto] [--executor <tool>] [--skip-verify] [--heartbeat] [-y] [-c]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
-<base>@~/.maestro/workflows/odyssey-base.md</base>
+<base>~/.pi/agent/packages/pi-maestro-flow/workflows/odyssey-base.md</base>
 
 <purpose>
 Requirement-to-delivery closed loop: parse requirement → define acceptance criteria →
@@ -153,7 +153,7 @@ S_INTAKE → S_PLAN → S_EXECUTE → S_VERIFY → S_FIX → S_GENERALIZE → S_
 <transitions>
 S_INTAKE → S_INTAKE       : -c + session found (resume)
 S_INTAKE → S_PLAN         : requirement + criteria defined
-S_INTAKE → S_INTAKE       : no requirement → AskUserQuestion
+S_INTAKE → S_INTAKE       : no requirement → user prompt
 
 S_PLAN    → S_EXECUTE
 S_EXECUTE → S_VERIFY
@@ -182,7 +182,7 @@ S_RECORD → END
 
 1. Parse requirement and flags, generate slug, create SESSION_DIR
 2. **Define acceptance criteria** — analyze requirement → derive testable criteria. Each gets `verify_method`: test | grep | cli-review | manual
-   - Normal: AskUserQuestion to confirm/edit
+   - Normal: user prompt to confirm/edit
    - `-y`: auto-derive, record `{"phase":"decision","type":"criteria-confirmation","status":"deferred"}`
 3. Search prior knowledge: `maestro search`, related sessions
 4. Write session.json + understanding.md section 1. Mark G1 done. Emit Goal Prompt.
@@ -214,7 +214,7 @@ Commit: `"odyssey-planex({slug}): PLAN — create execution plan"`
 
 Load available tools: `maestro delegate-config show --json`.
 
-Present AskUserQuestion with 3 questions:
+Present user prompt with 3 questions:
 1. **Executor** — Auto (domain routing) | Agent (all tasks) | specific CLI tool | Other (custom domain routing)
 2. **Review** — Skip | {tool} review (git diff quality check)
 3. **Verify** — Auto (delegate convergence + structure + anti-pattern check) | specific tool | Skip
@@ -239,7 +239,7 @@ Execute tasks per plan order. Independent tasks may run in parallel.
 
 **Agent path:**
 ```
-Spawn Agent with: task definition, acceptance criteria refs, prior task summaries, specs_content
+dispatch via teammate with: task definition, acceptance criteria refs, prior task summaries, specs_content
 Agent implements → verifies convergence → auto-fix (max 3) → returns result
 ```
 
@@ -335,7 +335,7 @@ Iron gate — every acceptance criterion checked objectively.
 | `test` | Run relevant tests, check pass/fail |
 | `grep` | Grep for expected pattern |
 | `cli-review` | `maestro delegate "PURPOSE: Verify criterion {criterion_id}: {criterion}\nTASK: Read implementation code \| Check behavior matches criterion \| Report pass/fail with file:line evidence\nMODE: analysis\nCONTEXT: @{relevant_files}\nEXPECTED: JSON {criterion_id, status: passed\|failed, evidence: [{file, line, detail}]}" --role review --mode analysis` |
-| `manual` | Normal: AskUserQuestion / `-y`: record `deferred` |
+| `manual` | Normal: user prompt / `-y`: record `deferred` |
 
 Record per criterion: `{"phase":"verification","type":"criterion-check","criterion_id":"AC1","method":"","result":"passed|failed","evidence":"","iteration":N}`. Update acceptance_criteria[].status. Append to iterations[].
 
@@ -421,7 +421,7 @@ Commit: `"odyssey-planex({slug}): GENERALIZE — pattern scan complete"`
    | risk + complex | Create issue |
    | safe | Skip with logged per-item reason |
 
-   Normal: AskUserQuestion per hit | `-y`: auto-route to execute, create issue for rest
+   Normal: user prompt per hit | `-y`: auto-route to execute, create issue for rest
 
 3. **Cross-phase loops:** `loops >= max_loops` → must log per-item reasons, advance to S_RECORD.
 
@@ -438,12 +438,12 @@ Commit: `"odyssey-planex({slug}): DISCOVER — findings classified"`
    - Acceptance criteria template → `/spec-add review`
    - Generalization pattern → `/spec-add coding`
 
-3. Mark G7 done. Pending decisions: Normal → AskUserQuestion | `-y` → skip (show deferred count).
+3. Mark G7 done. Pending decisions: Normal → user prompt | `-y` → skip (show deferred count).
 
 4. **Goal audit (hardened):**
    - `done` → confirmed
    - `skipped` → confirmed ONLY if corresponding `skip_when` flag is true
-   - **Hard rule:** G5 and G6 CANNOT be `skipped` unless `skip_generalize == true`. Pending without flag → `failed` (Normal: AskUserQuestion | `-y`: record `failed`)
+   - **Hard rule:** G5 and G6 CANNOT be `skipped` unless `skip_generalize == true`. Pending without flag → `failed` (Normal: user prompt | `-y`: record `failed`)
    - `phase_goals_all_done = true` only when all goals pass this audit
 
 5. `current_state = "COMPLETED"`, emit completion summary.
@@ -474,12 +474,12 @@ Commit: `"odyssey-planex({slug}): RECORD — session summary"`
 
 | Decision Point | Normal | `-y` |
 |---------------|--------|------|
-| S_INTAKE criteria confirmation | AskUserQuestion | auto-derive, `deferred` |
-| S_EXECUTE execution options | AskUserQuestion | use defaults (auto/Skip/Auto), `confirmed: true` |
-| S_EXECUTE task blocked (3 retries) | AskUserQuestion: continue or stop | auto continue, log blocked |
-| S_VERIFY manual criterion | AskUserQuestion | `deferred` |
-| S_VERIFY max iteration reached | AskUserQuestion | auto accept, `deferred` |
-| A_DISCOVER hit routing | AskUserQuestion | auto-route to execute, create issue for rest |
+| S_INTAKE criteria confirmation | user prompt | auto-derive, `deferred` |
+| S_EXECUTE execution options | user prompt | use defaults (auto/Skip/Auto), `confirmed: true` |
+| S_EXECUTE task blocked (3 retries) | user prompt: continue or stop | auto continue, log blocked |
+| S_VERIFY manual criterion | user prompt | `deferred` |
+| S_VERIFY max iteration reached | user prompt | auto accept, `deferred` |
+| A_DISCOVER hit routing | user prompt | auto-route to execute, create issue for rest |
 
 ### Goal Prompt convergence rules
 

package/skills/odyssey-review-test-fix/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: odyssey-review-test-fix
 description: "Deep review + fix cycle — archaeology, exploration, multi-dimensional review, targeted fix, generalization, discovery, and knowledge persistence Arguments: <target> [--dimensions <list>] [--fix-threshold critical|high|medium|low|all] [--skip-fix] [--skip-generalize] [--auto] [-y] [-c] [--heartbeat]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
-<base>@~/.maestro/workflows/odyssey-base.md</base>
+<base>~/.pi/agent/packages/pi-maestro-flow/workflows/odyssey-base.md</base>
 
 <purpose>
 archaeology → explore → multi-dimensional review → fix ALL findings → confirm → generalize → discover → persist. Zero-residual: every finding gets an action.
@@ -139,7 +139,7 @@ S_INTAKE → S_ARCHAEOLOGY → S_EXPLORE → S_REVIEW → S_FIX → S_CONFIRM
 <transitions>
 S_INTAKE → S_INTAKE       : -c + session found → A_RESUME_SESSION
 S_INTAKE → S_ARCHAEOLOGY  : target resolved → A_INTAKE
-S_INTAKE → S_INTAKE       : no target → AskUserQuestion
+S_INTAKE → S_INTAKE       : no target → user prompt
 
 S_ARCHAEOLOGY → S_EXPLORE     : complete
 S_EXPLORE     → S_REVIEW      : complete
@@ -214,7 +214,7 @@ for tier in [critical, high, medium, low].filter(>= threshold):
   tier done → auto-commit
 ```
 
-Normal: AskUserQuestion per tier. `-y`: auto-fix all.
+Normal: user prompt per tier. `-y`: auto-fix all.
 Remaining > 0 → retry (max_fix_rounds = 5). Unchanged 2 rounds → classify each individually. After 5 rounds with remaining > 0 → escalate: Normal: AskUserQuestion (continue/accept/reclassify) | `-y`: classify remaining as `deferred`, proceed.
 Blanket "pre-existing" forbidden.
 
@@ -288,7 +288,7 @@ Commit: `"odyssey-review({slug}): GENERALIZE — pattern scan complete"`
    | risk + complex | Create issue |
    | safe | Skip with logged per-item reason |
 
-   Normal: AskUserQuestion per hit | `-y`: auto-fix with template, create issue for rest
+   Normal: user prompt per hit | `-y`: auto-fix with template, create issue for rest
 
 3. **Cross-phase loops:** `loops >= max_loops` → must log per-item reasons, advance to S_RECORD.
 
@@ -304,12 +304,12 @@ Commit: `"odyssey-review({slug}): DISCOVER — sibling triage complete"`
    - Architecture violation pattern → `/spec-add arch`
    - Reusable generalization pattern → `/spec-add coding`
 
-2. Mark G6 done. Pending decisions: Normal → AskUserQuestion | `-y` → skip (show deferred count).
+2. Mark G6 done. Pending decisions: Normal → user prompt | `-y` → skip (show deferred count).
 
 3. **Goal audit (hardened):**
    - `done` → confirmed
    - `skipped` → confirmed ONLY if corresponding `skip_when` flag is true
-   - **Hard rule:** G4 and G5 CANNOT be `skipped` unless `skip_generalize == true`. Pending without flag → `failed` (Normal: AskUserQuestion | `-y`: record `failed`)
+   - **Hard rule:** G4 and G5 CANNOT be `skipped` unless `skip_generalize == true`. Pending without flag → `failed` (Normal: user prompt | `-y`: record `failed`)
    - `phase_goals_all_done = true` only when all goals pass this audit
 
 4. `current_state = "COMPLETED"`, emit completion summary.
@@ -338,10 +338,10 @@ Commit: `"odyssey-review({slug}): RECORD — summary and knowledge persistence"`
 
 | Decision Point | Normal | `-y` |
 |---------------|--------|------|
-| S_FIX tier candidates | AskUserQuestion | auto-fix, deferred |
-| S_FIX re-review new findings | AskUserQuestion | auto-append |
+| S_FIX tier candidates | user prompt | auto-fix, deferred |
+| S_FIX re-review new findings | user prompt | auto-append |
 | S_CONFIRM needs_rework | Display → S_FIX | auto proceed |
-| A_DISCOVER hit routing | AskUserQuestion | auto-fix with template, create issue for rest |
+| A_DISCOVER hit routing | user prompt | auto-fix with template, create issue for rest |
 
 ### Goal Prompt convergence rules
 
@@ -349,7 +349,7 @@ Commit: `"odyssey-review({slug}): RECORD — summary and knowledge persistence"`
 Stop when remaining_actionable == 0, confirmation == confirmed,
 generalization exhausted, phase_goals_all_done=true.
 Fix iterates by severity tier; each tier re-reviews modified area, new findings appended.
-Every finding must have action (fix/issue/decision). Decision pending must AskUserQuestion.
+Every finding must have action (fix/issue/decision). Decision pending must user prompt.
 ```
 
 </appendix>

package/skills/odyssey-ui/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: odyssey-ui
 description: "Long-running UI optimization cycle — visual survey, multi-dimensional audit, divergent exploration, fix, verify, generalize, and design knowledge persistence Arguments: <target> [--dimensions <list>] [--fix-threshold <severity>] [--skip-fix] [--skip-generalize] [--auto] [-y] [-c] [--heartbeat]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
-<base>@~/.maestro/workflows/odyssey-base.md</base>
+<base>~/.pi/agent/packages/pi-maestro-flow/workflows/odyssey-base.md</base>
 
 <purpose>
 survey → 6-dimension audit → divergent exploration → fix → verify → generalize → discover → persist.
@@ -138,7 +138,7 @@ S_INTAKE → S_SURVEY → S_AUDIT → S_DIVERGE → S_FIX → S_VERIFY → S_GEN
 <transitions>
 S_INTAKE → S_INTAKE       : -c + session found → A_RESUME
 S_INTAKE → S_SURVEY       : target resolved → A_INTAKE
-S_INTAKE → S_INTAKE       : no target → AskUserQuestion
+S_INTAKE → S_INTAKE       : no target → user prompt
 
 S_SURVEY  → S_AUDIT       : complete
 S_AUDIT   → S_DIVERGE     : complete
@@ -221,7 +221,7 @@ Commit: `"odyssey-ui({slug}): DIVERGE — creative exploration"`
 Skip if `--skip-fix`.
 1. **Exhaustive fix**: ALL findings/ideas by priority tier (critical → high → medium → low + high-impact ideas). After each tier, re-review — new findings append.
 2. Each fix → evidence phase=fix
-3. Normal: AskUserQuestion per-fix | `-y`: auto-proceed, record `deferred`
+3. Normal: user prompt per-fix | `-y`: auto-proceed, record `deferred`
 
 Commit: `"odyssey-ui({slug}): FIX — implement improvements"`
 
@@ -291,7 +291,7 @@ Commit: `"odyssey-ui({slug}): GENERALIZE — pattern scan complete"`
    | risk + design decision needed | Create issue |
    | safe | Skip with logged per-item reason |
 
-   Normal: AskUserQuestion per hit | `-y`: auto-fix with template, create issue for rest
+   Normal: user prompt per hit | `-y`: auto-fix with template, create issue for rest
 
 3. **Cross-phase loops:** `loops >= max_loops` → must log per-item reasons, advance to S_RECORD.
 
@@ -307,12 +307,12 @@ Commit: `"odyssey-ui({slug}): DISCOVER — sibling triage complete"`
    - Accessibility rule: WCAG requirement + implementation approach → `/spec-add ui`
    - Reusable generalization pattern: signature + application scope → `/spec-add coding`
 
-2. Mark G7 done. Pending decisions: Normal → AskUserQuestion | `-y` → skip (show deferred count).
+2. Mark G7 done. Pending decisions: Normal → user prompt | `-y` → skip (show deferred count).
 
 3. **Goal audit (hardened):**
    - `done` → confirmed
    - `skipped` → confirmed ONLY if corresponding `skip_when` flag is true
-   - **Hard rule:** G5 and G6 CANNOT be `skipped` unless `skip_generalize == true`. Pending without flag → `failed` (Normal: AskUserQuestion | `-y`: record `failed`)
+   - **Hard rule:** G5 and G6 CANNOT be `skipped` unless `skip_generalize == true`. Pending without flag → `failed` (Normal: user prompt | `-y`: record `failed`)
    - `phase_goals_all_done = true` only when all goals pass this audit
 
 4. `current_state = "COMPLETED"`, emit completion summary.
@@ -343,8 +343,8 @@ Commit: `"odyssey-ui({slug}): RECORD — summary and knowledge persistence"`
 
 | Decision Point | Normal | `-y` |
 |---------------|--------|------|
-| A_FIX improvement confirmation | AskUserQuestion | auto-proceed, deferred |
-| A_DISCOVER hit routing | AskUserQuestion | auto-fix with template, create issue for rest |
+| A_FIX improvement confirmation | user prompt | auto-proceed, deferred |
+| A_DISCOVER hit routing | user prompt | auto-fix with template, create issue for rest |
 
 ### Goal Prompt convergence rules
 
@@ -352,7 +352,7 @@ Commit: `"odyssey-ui({slug}): RECORD — summary and knowledge persistence"`
 Stop when audit + diverge findings all addressed (fix/issue/decision),
 phase_goals_all_done=true. Fix by impact x severity per tier.
 Re-review after each tier — new findings append and continue.
-Pending decisions must AskUserQuestion — no self-resolve.
+Pending decisions must user prompt — no self-resolve.
 ```
 
 </appendix>

package/skills/prompt-generator/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: prompt-generator
 description: "Generate or convert Claude Code prompt files — command orchestrators, skill files, agent role definitions, or style conversion of existing files. Follows GSD-style content separation with built-in quality gates. Triggers on \"create command\", \"new command\", \"create skill\", \"new skill\", \"create agent\", \"new agent\", \"convert command\", \"convert skill\", \"convert agent\", \"prompt generator\", \"优化\"."
-allowed-tools: Read Write Edit Bash Glob AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob maestro
 ---
 
 <purpose>
@@ -169,7 +169,7 @@ Read 1-2 similar files to extract patterns: section structure, naming convention
 | Standard | Multi-aspect domain | `<role>` + 2-4 domain sections |
 | Expert | Deep domain with rules | `<role>` + 4-6 domain sections |
 
-If unclear, ask user with AskUserQuestion.
+If unclear, ask user with user prompt.
 
 ## 5. Generate Content
 
@@ -193,7 +193,7 @@ Generate a complete command file with:
 **Command writing rules:**
 - Steps are **numbered** (`## 1.`, `## 2.`) — follow `plan-phase.md` and `new-project.md` style
 - Use banners for phase transitions: `━━━ SKILL ► ACTION ━━━`
-- Agent spawning uses `Agent({ subagent_type, prompt, description, run_in_background })` pattern
+- Agent spawning uses `teammate({ subagent_type, prompt, description, run_in_background })` pattern
 - Prompt to agents uses `<objective>`, `<files_to_read>`, `<output>` blocks
 - Include `<offer_next>` block with formatted completion status
 - Handle agent return markers: `## TASK COMPLETE`, `## TASK BLOCKED`, `## CHECKPOINT REACHED`
@@ -341,7 +341,7 @@ Set `$TARGET_PATH = $SOURCE_PATH` (in-place conversion) unless user specifies ou
 | `<process>` with numbered steps | At least 3 `## N.` headers |
 | Step 1 is initialization | Parses args or loads context |
 | Last step is status/report | Displays results or routes to `<offer_next>` |
-| Agent spawning (if complex) | `Agent({` call with `subagent_type` |
+| Agent spawning (if complex) | `teammate({` call with `subagent_type` |
 | Agent prompt structure | `<files_to_read>` + `<objective>` or `<output>` blocks |
 | Return handling | Routes on `## TASK COMPLETE` / `## TASK BLOCKED` markers |
 | `<offer_next>` | Banner + summary + next command suggestion |
@@ -375,7 +375,7 @@ Set `$TARGET_PATH = $SOURCE_PATH` (in-place conversion) unless user specifies ou
 | Examples present | Each domain section has 1+ comparison table or decision table |
 | `<output_contract>` | Defines return markers (COMPLETE/BLOCKED/CHECKPOINT) |
 | `<quality_gate>` | 3+ checkbox self-check items |
-| Content separation | No `AskUserQuestion`, no banner display, no argument parsing |
+| Content separation | No `user prompt`, no banner display, no argument parsing |
 
 ### 6d. Quality Gate Result
 

package/skills/quality-auto-test/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: quality-auto-test
 description: "Use when test coverage needs automated expansion or existing tests need iterative convergence Arguments: <phase> [-y] [-c N] [--max-iter N] [--layer L0|L1|L2|L3] [--dry-run] [--re-run]"
-allowed-tools: Read Write Edit Bash Glob Grep AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep maestro
 ---
 
 <purpose>
@@ -11,7 +11,7 @@ Layers L0→L3 sequential (fail-fast), scenarios within layer parallel. `--max-i
 </purpose>
 
 <required_reading>
-@~/.maestro/workflows/auto-test.md
+~/.pi/agent/packages/pi-maestro-flow/workflows/auto-test.md
 </required_reading>
 
 <context>
@@ -60,7 +60,7 @@ Flags, artifact context resolution, and output formats defined in workflow auto-
 </invariants>
 
 <execution>
-Follow '~/.maestro/workflows/auto-test.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/auto-test.md' completely.
 
 ### Phase Gates (MANDATORY, BLOCKING)
 

package/skills/quality-debug/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: quality-debug
 description: "Use when bugs, test failures, or unexpected behavior need systematic root cause investigation Arguments: [issue description] [-c] [--from-uat <phase>] [--parallel]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,7 +9,7 @@ Debug issues using scientific method with subagent isolation and persistent debu
 </purpose>
 
 <required_reading>
-@~/.maestro/workflows/debug.md
+~/.pi/agent/packages/pi-maestro-flow/workflows/debug.md
 </required_reading>
 
 <context>
@@ -54,7 +54,7 @@ Each artifact's type determines its outputs at `.workflow/{a.path}/`:
 </invariants>
 
 <execution>
-Follow '~/.maestro/workflows/debug.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/debug.md' completely.
 
 ### Phase Gates (MANDATORY, BLOCKING)
 

package/skills/quality-refactor/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: quality-refactor
 description: "Use when accumulated tech debt needs systematic identification and safe reduction Arguments: [<scope>]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,7 +9,7 @@ Targeted refactoring with safety guarantees: plan → confirm → execute with t
 </purpose>
 
 <required_reading>
-@~/.maestro/workflows/refactor.md
+~/.pi/agent/packages/pi-maestro-flow/workflows/refactor.md
 </required_reading>
 
 <context>
@@ -42,7 +42,7 @@ If not provided, prompt user for scope.
 </invariants>
 
 <execution>
-Follow '~/.maestro/workflows/refactor.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/refactor.md' completely.
 
 ### Phase Gates (MANDATORY, BLOCKING)
 

package/skills/quality-retrospective/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: quality-retrospective
 description: "Use after completing a phase to extract lessons, patterns, and improvement opportunities Arguments: [phase|N..M] [--lens technical|process|quality|decision] [--all] [--no-route] [--compare N] [-y]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,14 +9,14 @@ Post-execution retrospective (复盘): four parallel lenses (technical/process/q
 </purpose>
 
 <required_reading>
-@~/.maestro/workflows/retrospective.md
+~/.pi/agent/packages/pi-maestro-flow/workflows/retrospective.md
 </required_reading>
 
 <deferred_reading>
-- @~/.maestro/workflows/issue.md (issues.jsonl schema for auto-creation)
-- @~/.maestro/workflows/learn.md (tip routing via manage-knowhow-capture tip)
-- @~/.maestro/workflows/verify.md (verification.json schema for quality lens parsing)
-- @~/.maestro/workflows/review.md (review.json schema for quality lens parsing)
+- ~/.pi/agent/packages/pi-maestro-flow/workflows/issue.md (issues.jsonl schema for auto-creation)
+- ~/.pi/agent/packages/pi-maestro-flow/workflows/learn.md (tip routing via manage-knowhow-capture tip)
+- ~/.pi/agent/packages/pi-maestro-flow/workflows/verify.md (verification.json schema for quality lens parsing)
+- ~/.pi/agent/packages/pi-maestro-flow/workflows/review.md (review.json schema for quality lens parsing)
 </deferred_reading>
 
 <context>
@@ -44,7 +44,7 @@ Modes (scan/single/range/all) and storage paths defined in workflow retrospectiv
 </invariants>
 
 <execution>
-Follow `~/.maestro/workflows/retrospective.md` Stages 1–8 in order.
+Follow `~/.pi/agent/packages/pi-maestro-flow/workflows/retrospective.md` Stages 1–8 in order.
 
 ### Phase Gates (MANDATORY, BLOCKING)
 
@@ -64,7 +64,7 @@ Follow `~/.maestro/workflows/retrospective.md` Stages 1–8 in order.
 - REQUIRED: `retrospective.json` written with metrics, findings, insights, routing.
 - REQUIRED: `retrospective.md` written (human-readable).
 - REQUIRED: Issue rows match canonical `issues.jsonl` schema (status "open", full fields).
-- REQUIRED: Note tips routed via `Skill({ skill: "manage-knowhow-capture", args: "tip ..." })`.
+- REQUIRED: Note tips routed via `invoke /skill: "manage-knowhow-capture", args: "tip ..." })`.
 - REQUIRED: Unless `-y` flag is set, confirm before each external write (issues.jsonl append, spec-entry append, knowhow-capture). With `-y`, skip all confirmation prompts.
 - BLOCKED if routing incomplete: finish all write operations before reporting.
 
@@ -100,7 +100,7 @@ Follow `~/.maestro/workflows/retrospective.md` Stages 1–8 in order.
 - [ ] If routing enabled (default): every recommendation either created an artifact or was explicitly skipped by user
 - [ ] Spec entries (if any) appended as `<spec-entry>` to matching `.workflow/specs/{category-file}.md`
 - [ ] Issue rows (if any) match canonical issues.jsonl schema (status "open", full issue_history, all required fields)
-- [ ] Note tips (if any) created via `Skill({ skill: "manage-knowhow-capture", args: "tip ..." })`
+- [ ] Note tips (if any) created via `invoke /skill: "manage-knowhow-capture", args: "tip ..." })`
 - [ ] `.workflow/specs/learnings.md` appended with one `<spec-entry>` per insight regardless of routing target
 - [ ] No existing phase artifacts modified (verification.json, review.json, plan.json untouched)
 - [ ] Confirmation banner displays routing counts and next-step suggestions

package/skills/quality-review/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: quality-review
 description: "Use after execution to evaluate code quality across correctness, security, performance, and architecture Arguments: <phase> [--level quick|standard|deep] [--dimensions security,architecture,...] [--skip-specs]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,11 +9,11 @@ Multi-dimensional code review on a phase's changed files. Three levels (quick/st
 </purpose>
 
 <required_reading>
-@~/.maestro/workflows/review.md
+~/.pi/agent/packages/pi-maestro-flow/workflows/review.md
 </required_reading>
 
 <deferred_reading>
-- [index.json](~/.maestro/templates/index.json) — read when updating phase index after review
+- [index.json](~/.pi/agent/packages/pi-maestro-flow/templates/index.json) — read when updating phase index after review
 </deferred_reading>
 
 <context>
@@ -60,7 +60,7 @@ Each artifact's type determines its outputs at `.workflow/{a.path}/`:
 </invariants>
 
 <execution>
-Follow '~/.maestro/workflows/review.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/review.md' completely.
 
 ### Phase Gates (MANDATORY, BLOCKING)
 

package/skills/quality-sync/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: quality-sync
 description: "Sync codebase docs by tracing git diff impact Arguments: [--full] [--since <commit|HEAD~N>] [--dry-run]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,7 +9,7 @@ Sync codebase docs after code changes: git diff → trace impact via doc-index.j
 </purpose>
 
 <required_reading>
-@~/.maestro/workflows/sync.md
+~/.pi/agent/packages/pi-maestro-flow/workflows/sync.md
 </required_reading>
 
 <context>
@@ -30,7 +30,7 @@ $ARGUMENTS -- optional flags:
 </invariants>
 
 <execution>
-Follow '~/.maestro/workflows/sync.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/sync.md' completely.
 
 ### Phase Gates (MANDATORY, BLOCKING)
 

package/skills/quality-test/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: quality-test
 description: "Use when implementation needs user acceptance testing with interactive verification and gap closure Arguments: [phase] [--smoke] [--auto-fix] [--frontend-verify]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,7 +9,7 @@ UAT-style conversational testing for a completed phase. Interactive scenario wal
 </purpose>
 
 <required_reading>
-@~/.maestro/workflows/test.md
+~/.pi/agent/packages/pi-maestro-flow/workflows/test.md
 </required_reading>
 
 <context>
@@ -31,7 +31,7 @@ Flags, artifact context resolution, and output directory format defined in workf
 </invariants>
 
 <execution>
-**Mode select:** `--frontend-verify` → 走下方 **Frontend Verify Mode**（确定性浏览器 smoke，**不是**对话式 UAT）；否则 Follow '~/.maestro/workflows/test.md' completely.
+**Mode select:** `--frontend-verify` → 走下方 **Frontend Verify Mode**（确定性浏览器 smoke，**不是**对话式 UAT）；否则 Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/test.md' completely.
 
 ### Frontend Verify Mode (`--frontend-verify`)
 
@@ -54,7 +54,7 @@ Ralph-invoked 完成：`maestro ralph complete <idx> --status {STATUS} --evidenc
 
 ---
 
-Follow '~/.maestro/workflows/test.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/test.md' completely.
 
 ### Phase Gates (MANDATORY, BLOCKING)
 

package/skills/scholar-anti-ai-writing/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: scholar-anti-ai-writing
 description: "Remove AI writing patterns from academic prose. Detects and fixes inflated symbolism, promotional language, superficial analyses, vague attributions, AI vocabulary, and formulaic structures. Supports English and Chinese. Triggers on \"remove AI patterns\", \"humanize text\", \"anti-AI polish\", \"去除AI写作痕迹\", \"人性化处理\"."
-allowed-tools: Read Write Edit Bash Glob Grep AskUserQuestion TodoWrite
+allowed-tools: Read Write Edit Bash Glob Grep maestro
 ---
 
 # Scholar Anti-AI Writing

package/skills/scholar-citation-verify/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: scholar-citation-verify
 description: "Four-layer citation verification for academic papers. Scans LaTeX/BibTeX files, verifies every citation via WebSearch and Google Scholar, generates verification report with fix suggestions. Triggers on \"verify citations\", \"check references\", \"citation verification\", \"prevent fake citations\", \"引用验证\"."
-allowed-tools: Read Write Edit Bash Glob Grep WebSearch WebFetch AskUserQuestion TodoWrite
+allowed-tools: Read Write Edit Bash Glob Grep WebSearch WebFetch maestro
 ---
 
 # Scholar Citation Verify