pi-maestro-flow 0.2.0 → 0.3.0

package/skills/maestro-guard/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-guard
 description: "Manage editing boundary restrictions Arguments: <on|off|status|allow <path>|deny <path>>"
-allowed-tools: Read Write Bash Glob
+allowed-tools: Read Write Bash Glob maestro
 ---
 
 <purpose>
@@ -33,7 +33,7 @@ and blocks operations targeting files outside boundaries. Requires hooks level >
 <invariants>
 1. **Config-only mutation** — guard MUST only modify the `guard` section of `.workflow/config.json`; NEVER touch other config sections or files
 2. **Non-destructive** — `off` MUST preserve existing paths and mode; NEVER clear the path list when disabling
-3. **Mode switch confirmation** — switching between allow/deny mode MUST require AskUserQuestion confirmation when existing paths will be cleared
+3. **Mode switch confirmation** — switching between allow/deny mode MUST require user prompt confirmation when existing paths will be cleared
 4. **Hook dependency** — guard MUST warn when enabled but `workflow-guard` hook is not active (hooks level < full)
 5. **Path normalization** — all paths MUST use forward slashes with trailing slash for directories; NEVER store raw backslash paths
 </invariants>
@@ -52,7 +52,7 @@ and blocks operations targeting files outside boundaries. Requires hooks level >
 
 **GATE 3: Execute → Confirm**
 - REQUIRED: Config mutation applied (for on/off/allow/deny) or status displayed (for status).
-- REQUIRED: Mode-switch AskUserQuestion answered (for allow↔deny transitions with existing paths).
+- REQUIRED: Mode-switch user prompt answered (for allow↔deny transitions with existing paths).
 - BLOCKED if: user declines mode switch.
 
 **Step 1: Parse subcommand**
@@ -85,14 +85,14 @@ Read `.workflow/config.json`. If file missing, initialize with empty guard secti
 
 **`allow <path>`:**
 - Normalize path to forward slashes, ensure trailing slash for directories
-- If `guard.mode` is `deny`, AskUserQuestion: "Switching from deny to allow mode will clear existing paths ({N} paths). Continue?" — abort if user declines.
+- If `guard.mode` is `deny`, user prompt: "Switching from deny to allow mode will clear existing paths ({N} paths). Continue?" — abort if user declines.
 - Add path to `guard.paths` (deduplicate)
 - Set `guard.enabled = true` if not already
 - Write config
 
 **`deny <path>`:**
 - Normalize path to forward slashes, ensure trailing slash for directories
-- If `guard.mode` is `allow`, AskUserQuestion: "Switching from allow to deny mode will clear existing paths ({N} paths). Continue?" — abort if user declines.
+- If `guard.mode` is `allow`, user prompt: "Switching from allow to deny mode will clear existing paths ({N} paths). Continue?" — abort if user declines.
 - Set `guard.mode = "deny"`
 - Add path to `guard.paths` (deduplicate)
 - Set `guard.enabled = true` if not already (symmetric with `allow`: adding a deny path auto-enables the guard)

package/skills/maestro-help/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-help
 description: "Maestro Flow 命令帮助系统。搜索命令、浏览技能、工作流推荐、新手引导。Triggers on \"maestro-help\", \"帮助\", \"命令\", \"怎么用\", \"skill\", \"workflow\", \"maestro 怎么用\"."
-allowed-tools: Read Grep Glob AskUserQuestion
+allowed-tools: Read Grep Glob maestro
 ---
 
 # Maestro Help
@@ -314,8 +314,8 @@ Odyssey 长周期循环（独立路径）
 ## Related Resources
 
 - **Guide 目录**: `guide/` — 17 个专题指南文档
-- **Delegate 参考**: `~/.maestro/workflows/delegate-usage.md`
-- **Coding 哲学**: `~/.maestro/workflows/coding-philosophy.md`
+- **Delegate 参考**: `~/.pi/agent/packages/pi-maestro-flow/workflows/delegate-usage.md`
+- **Coding 哲学**: `~/.pi/agent/packages/pi-maestro-flow/workflows/coding-philosophy.md`
 - **CLI 工具配置**: `~/.maestro/cli-tools.json`
 
 ## Statistics

package/skills/maestro-impeccable/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-impeccable
 description: "Use when designing, auditing, polishing, or improving frontend UI — websites, dashboards, landing pages, components Arguments: <command|intent> [target] [flags] — 可选 chain: build|redesign|improve|enhance|launch|harden|foundation|live"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion TodoWrite
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -25,7 +25,7 @@ $ARGUMENTS first word determines mode:
 
 ## Command Routing
 
-All workflows at `~/.maestro/workflows/impeccable/{command}.md`:
+All workflows at `~/.pi/agent/packages/pi-maestro-flow/workflows/impeccable/{command}.md`:
 
 | Command | Category | Description |
 |---------|----------|-------------|
@@ -61,7 +61,7 @@ responsive-design.md, spatial-design.md, typography.md, ux-writing.md
 
 ## Chains
 
-Chain step names below reuse Command Routing names but resolve through the chain runner. To avoid ambiguity with Direct command invocation, internal display, todo items, and session status records always tag chain steps with the `impeccable:` prefix (e.g. `impeccable:craft`, `impeccable:critique`). The bare names in this table refer to the workflow file at `~/.maestro/workflows/impeccable/{name}.md` that the chain step reads.
+Chain step names below reuse Command Routing names but resolve through the chain runner. To avoid ambiguity with Direct command invocation, internal display, todo items, and session status records always tag chain steps with the `impeccable:` prefix (e.g. `impeccable:craft`, `impeccable:critique`). The bare names in this table refer to the workflow file at `~/.pi/agent/packages/pi-maestro-flow/workflows/impeccable/{name}.md` that the chain step reads.
 
 | Chain | Steps | Scenario |
 |-------|-------|----------|
@@ -153,7 +153,7 @@ Before reading any command workflow:
 
 1. **Context**: `maestro load --type spec --category ui` → if empty → `maestro impeccable load-context`
 2. **PRODUCT.md**: missing/placeholder (<200 chars / `[TODO]`) → execute teach first, then resume original task
-3. **Register**: identify brand/product → Read `~/.maestro/workflows/impeccable/{brand|product}.md`
+3. **Register**: identify brand/product → Read `~/.pi/agent/packages/pi-maestro-flow/workflows/impeccable/{brand|product}.md`
 
 ## Direct Execution
 
@@ -164,7 +164,7 @@ Before reading any command workflow:
    Category: {category} | Target: {target}
    ─────────────────────────────────────────
    ```
-3. Read `~/.maestro/workflows/impeccable/{command}.md`
+3. Read `~/.pi/agent/packages/pi-maestro-flow/workflows/impeccable/{command}.md`
 4. **TodoWrite tracking**: create todo items for each major phase in the workflow file
    - Format: `[{command}] {phase description}`
    - Mark each phase completed immediately upon finishing
@@ -192,7 +192,7 @@ Before reading any command workflow:
    - `↺` marks refine loop with max iteration count
    - Conditional steps show trigger condition
    - Skipped conditional steps marked `(skipped)`
-3. **Confirm chain session**: AskUserQuestion "Create chain session for '{chain_type}' targeting '{target}'?" — proceed only if user confirms. On decline, abort chain.
+3. **Confirm chain session**: user prompt "Create chain session for '{chain_type}' targeting '{target}'?" — proceed only if user confirms. On decline, abort chain.
    Create session: `.workflow/.maestro/ui-craft-{YYYYMMDD-HHmmss}/status.json`
    ```json
    { "chain_type": "...", "target": "...", "steps": [...], "current_step": 0,
@@ -203,7 +203,7 @@ Before reading any command workflow:
    - If conditional step is skipped, immediately mark completed
    - Quality gate steps include threshold: `[chain] step 5: impeccable:critique ◆ gate ≥26/40`
 5. For each step:
-   - Read `~/.maestro/workflows/impeccable/{command}.md` → execute
+   - Read `~/.pi/agent/packages/pi-maestro-flow/workflows/impeccable/{command}.md` → execute
    - **Step start**: TodoWrite marks current step in_progress
    - **Step done**: TodoWrite marks completed + update status.json (`current_step`, step `status`)
    - **Step failed**: TodoWrite marks completed (with note) + record reason

package/skills/maestro-init/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-init
 description: "Initialize project with auto state detection Arguments: [-y] [--from <source>] [--from-brainstorm SESSION-ID]"
-allowed-tools: Read Write Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,15 +9,12 @@ Initialize project: detect state, create `.workflow/` with project.md, state.jso
 Entry point; downstream: maestro-roadmap or maestro-brainstorm.
 </purpose>
 
-<required_reading>
-@~/.maestro/workflows/init.md
-</required_reading>
+> **Required**: Read `~/.pi/agent/packages/pi-maestro-flow/workflows/init.md` before proceeding.
 
-<deferred_reading>
-- [project.md](~/.maestro/templates/project.md) — read when generating project description
-- [state.json](~/.maestro/templates/state.json) — read when creating initial state
-- [config.json](~/.maestro/templates/config.json) — read when creating workflow configuration
-</deferred_reading>
+> **Reference files** (read when needed):
+> - [project.md](~/.pi/agent/packages/pi-maestro-flow/templates/project.md) — read when generating project description
+> - [state.json](~/.pi/agent/packages/pi-maestro-flow/templates/state.json) — read when creating initial state
+> - [config.json](~/.pi/agent/packages/pi-maestro-flow/templates/config.json) — read when creating workflow configuration
 
 <context>
 $ARGUMENTS — none for interactive mode, or `-y` with `@file` reference for auto mode.
@@ -39,12 +36,12 @@ Check for `.workflow/state.json` -- loads context if project already initialized
 1. **Idempotent init** — re-running init on an already-initialized project MUST detect existing `.workflow/` and warn (E002); NEVER silently overwrite existing state
 2. **Scope guard** — init MUST only make initialization decisions; NEVER prejudge roadmap structure, plan scope, or implementation details
 3. **All artifacts required** — init MUST NOT report completion until project.md, state.json, and config.json all exist; missing artifacts MUST be created before exit
-4. **Template-driven** — deferred templates (project.md, state.json, config.json) MUST be read from `~/.maestro/templates/` and customized; NEVER generate from scratch without template
+4. **Template-driven** — deferred templates (project.md, state.json, config.json) MUST be read from `~/.pi/agent/packages/pi-maestro-flow/templates/` and customized; NEVER generate from scratch without template
 5. **Interview writes back** — all interactive decisions MUST be written to project.md/config.json before proceeding to research or completion; NEVER leave decisions unrecorded
 </invariants>
 
 <interview_protocol>
-Follows @~/.maestro/workflows/interview-mechanics.md standard.
+Follows `~/.pi/agent/packages/pi-maestro-flow/workflows/interview-mechanics.md` standard.
 
 **Interaction mode**: convergent menu-driven
 **Decision tree** (strict order): project type (greenfield / existing codebase onboarding) → tech stack detection and confirmation → directory structure preferences → initial configuration (specs categories, wiki bootstrap)
@@ -78,7 +75,7 @@ Follows @~/.maestro/workflows/interview-mechanics.md standard.
 1. Check if `.workflow/` already exists — if so, load state and warn (E002 for greenfield conflicts)
 2. Validate `--from` source is accessible if provided
 
-Follow '~/.maestro/workflows/init.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/init.md' completely.
 
 ### Artifact Verification (before completion)
 

package/skills/maestro-merge/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-merge
 description: "Merge milestone worktree branch back to main Arguments: -m <milestone-number> [--force] [--dry-run] [--no-cleanup] [--continue]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,9 +9,7 @@ Merge a milestone worktree branch back into main, sync scratch artifacts, and re
 Two-phase: git merge first, artifact sync second (only after git succeeds).
 </purpose>
 
-<required_reading>
-@~/.maestro/workflows/merge.md
-</required_reading>
+> **Required**: Read `~/.pi/agent/packages/pi-maestro-flow/workflows/merge.md` before proceeding.
 
 <context>
 $ARGUMENTS -- milestone number and optional flags.
@@ -20,7 +18,7 @@ Flags (`-m`, `--force`, `--dry-run`, `--no-cleanup`, `--continue`), merge sequen
 </context>
 
 <execution>
-Follow '~/.maestro/workflows/merge.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/merge.md' completely.
 
 ### Phase Gates (MANDATORY, BLOCKING)
 
@@ -44,7 +42,7 @@ Follow '~/.maestro/workflows/merge.md' completely.
 <completion>
 ### Knowledge inquiry
 
-After successful merge, use `AskUserQuestion` to confirm knowledge persistence:
+After successful merge, use `user prompt` to confirm knowledge persistence:
 
 ```
 question: "Merge 完成。是否记录里程碑经验教训？"
@@ -61,8 +59,8 @@ User selects "记录经验" → prompt for title/insight, then persist via `Skil
 
 | Condition | Suggestion |
 |-----------|-----------|
-| Merge complete | Skill({ skill: "manage-status" }) |
-| Audit needed | Skill({ skill: "maestro-milestone-audit" }) |
+| Merge complete | invoke /skill: "manage-status" }) |
+| Audit needed | invoke /skill: "maestro-milestone-audit" }) |
 </completion>
 
 <error_codes>

package/skills/maestro-milestone-audit/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-milestone-audit
 description: "Audit current milestone for cross-phase integration gaps Arguments: [<milestone>]"
-allowed-tools: Read Write Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,9 +9,7 @@ Audit milestone for phase coverage, execution completeness, and integration gaps
 Produces audit-report.md with PASS/FAIL verdict.
 </purpose>
 
-<required_reading>
-@~/.maestro/workflows/milestone-audit.md
-</required_reading>
+> **Required**: Read `~/.pi/agent/packages/pi-maestro-flow/workflows/milestone-audit.md` before proceeding.
 
 <context>
 Milestone: $ARGUMENTS (optional -- defaults to current_milestone from state.json).
@@ -40,7 +38,7 @@ If $ARGUMENTS is empty AND current_milestone is null → raise E001 with message
 </context>
 
 <execution>
-Follow '~/.maestro/workflows/milestone-audit.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/milestone-audit.md' completely.
 
 Audit checklist steps (phase coverage, ad-hoc completeness, execution completeness, cross-artifact integration) are defined in workflow `milestone-audit.md`.
 

package/skills/maestro-milestone-complete/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-milestone-complete
 description: "Archive completed milestone and prepare for next Arguments: [<milestone>]"
-allowed-tools: Read Write Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,13 +9,10 @@ Archive passed milestone: validate, archive artifacts, extract knowhow, advance
 Requires audit PASS; produces milestone archive and learnings.
 </purpose>
 
-<required_reading>
-@~/.maestro/workflows/milestone-complete.md
-</required_reading>
+> **Required**: Read `~/.pi/agent/packages/pi-maestro-flow/workflows/milestone-complete.md` before proceeding.
 
-<deferred_reading>
-- [state.json](~/.maestro/templates/state.json) — read when updating milestone_history and advancing state
-</deferred_reading>
+> **Reference files** (read when needed):
+> - [state.json](~/.pi/agent/packages/pi-maestro-flow/templates/state.json) — read when updating milestone_history and advancing state
 
 <context>
 Milestone: $ARGUMENTS (optional -- defaults to current_milestone from state.json).
@@ -30,7 +27,7 @@ If $ARGUMENTS is empty AND current_milestone is null → raise E001 with message
 </context>
 
 <execution>
-Follow '~/.maestro/workflows/milestone-complete.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/milestone-complete.md' completely.
 
 Archive flow steps (validation, directory archival, artifact history, knowhow extraction, state advancement, cleanup) are defined in workflow `milestone-complete.md`.
 
@@ -52,7 +49,7 @@ Archive flow steps (validation, directory archival, artifact history, knowhow ex
 - BLOCKED if missing: knowhow extraction not attempted or project.md not updated — state advancement requires completed knowledge capture.
 
 **GATE 4: State Advancement → Completion**
-- REQUIRED: AskUserQuestion confirmation before state.json advancement — show current milestone, next milestone (or null for adhoc), and artifacts to clear. User must confirm or abort.
+- REQUIRED: user prompt confirmation before state.json advancement — show current milestone, next milestone (or null for adhoc), and artifacts to clear. User must confirm or abort.
 - REQUIRED: state.json updated — next milestone as current (standard) or current_milestone=null (adhoc) (after confirmation).
 - REQUIRED: Roadmap snapshot saved (standard only).
 - BLOCKED if missing: state.json not advanced — project remains stuck on completed milestone.
@@ -67,10 +64,10 @@ After knowhow extraction (step 4), scan `learnings.md` for promotion candidates:
 2. **Convention drift detection**: Compare executed task summaries against `coding-conventions.md` and `architecture-constraints.md`:
    → Ask: "Were any established conventions bypassed during this milestone? Should conventions be updated?"
 
-3. **Wiki island check**: AskUserQuestion "Run wiki-connect --fix to link newly extracted knowledge?" — execute `manage-wiki connect --fix` only if user confirms.
+3. **Wiki island check**: user prompt "Run wiki-connect --fix to link newly extracted knowledge?" — execute `manage-wiki connect --fix` only if user confirms.
 
-Each promotion candidate requires explicit user confirmation via AskUserQuestion before writing:
-- **"Promote"** → invoke `Skill({ skill: "spec-add", args: "<category> <content>" })` with promoted content, preserving original date and source traceability.
+Each promotion candidate requires explicit user confirmation via user prompt before writing:
+- **"Promote"** → invoke `invoke /skill: "spec-add", args: "<category> <content>" })` with promoted content, preserving original date and source traceability.
 - **"Skip"** → do not promote this candidate; proceed to next.
 - **"Skip all"** → skip remaining candidates.
 

package/skills/maestro-milestone-release/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-milestone-release
 description: "Bump version, generate changelog, tag milestone Arguments: [<version>] [--bump patch|minor|major] [--dry-run] [--no-tag] [--no-push]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -10,9 +10,7 @@ Package a completed milestone into a releasable version: version bump → change
 Pipeline position: downstream of `/maestro-milestone-complete`. Terminal command.
 </purpose>
 
-<required_reading>
-@~/.maestro/workflows/milestone-release.md
-</required_reading>
+> **Required**: Read `~/.pi/agent/packages/pi-maestro-flow/workflows/milestone-release.md` before proceeding.
 
 <context>
 $ARGUMENTS -- optional explicit version string and flags.
@@ -40,14 +38,14 @@ $ARGUMENTS -- optional explicit version string and flags.
 </context>
 
 <interview_protocol>
-Follows @~/.maestro/workflows/interview-mechanics.md standard.
+Follows `~/.pi/agent/packages/pi-maestro-flow/workflows/interview-mechanics.md` standard.
 
 **Decision points**: version bump type (major / minor / patch / custom), changelog review and confirmation
 **Scope guard**: only release decisions; do not prejudge next milestone scope
 </interview_protocol>
 
 <execution>
-Follow '~/.maestro/workflows/milestone-release.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/milestone-release.md' completely.
 
 ### Phase Gates (MANDATORY, BLOCKING)
 
@@ -61,13 +59,13 @@ Follow '~/.maestro/workflows/milestone-release.md' completely.
 
 **GATE 3: Changelog → Tag/Push**
 - REQUIRED: CHANGELOG.md entry written with milestone summary + grouped changes.
-- REQUIRED: AskUserQuestion confirmation before creating release commit — show version, changelog diff, and files to be committed. User must confirm or abort.
+- REQUIRED: user prompt confirmation before creating release commit — show version, changelog diff, and files to be committed. User must confirm or abort.
 - REQUIRED: Release commit created with conventional message (after confirmation).
 
 **GATE 4: Tag → Push → Completion**
-- REQUIRED: AskUserQuestion confirmation before git tag creation — show tag name and annotation (unless --no-tag). User must confirm or abort.
+- REQUIRED: user prompt confirmation before git tag creation — show tag name and annotation (unless --no-tag). User must confirm or abort.
 - REQUIRED: Annotated git tag created (unless --no-tag) (after confirmation).
-- REQUIRED: AskUserQuestion confirmation before git push — show remote and refs to push (unless --no-push). User must confirm or abort.
+- REQUIRED: user prompt confirmation before git push — show remote and refs to push (unless --no-push). User must confirm or abort.
 - REQUIRED: state.json updated with last_release_version + last_release_at.
 
 For `--dry-run`: print computed version, changelog diff, and tag name without side effects.
@@ -126,6 +124,6 @@ Status verdicts:
 - [ ] Release commit created with conventional message
 - [ ] Annotated git tag created (unless `--no-tag`)
 - [ ] Commit + tag pushed to remote (unless `--no-push` or push failed → W002)
-- [ ] User confirmed before each destructive git operation (commit, tag, push) via AskUserQuestion
-- [ ] state.json updated with last_release_version + last_release_at timestamp (after AskUserQuestion confirmation)
+- [ ] User confirmed before each destructive git operation (commit, tag, push) via user prompt
+- [ ] state.json updated with last_release_version + last_release_at timestamp (after user prompt confirmation)
 </success_criteria>

package/skills/maestro-next/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-next
 description: "Single-command recommendation — pick the best next command from the pool and execute it Arguments: <intent> [-y] [--dry-run] [--top N] [--list]"
-allowed-tools: Read Bash Glob Grep Skill AskUserQuestion
+allowed-tools: Read Bash Glob Grep maestro
 ---
 
 <purpose>
@@ -38,7 +38,7 @@ S_STATE     — 读 project state、推断 lifecycle_position         PERSIST:
 S_RANK      — 路由表评分、生成 top-N candidates                 PERSIST: —
 S_LIST      — `--list` 模式：分组展示候选池                     PERSIST: —
 S_PRESENT   — 显示 top pick + 备选 + 推荐理由 + 执行参数        PERSIST: —
-S_CONFIRM   — AskUserQuestion 选择/修改参数（auto_mode 跳过）    PERSIST: —
+S_CONFIRM   — user prompt 选择/修改参数（auto_mode 跳过）    PERSIST: —
 S_EXECUTE   — `Skill({ skill, args })` 单次调用                 PERSIST: —
 S_FALLBACK  — intent 空且 clarification 失败                    PERSIST: —
 </states>
@@ -49,7 +49,7 @@ S_PARSE:
   → S_LIST       WHEN: --list flag
   → S_STATE      WHEN: intent text present
   → S_STATE      WHEN: keyword "continue"/"next"/"go"/"继续"/"下一步"/"接下来"
-  → S_PARSE      WHEN: no intent (max 1 clarify round)    DO: AskUserQuestion
+  → S_PARSE      WHEN: no intent (max 1 clarify round)    DO: user prompt
   → S_FALLBACK   WHEN: clarification empty
 
 S_STATE:
@@ -71,7 +71,7 @@ S_CONFIRM:
   → END          WHEN: 用户取消
 
 S_EXECUTE:
-  → END          DO: Skill({ skill: <chosen>, args: <args> }) → 输出 "✅ 已执行 /<command>"
+  → END          DO: invoke /skill: <chosen>, args: <args> }) → 输出 "✅ 已执行 /<command>"
 
 S_FALLBACK:
   → END          DO: raise E001
@@ -261,7 +261,7 @@ AskUserQuestion (single-select, header: "执行确认"):
 - [ ] top pick 展示附"推荐理由"（命中规则 + lifecycle 位置）
 - [ ] `--dry-run` 仅展示，不执行
 - [ ] `-y` 自动执行 top pick；用户传入时透传到 skill args
-- [ ] 非自动模式通过 AskUserQuestion 确认或选备选
+- [ ] 非自动模式通过 user prompt 确认或选备选
 - [ ] 选定命令通过单次 `Skill()` 调用执行
 - [ ] 不创建 session / 不生成 status.json / 不触发后续 chain
 - [ ] `--list` 模式按 workflow 簇分组展示

package/skills/maestro-overlay/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-overlay
 description: "Create or edit command overlays from natural language Arguments: <intent> — 描述要添加的规则或步骤，如 'always verify after execute'"
-allowed-tools: Read Write Bash Glob Grep AskUserQuestion
+allowed-tools: Read Write Bash Glob Grep maestro
 ---
 
 <purpose>
@@ -10,7 +10,7 @@ Turn natural-language instructions into command overlays — JSON patch files th
 </purpose>
 
 <required_reading>
-@~/.maestro/workflows/overlays.md
+Read and follow `~/.pi/agent/packages/pi-maestro-flow/workflows/overlays.md`.
 @~/.maestro/cli-tools.json
 </required_reading>
 
@@ -37,14 +37,14 @@ Turn natural-language instructions into command overlays — JSON patch files th
 2. **Idempotent** — re-running `maestro overlay apply` with the same overlay JSON MUST produce no file changes
 3. **Creation only** — this skill MUST only create overlays; listing and removal are handled by `maestro overlay list` (ink TUI)
 4. **Pristine source preferred** — injection point analysis MUST read from `$PKG_ROOT/.claude/commands/` (untouched originals) first, fall back to `~/.claude/commands/` only if pristine unavailable
-5. **User approval before write** — overlay JSON MUST be shown and approved via AskUserQuestion before writing to disk; NEVER auto-install without confirmation
-6. **Chain skip option mandatory** — if a skill chain is configured, the injected content MUST include a "Skip" option in AskUserQuestion; NEVER force the user into a chain
+5. **User approval before write** — overlay JSON MUST be shown and approved via user prompt before writing to disk; NEVER auto-install without confirmation
+6. **Chain skip option mandatory** — if a skill chain is configured, the injected content MUST include a "Skip" option in user prompt; NEVER force the user into a chain
 </invariants>
 
 <execution>
 ### 1. Parse user intent
 
-Treat the argument as natural-language intent. If unclear, ask up to 2 questions with AskUserQuestion: (a) which command(s) to target, (b) where in the command flow the injection should happen.
+Treat the argument as natural-language intent. If unclear, ask up to 2 questions with user prompt: (a) which command(s) to target, (b) where in the command flow the injection should happen.
 
 ### 2. Identify targets, injection points, and visualize
 
@@ -71,16 +71,16 @@ If the user wants a whole new section, use `mode: new-section` with `afterSectio
   <success_criteria>
 ```
 
-Use AskUserQuestion to confirm:
+Use user prompt to confirm:
 - **"Confirm"** — proceed with this injection point
 - **"Pick different section"** — re-select section/mode
 - **"Cancel"** — abort
 
 ### 2.5. Skill chain configuration
 
-After confirming the injection point, ask whether this overlay should chain to another skill upon completion. This enables the overlay's injected content to hand off to a skill via AskUserQuestion at runtime, using `Skill({ skill: "...", args: "..." })` syntax.
+After confirming the injection point, ask whether this overlay should chain to another skill upon completion. This enables the overlay's injected content to hand off to a skill via user prompt at runtime, using `invoke /skill: "...", args: "..." })` syntax.
 
-Use AskUserQuestion:
+Use user prompt:
 - **"No chain"** — standard overlay, no skill handoff
 - **"Chain to skill"** → ask for the target skill name (e.g., `quality-review`, `maestro-execute`, `quality-test`)
 - **"Chain with alternatives"** → ask for primary skill + 1-2 alternative skills
@@ -114,34 +114,34 @@ Build a slug from the user's intent (kebab-case, lowercase). Write to `~/.maestr
 - `@~/.maestro/...` references are encouraged for pointing at docs
 - Escape `\n` in JSON strings; use a HEREDOC via Bash if content is long
 
-**Skill chain content** — if a chain was configured in Step 2.5, append a Skill Handoff block at the end of the patch `content`. The handoff uses AskUserQuestion so the user controls whether to proceed:
+**Skill chain content** — if a chain was configured in Step 2.5, append a Skill Handoff block at the end of the patch `content`. The handoff uses user prompt so the user controls whether to proceed:
 
 ```markdown
 ---
 
 **Skill Handoff** (overlay)
 
-After the above step completes, use AskUserQuestion:
+After the above step completes, use user prompt:
 - "Proceed to /quality-review" — Hand off to quality review
 - "Skip" — Continue with current command flow
 - "Alternative: /maestro-execute" — Run execution with built-in verification instead
 
 On user selection:
-- Proceed → Skill({ skill: "quality-review", args: "{phase}" })
-- Alternative → Skill({ skill: "maestro-execute", args: "{phase}" })
+- Proceed → invoke /skill: "quality-review", args: "{phase}" })
+- Alternative → invoke /skill: "maestro-execute", args: "{phase}" })
 - Skip → continue normally
 ```
 
 Handoff rules:
 - Always include a **"Skip"** option — the user can always decline the chain
-- Use `Skill({ skill: "<name>", args: "..." })` syntax for handoff calls
+- Use `invoke /skill: "<name>", args: "..." })` syntax for handoff calls
 - Mark handoff heading with `(overlay)` tag
 - Support runtime variable placeholders: `{phase}`, `{description}`, `{session_id}`
 - Keep handoff block under 10 lines of markdown
 
 ### 3.5. Content approval
 
-Display the full overlay JSON to the user. AskUserQuestion:
+Display the full overlay JSON to the user. user prompt:
 - **"Approve & install"** — proceed to installation
 - **"Edit"** — user provides corrections, re-draft
 - **"Cancel"** — discard overlay, do not write
@@ -172,7 +172,7 @@ Show the user:
 Name:    <slug>
 Path:    ~/.maestro/overlays/<slug>.json
 Targets: maestro-execute (applied), maestro-plan (skipped: missing)
-Chain:   quality-review (via AskUserQuestion) | none
+Chain:   quality-review (via user prompt) | none
 Scopes:  [global]
 
 Re-apply: maestro overlay apply
@@ -190,7 +190,7 @@ After the report, remind the user they can run `maestro overlay list` for the in
 - [ ] Re-running `maestro overlay apply` produces no file changes (idempotent)
 - [ ] User shown the report with target list and removal instructions
 - [ ] Injection point preview shown (with existing overlays + `>>>` marker) and confirmed before drafting
-- [ ] If chain configured, `content` includes Skill Handoff block with AskUserQuestion + Skip option + `Skill()` calls
+- [ ] If chain configured, `content` includes Skill Handoff block with user prompt + Skip option + `Skill()` calls
 </success_criteria>
 
 <completion>

package/skills/maestro-plan/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-plan
 description: "Use when creating, revising, or verifying an execution plan for a milestone or task Arguments: [milestone] [--spec SPEC-xxx] [-y] [--gaps] [--tdd] [--dir <path>] [--from <source>] [--revise [instructions]] [--check <plan-dir>]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -9,16 +9,13 @@ Create, revise, or verify execution plans (5-stage pipeline).
 Produces plan.json + TASK files; registers PLN artifact in state.json.
 </purpose>
 
-<required_reading>
-@~/.maestro/workflows/plan.md
-</required_reading>
+> **Required**: Read `~/.pi/agent/packages/pi-maestro-flow/workflows/plan.md` before proceeding.
 
-<deferred_reading>
-- [plan.json](~/.maestro/templates/plan.json) — read when generating plan output
-- [task.json](~/.maestro/templates/task.json) — read when generating task files
-- [state.json](~/.maestro/templates/state.json) — read when registering artifact
-- [boundary-grill.md](~/.maestro/workflows/boundary-grill.md) — read when boundary conflicts detected (in P4)
-</deferred_reading>
+> **Reference files** (read when needed):
+> - [plan.json](~/.pi/agent/packages/pi-maestro-flow/templates/plan.json) — read when generating plan output
+> - [task.json](~/.pi/agent/packages/pi-maestro-flow/templates/task.json) — read when generating task files
+> - [state.json](~/.pi/agent/packages/pi-maestro-flow/templates/state.json) — read when registering artifact
+> - [boundary-grill.md](~/.pi/agent/packages/pi-maestro-flow/workflows/boundary-grill.md) — read when boundary conflicts detected (in P4)
 
 <context>
 $ARGUMENTS — milestone number, or no args for current milestone, with optional flags.
@@ -59,7 +56,7 @@ Bash("maestro collab preflight --phase <phase-number>")
 ```
 If exit code is 1, present warnings and ask whether to proceed.
 
-Follow '~/.maestro/workflows/plan.md' completely.
+Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/plan.md' completely.
 
 ### Plan Agent Model
 
@@ -149,7 +146,7 @@ Status verdicts:
 - **NEEDS_RETRY** — Plan failed (tooling error, transient issue); ralph will retry
 - **BLOCKED** — External hard blocker (e.g., upstream artifact missing, dependency unavailable); pass `--reason "..."`
 
-> Ambiguous requirements are NOT a completion status — resolve them in-place via `AskUserQuestion` during planning (≤3 rounds), then proceed to DONE. `NEEDS_CONTEXT` has been removed; context shortage is handled by the harness's automatic compaction.
+> Ambiguous requirements are NOT a completion status — resolve them in-place via `user prompt` during planning (≤3 rounds), then proceed to DONE. `NEEDS_CONTEXT` has been removed; context shortage is handled by the harness's automatic compaction.
 
 ### Next-step routing
 

package/skills/maestro-player/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: maestro-player
 description: "Play workflow templates with checkpoint resume Arguments: <template-slug|path> [--context key=value...] [-c [session-id]] [--list] [--dry-run]"
-allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion Skill
+allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
 ---
 
 <purpose>
@@ -59,7 +59,7 @@ $ARGUMENTS — template slug/path, or flags.
 }
 ```
 
-**Output boundary**: ALL file writes MUST target `.workflow/.maestro/player-*/` (session status.json + step outputs) only. Template files (`~/.maestro/templates/workflows/`) are read-only. NEVER modify source code or `.claude/commands/` files.
+**Output boundary**: ALL file writes MUST target `.workflow/.maestro/player-*/` (session status.json + step outputs) only. Template files (`~/.pi/agent/packages/pi-maestro-flow/templates/workflows/`) are read-only. NEVER modify source code or `.claude/commands/` files.
 </context>
 
 <invariants>
@@ -88,7 +88,7 @@ S_ROUTE:
   → handleList    WHEN: --list                              DO: scan index.json, display templates
   → S_RESUME      WHEN: -c flag
   → S_LOAD        WHEN: template slug/path provided
-  → handleList    WHEN: no args                             DO: display templates + AskUserQuestion
+  → handleList    WHEN: no args                             DO: display templates + user prompt
 
 S_RESUME:
   → S_EXEC_LOOP   WHEN: session found                      DO: A_RESUME_SESSION
@@ -107,7 +107,7 @@ S_EXEC_LOOP:
   → END           WHEN: checkpoint pause                    DO: set status=paused, display resume command
   → END           WHEN: abort chosen                        DO: set status=aborted, save progress
   GUARD: cli nodes → Bash(run_in_background: true) + STOP, wait for callback
-  GUARD: on failure → on_fail: skip (log, advance) | retry (once) | abort (AskUserQuestion: Retry/Skip/Abort). Default on_fail when not specified: `abort` (prompt user via AskUserQuestion).
+  GUARD: on failure → on_fail: skip (log, advance) | retry (once) | abort (user prompt: Retry/Skip/Abort). Default on_fail when not specified: `abort` (prompt user via user prompt).
   GUARD: after step 3+ → display context hint "可随时 /maestro-player -c 恢复"
 
 S_COMPLETE:
@@ -129,7 +129,7 @@ S_COMPLETE:
 1. Resolve template: absolute path → as-is; relative → from cwd; slug → index.json lookup
 2. Parse `--context key=value` pairs
 3. Validate template (template_id, nodes, edges, context_schema required)
-4. Collect missing required variables via AskUserQuestion
+4. Collect missing required variables via user prompt
 5. Bind {variable} placeholders (leave {N-xxx.field} and {prev_*} for runtime)
 
 ### A_INIT_SESSION