maestro-flow 0.4.10 → 0.4.12

package/.agents/skills/maestro-blueprint/SKILL.md

@@ -0,0 +1,132 @@
+---
+name: maestro-blueprint
+description: Generate formal specification package (Product Brief, PRD, Architecture, Epics) through 6-phase document chain
+argument-hint: "<idea or @file> [-y] [-c] [--from <source>]"
+allowed-tools:
+  - read_file
+  - write_file
+  - edit_file
+  - shell
+  - find_files
+  - search
+  - delegate_subagent
+  - ask_user
+---
+<!-- Open-standard mirror generated by scripts/build-agents-standard.mjs — do not edit; re-run after editing .claude/ source. -->
+
+<purpose>
+Formal specification document chain producing a complete specification package through 6 sequential phases with multi-CLI analysis and interactive refinement. Pure documentation — no code generation, no roadmap generation.
+
+Parallel to `brainstorm` as an upstream origin command:
+- **brainstorm** = divergent exploration (lightweight, multi-role creative)
+- **blueprint** = convergent documentation (heavyweight, 6-phase formal spec chain)
+
+Output: `.workflow/blueprint/BLP-{slug}-{date}/` containing Product Brief, PRD, Architecture, and Epics.
+</purpose>
+
+<required_reading>
+@~/.maestro/workflows/blueprint.md
+</required_reading>
+
+<deferred_reading>
+- [blueprint-config.json](~/.maestro/templates/blueprint-config.json) — read when initializing blueprint configuration
+</deferred_reading>
+
+<context>
+$ARGUMENTS -- idea text, @file reference, or upstream context source.
+
+**Flags:**
+- `-y` / `--yes`: Auto mode — skip interactive questions, use recommended defaults
+- `-c` / `--continue`: Resume from last checkpoint (reads blueprint-config.json)
+- `--from <source>`: Load upstream context package (brainstorm:ID, @file, or path). Consumes context-package.json
+- `--from-brainstorm SESSION-ID`: (backward compat alias for `--from brainstorm:ID`)
+
+**Input types:**
+- Direct text: `"Build a real-time collaboration platform with WebSocket"`
+- File reference: `@requirements.md`
+- Context import: `--from brainstorm:BRN-001` or `--from @requirements.md` or `--from path/`
+- Resume: `-c` (resumes from first incomplete phase)
+
+**Pipeline position:**
+```
+maestro-brainstorm (optional upstream)
+        ↓ guidance-specification.md / context-package.json
+maestro-blueprint
+        ↓ .workflow/blueprint/BLP-{slug}-{date}/
+maestro-analyze → maestro-roadmap → maestro-plan
+```
+
+**Output boundary**: ALL file writes MUST target `.workflow/blueprint/BLP-{slug}-{date}/` or `.workflow/state.json` only. NEVER modify source code or files outside these paths.
+
+### Pre-load specs
+1. **Architecture specs**: Run `maestro spec load --category arch` to load architecture constraints. Use as context for architecture decisions (Phase 4).
+2. Optional — proceed without if unavailable.
+</context>
+
+<interview_protocol>
+Interview the user relentlessly about every aspect of the spec until shared understanding is reached. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one; if a question can be answered by exploring the codebase, explore the codebase instead. Active only in interactive mode; skip when `-y/--yes`, `-c/--continue`, or input is already specific (clear idea + scope).
+
+- Ask one question per turn via ask_user and wait for the user's feedback before continuing; every question must carry a recommended answer marked `(Recommended)`, 2–4 options total, and a `Proceed now` option.
+- Never ask what code can verify — resolve via `state.json`, existing artifacts, `maestro spec load`, or direct codebase exploration (Glob/Grep/Read) instead of prompting.
+- Walk the decision dependency tree depth-first: scope → spec type → focus areas → requirement priorities. Do not open the next branch until the current one is settled.
+- Scope guard: only decide the shape of the specification. Do not pre-resolve roadmap phases or plan tasks — those belong to downstream commands.
+
+Decision points: scope (full product / feature set / single feature) → spec type (service / api / library / platform) → focus areas → whether to run codebase exploration.
+
+Exit: on consensus or `Proceed now`, persist decisions in blueprint-config.json and proceed to Phase 1.
+</interview_protocol>
+
+<execution>
+Follow `~/.maestro/workflows/blueprint.md` completely.
+
+### Phase chain
+
+```
+P0: Spec Study → P1: Discovery → P1.5: Req Expansion → P2: Product Brief → P3: PRD → P4: Architecture → P5: Epics → P6: Readiness Check
+```
+
+P6 gate: Pass (>=80%) → Handoff | Review (60-79%) → Handoff w/caveats | Fail (<60%) → P6.5 Auto-Fix (max 2 iter) → re-check
+
+### Next-step routing on completion
+
+| Condition | Suggestion |
+|-----------|-----------|
+| Need codebase analysis | /maestro-analyze {topic} --from blueprint:BLP-xxx |
+| Ready for roadmap | /maestro-roadmap --from blueprint:BLP-xxx |
+| Small scope, direct plan | /maestro-plan --from blueprint:BLP-xxx |
+| Need project setup | /maestro-init |
+</execution>
+
+<error_codes>
+| Code | Severity | Condition | Recovery |
+|------|----------|-----------|----------|
+| E001 | error | Idea text or @file required | Prompt user for input |
+| E002 | error | Context source not found (--from) | Show available sessions/sources |
+| E006 | error | `.workflow/` not initialized | Run maestro-init first |
+| E007 | error | Phase 6 readiness Fail after 2 auto-fix iterations | Present manual fix options |
+| W001 | warning | CLI analysis failed, using fallback | Continue with available data |
+| W002 | warning | Codebase exploration failed | Continue without codebase context |
+| W003 | warning | Glossary has < 5 terms | Note in readiness check |
+| W004 | warning | Review-level readiness score (60-79%) | Proceed with caveats |
+| W005 | warning | External research agent failed | Continue without apiResearchContext |
+</error_codes>
+
+<success_criteria>
+- [ ] Interactive mode: interview decisions persisted in blueprint-config.json
+- [ ] `blueprint-config.json` created with session metadata and phase tracking
+- [ ] `product-brief.md` with vision, goals, scope, multi-perspective synthesis
+- [ ] `glossary.json` with 5+ core terms for cross-document consistency
+- [ ] `requirements/` directory with `_index.md` + individual `REQ-*.md` + `NFR-*.md` files
+- [ ] All requirements have RFC 2119 keywords and acceptance criteria
+- [ ] `architecture/` directory with `_index.md` + individual `ADR-*.md` files
+- [ ] Architecture includes state machine, config model, error handling, observability (service type)
+- [ ] `epics/` directory with `_index.md` + individual `EPIC-*.md` files
+- [ ] Cross-Epic dependency map (Mermaid) and MVP subset tagged
+- [ ] `readiness-report.md` with 4-dimension quality scores and traceability matrix
+- [ ] `blueprint-summary.md` with one-page executive summary
+- [ ] All documents have valid YAML frontmatter with session_id
+- [ ] Glossary terms used consistently across all documents
+- [ ] Readiness gate: Pass (>=80%) or Review (>=60%) with documented caveats
+- [ ] Artifact registered in state.json (type=blueprint)
+- [ ] context-package.json generated for downstream consumption
+</success_criteria>

package/.agents/skills/maestro-brainstorm/SKILL.md

@@ -0,0 +1,134 @@
+---
+name: maestro-brainstorm
+description: Use when exploring ideas, evaluating approaches, or needing multi-perspective analysis before implementation
+argument-hint: "[topic|role-name] [--yes] [--count N] [--session ID] [--update] [--skip-questions] [--include-questions] [--style-skill PKG]"
+allowed-tools:
+  - read_file
+  - write_file
+  - shell
+  - find_files
+  - search
+  - delegate_subagent
+  - ask_user
+---
+<!-- Open-standard mirror generated by scripts/build-agents-standard.mjs — do not edit; re-run after editing .claude/ source. -->
+
+<purpose>
+Unified brainstorming combining interactive framework generation, multi-role parallel analysis, cross-role review, and resolution writeback. Two modes: Auto (full pipeline: guidance-specification → parallel {role}/ multi-file analysis → cross-role-reviewer compares Decision Digests for conflicts/gaps/synergies → user-confirmed resolutions patched into role files + logged in guidance §12) and Single Role (individual role analysis for an existing session). Outputs structured artifacts in `.workflow/scratch/brainstorm-{slug}-{date}/` ready for downstream planning (roadmap / analyze / blueprint consume `guidance-specification.md`).
+</purpose>
+
+<required_reading>
+@~/.maestro/workflows/brainstorm.md
+</required_reading>
+
+<deferred_reading>
+- [scratch-index.json](~/.maestro/templates/scratch-index.json) — read when operating in scratch mode
+- [index.json](~/.maestro/templates/index.json) — read when operating in phase mode
+- [brainstorm-visualize.md](~/.maestro/workflows/brainstorm-visualize.md) — read when html-prototypes/ produced and user wants to browse them
+</deferred_reading>
+
+<context>
+$ARGUMENTS -- topic text for auto mode, or role name for single role mode.
+
+**Auto mode**: topic text (e.g., "Build real-time collaboration platform") triggers full pipeline.
+**Single role mode**: valid role name (e.g., "system-architect") runs one role analysis.
+**All output** goes to `.workflow/scratch/{YYYYMMDD}-brainstorm-{slug}/`.
+**Artifact registration**: On completion, registers artifact (type=brainstorm) in state.json.
+**Output boundary**: ALL file writes MUST target `{output_dir}/` or `.workflow/state.json` only. NEVER modify source code or files outside these paths.
+**Produced files**: `guidance-specification.md`, `design-research.md` (optional), `{role}/analysis.md` + `{role}/analysis-F-*.md` + `{role}/findings-*.md` (per selected role).
+
+**Valid roles**: data-architect, product-manager, product-owner, scrum-master, subject-matter-expert, system-architect, test-strategist, ui-designer, ux-expert
+
+**Flags**:
+- `--yes` / `-y`: Auto mode, skip interactive questions, use defaults
+- `--count N`: Number of roles to select (default 3, max 9)
+- `--session ID`: Use existing session
+- `--update`: Update existing analysis (single role)
+- `--skip-questions`: Skip context gathering questions
+- `--include-questions`: Force context gathering even if analysis exists
+- `--style-skill PKG`: Style package for ui-designer role
+
+### Pre-load specs
+1. **Architecture specs**: Run `maestro spec load --category arch` to load architecture constraints. Use as context for multi-role analysis — ensures roles respect documented decisions.
+2. Optional — proceed without if unavailable.
+
+### Role Knowledge
+1. Browse accumulated knowledge for this role:
+   `maestro wiki list --category arch`
+2. Analyze the index, identify entries relevant to the current task
+3. Load selected documents:
+   `maestro wiki load <id1> [id2] [id3...]`
+4. Review loaded knowledge before proceeding
+</context>
+
+<interview_protocol>
+Interview the user relentlessly until shared understanding is reached. Active only in interactive mode; skip when `--yes/-y`, `--skip-questions`, `--session` (existing session), or input is already specific.
+
+- One decision per turn via ask_user with 2–4 options + a (Recommended) default; every question must include a `Proceed now` option.
+- Never ask what code can verify — resolve via `state.json`, the session directory, `maestro spec load`, or `maestro wiki search`.
+- Branch jumps allowed: the user may switch freely between mode / role / upstream / sub-pipeline branches; sequence is not enforced, but every decision point must end with a definite answer.
+- Scope guard: only ask about decisions owned by `brainstorm`. Do not pre-resolve roadmap/plan choices.
+
+Decision points: mode (auto / single-role / review-only) / role selection and `--count` / `--from` upstream source / whether to enable design-research and the DESIGN.md sub-pipeline.
+
+Exit: on consensus or `Proceed now`, write the table below into `guidance-specification.md` §11 and session metadata:
+`| # | Decision | Choice | Source (user / code / default) |`
+</interview_protocol>
+
+<execution>
+Follow '~/.maestro/workflows/brainstorm.md' completely.
+
+**Next-step routing on completion:**
+
+Auto mode:
+- Project not initialized → invoke_skill({ skill: "maestro-init" })
+- Project initialized, need formal spec package → invoke_skill({ skill: "maestro-blueprint", args: "--from brainstorm:{artifact_id}" })
+- Project initialized, quick roadmap → invoke_skill({ skill: "maestro-roadmap", args: "--from brainstorm:{artifact_id}" })
+- Need deeper analysis first → invoke_skill({ skill: "maestro-analyze", args: "{topic} --from brainstorm:{artifact_id}" })
+- `html-prototypes/` produced with 2+ files and user wants to browse → load `~/.maestro/workflows/brainstorm-visualize.md` and launch visualizer server (optional, user-triggered)
+- DESIGN.md established during Step 3.5 → suggest: "Run `/maestro-impeccable build <feature-description>` to build with the established design system"
+
+Single role mode:
+- More roles needed → invoke_skill({ skill: "maestro-brainstorm", args: "{next_role} --session {session_id}" })
+- All roles done, run synthesis → invoke_skill({ skill: "maestro-brainstorm", args: "{topic} --session {session_id}" })
+</execution>
+
+<error_codes>
+| Code | Severity | Condition | Recovery |
+|------|----------|-----------|----------|
+| E001 | error | Topic or role argument required | Prompt user for topic text or role name |
+| E002 | error | No active session for single role mode | Guide user to run auto mode first |
+| E003 | error | Invalid role name | Show valid roles list |
+| E006 | error | `--review-only` but no `{role}/analysis.md` found | Run auto or single-role mode first |
+| E007 | error | `--review-only` but `guidance-specification.md` missing | Run auto mode to generate guidance first |
+| W001 | warning | Fewer than 10 ideas in divergent phase | Proceed with available ideas |
+| W002 | warning | Project context (.workflow/) not found | Continue without project context |
+| W003 | warning | Role template not found | Use generic analysis structure |
+| W004 | warning | Validation score < 60 | Log warning, suggest manual review |
+| W005 | warning | External research agent failed | Continue without designResearchContext |
+| W006 | warning | Reviewer patch_targets heading drift (no match) | Skip that patch; report in final summary |
+</error_codes>
+
+<success_criteria>
+**Auto mode**:
+- [ ] Interactive mode: interview decision table written to `guidance-specification.md` §11 and session metadata
+- [ ] `guidance-specification.md` with RFC 2119 keywords, terminology, non-goals, feature decomposition (§10), decision tracking (§11), cross-role resolutions placeholder (§12)
+- [ ] `design-research.md` persisted when Step 1.7 external research ran (fail-soft: absence not a failure)
+- [ ] If `ui-designer` in selected_roles AND Step 3.5 ran: `.workflow/impeccable/DESIGN.md` exists (visual style established via impeccable explore)
+- [ ] `{role}/analysis.md` written for each selected role, containing §2 Decision Digest (4 tables) + §3 Cross-Cutting Foundations + §4 File Index
+- [ ] `{role}/analysis-F-{id}-{slug}.md` written per feature (one file per feature, < 2000 words)
+- [ ] `system-architect/analysis.md` §3 includes Data Model + State Machine when system-architect is selected
+- [ ] `ui-designer/analysis.md` references DESIGN.md visual constraints when ui-designer is selected
+- [ ] Each `{role}/analysis.md` §2 Decisions table has ≥ 1 row per feature
+- [ ] Cross-role review (Step 4.5) executed; reviewer compares §2 Decision Digests; output includes `patch_targets[]` for every finding
+- [ ] If findings exist: each accepted resolution applied via edit_file(annotate / strikeout / append) AND logged in `guidance-specification.md` §12 "Cross-Role Resolutions"
+- [ ] If zero findings: final report explicitly states "No cross-role issues detected"; guidance §12 unchanged
+- [ ] Heading-drift patch failures surfaced in final report (if any)
+- [ ] Session metadata updated with completion status (review_findings_count, resolutions_applied, patches_skipped)
+
+**Single role mode**:
+- [ ] `{role}/analysis.md` written with §2 Decision Digest + §4 File Index
+- [ ] `{role}/analysis-F-*.md` written when guidance §10 feature list available
+- [ ] §2 Decisions table references guidance decision IDs
+- [ ] Session metadata updated
+</success_criteria>

package/.agents/skills/maestro-collab/SKILL.md

@@ -0,0 +1,174 @@
+---
+name: maestro-collab
+description: Use when a question needs cross-verification from multiple CLI tools or diverse analytical perspectives
+argument-hint: "<requirement> [--tools gemini,qwen,claude] [--mode analysis|write] [--rule <template>] [-y]"
+allowed-tools:
+  - read_file
+  - write_file
+  - shell
+  - find_files
+  - search
+  - delegate_subagent
+  - ask_user
+---
+<!-- Open-standard mirror generated by scripts/build-agents-standard.mjs — do not edit; re-run after editing .claude/ source. -->
+
+
+<purpose>
+Fan-out requirement to multiple CLI tools in parallel → cross-verify for consensus/conflicts → synthesize into unified report with downstream artifacts (context.md + conclusions.json).
+</purpose>
+
+<context>
+$ARGUMENTS — requirement text and optional flags.
+
+**Flags**:
+- `--tools <list>`: Comma-separated CLI tools (default: first 3 enabled)
+- `--mode analysis|write`: Delegate mode (default: analysis)
+- `--rule <template>`: Shared rule template for all delegates
+- `-y`: Skip plan confirmation
+
+**Pre-load** (optional): `maestro spec load --category arch` + `maestro wiki list --category arch` → include in delegate prompts.
+
+**Output**: `.workflow/scratch/{YYYYMMDD}-collab-{slug}/`
+- `collab-report.md` — merged findings with consensus/conflict/unique tags
+- `context.md` — Locked/Free/Deferred decisions (plan compatible)
+- `conclusions.json` — structured: session_id, tools[], consensus_level, recommendation, confidence, dimensions[], decisions[]
+- `per-tool/{tool}-output.md` — raw outputs
+</context>
+
+<state_machine>
+
+<states>
+S_PARSE           — 解析参数、提取 flags                      PERSIST: —
+S_DISCOVER        — 发现可用 CLI 工具                          PERSIST: —
+S_CONFIRM         — 展示计划、用户确认（-y 跳过）              PERSIST: —
+S_FANOUT          — 构建 prompt、并行启动 delegate、STOP       PERSIST: —
+S_COLLECT         — 回调到达、收集结果                          PERSIST: per-tool outputs
+S_CROSS_VERIFY    — 分类发现（共识/冲突/独有）                  PERSIST: —
+S_SYNTHESIZE      — 解决冲突、生成 3 个输出文件                 PERSIST: outputs
+S_REGISTER        — 注册 CLB artifact                          PERSIST: state.json
+S_REPORT          — 显示摘要 + next-step routing               PERSIST: —
+</states>
+
+<transitions>
+
+S_PARSE:
+  → S_DISCOVER    WHEN: requirement non-empty              DO: extract requirement, tools, mode, rule, autoYes
+  → S_PARSE       WHEN: requirement empty                  DO: ask_user for requirement
+
+S_DISCOVER:
+  → S_CONFIRM     WHEN: eligible tools >= 2                DO: A_DISCOVER_TOOLS
+  → ERROR(E002)   WHEN: eligible tools < 2
+
+S_CONFIRM:
+  → S_FANOUT      WHEN: autoYes                            DO: A_SETUP_SESSION
+  → S_FANOUT      WHEN: user confirms "执行"               DO: A_SETUP_SESSION
+  → S_DISCOVER    WHEN: user selects "修改工具选择"         DO: re-select tools, validate >= 2
+  → END           WHEN: user cancels
+
+S_FANOUT:
+  → S_COLLECT     DO: A_PARALLEL_DELEGATE then STOP — wait for callbacks
+
+S_COLLECT:
+  → S_CROSS_VERIFY  WHEN: all callbacks arrived            DO: A_COLLECT_OUTPUTS
+  → ERROR(E004)     WHEN: all delegates failed
+  GUARD: 1+ succeeded → continue with partial results (W001)
+
+S_CROSS_VERIFY:
+  → S_SYNTHESIZE    DO: A_CLASSIFY_FINDINGS
+
+S_SYNTHESIZE:
+  → S_REGISTER      DO: A_GENERATE_OUTPUTS
+
+S_REGISTER:
+  → S_REPORT        DO: append CLB artifact to state.json (type: collab, scope: adhoc)
+
+S_REPORT:
+  → END             DO: display summary (requirement, tools, consensus_level, per-tool status, artifact id, output dir)
+
+</transitions>
+
+<actions>
+
+### A_DISCOVER_TOOLS
+
+```
+shell("maestro tools list --json 2>/dev/null || cat ~/.maestro/cli-tools.json")
+```
+Filter: enabled == true. If --mode write: exclude type == "api-endpoint".
+Auto-select (no --tools): first 3 eligible in config order.
+
+### A_SETUP_SESSION
+
+Create: `.workflow/scratch/{YYYYMMDD}-collab-{slug}/` + `per-tool/`.
+
+### A_PARALLEL_DELEGATE
+
+1. Build shared prompt:
+   ```
+   PURPOSE: {requirement}; success = actionable findings with evidence
+   TASK: {auto-decomposed into 3-5 specific verbs}
+   MODE: {delegateMode}
+   CONTEXT: @**/*
+   EXPECTED: Structured findings with file:line refs, confidence (0-100), prioritized recommendations
+   CONSTRAINTS: {from requirement}
+   ```
+2. Launch ALL delegates in ONE message — multiple `shell(run_in_background: true)`:
+   ```
+   maestro delegate "${prompt}" --to {tool} --mode ${mode} [--rule ${rule}]
+   ```
+3. **STOP immediately after launch. Wait for background callbacks.**
+
+### A_COLLECT_OUTPUTS
+
+On each callback: `maestro delegate output <id>` → write `per-tool/{tool}-output.md`.
+
+### A_CLASSIFY_FINDINGS
+
+Read all per-tool outputs. For each finding:
+
+| Condition | Tag |
+|-----------|-----|
+| 2+ tools agree | CONSENSUS |
+| Tools disagree | CONFLICT |
+| 1 tool only | UNIQUE |
+
+consensus_level = consensus_count / total_findings * 100.
+If consensus_level < 40%: W003.
+
+### A_GENERATE_OUTPUTS
+
+Resolve conflicts via evidence-weighted voting:
+- Higher confidence wins; more specific evidence (file:line) wins over general; tied → SUGGESTED
+
+Write 3 files:
+1. **collab-report.md**: Summary, Consensus Findings, Resolved Conflicts, Unresolved Items, Unique Insights, Recommendations, Per-Tool Confidence table
+2. **context.md**: Locked (CONSENSUS items), Free (UNIQUE with strong evidence), Deferred (UNRESOLVED conflicts). Standard Locked/Free/Deferred format for plan compatibility.
+3. **conclusions.json**: session_id, subject, mode, tools[], consensus_level, recommendation (Go/No-Go/Conditional), confidence, dimensions[{name, score, findings}], decisions[{title, classification, source_tools, rationale}]
+
+</actions>
+
+</state_machine>
+
+<error_codes>
+| Code | Condition | Recovery |
+|------|-----------|----------|
+| E002 | Fewer than 2 eligible tools | Check cli-tools.json, enable more tools |
+| E004 | All delegates failed | Abort with per-tool error details |
+| W001 | One tool failed | Continue with remaining (partial degradation) |
+| W003 | consensus_level < 40% | Flag in summary, recommend manual review |
+</error_codes>
+
+<success_criteria>
+- [ ] All delegates launched in parallel via shell(run_in_background: true), STOP after launch
+- [ ] Cross-verification: consensus/conflict/unique classification with consensus_level
+- [ ] 3 output files produced (collab-report.md, context.md, conclusions.json)
+- [ ] CLB artifact registered in state.json
+- [ ] Partial degradation: continued if 1+ tools succeeded
+</success_criteria>
+
+<next_step_routing>
+- Deep feasibility → `/maestro-analyze "{topic}"`
+- Plan from conclusions → `/maestro-plan --dir {dir}`
+- Expand → `/maestro-brainstorm "{topic}"`
+</next_step_routing>

package/.agents/skills/maestro-composer/SKILL.md

@@ -0,0 +1,181 @@
+---
+name: maestro-composer
+description: Compose reusable workflow templates from natural language
+argument-hint: "<workflow-description> [--resume] [--edit <template-path>]"
+allowed-tools:
+  - read_file
+  - write_file
+  - edit_file
+  - shell
+  - find_files
+  - search
+  - delegate_subagent
+  - ask_user
+  - invoke_skill
+---
+<!-- Open-standard mirror generated by scripts/build-agents-standard.mjs — do not edit; re-run after editing .claude/ source. -->
+
+<purpose>
+Interactive workflow template composer. Parse natural language → resolve executors → inject checkpoints → build DAG → persist to `~/.maestro/templates/workflows/`. Progressive disclosure — specs loaded only when phase needs them.
+
+Three entry modes: **New design** (default), **Resume** (`--resume`), **Edit** (`--edit <path>`).
+</purpose>
+
+<deferred_reading>
+- [node-catalog](~/.maestro/templates/workflows/specs/node-catalog.md) — read at Phase 2 (Resolve)
+- [template-schema](~/.maestro/templates/workflows/specs/template-schema.md) — read at Phase 5 (Persist)
+</deferred_reading>
+
+<context>
+$ARGUMENTS — natural language description, or flags.
+
+**Flags**: `--resume` (resume in-progress design), `--edit <path>` (edit existing template)
+
+**Constants**:
+- Template dir: `~/.maestro/templates/workflows/`
+- Template index: `~/.maestro/templates/workflows/index.json`
+- Design drafts: `.workflow/templates/design-drafts/`
+- Template ID: `wft-<slug>-<YYYYMMDD>`, Node ID: `N-<seq>`, Checkpoint: `CP-<seq>`
+- Max nodes: 20
+
+### Pre-load specs
+1. **Architecture specs**: Run `maestro spec load --category arch` to load architecture constraints. Use as context for node resolution — ensures workflow design respects documented patterns.
+2. **Coding specs**: Run `maestro spec load --category coding` to load coding conventions. Informs executor argument defaults and context injection.
+3. Optional — proceed without if unavailable.
+</context>
+
+<state_machine>
+
+<states>
+S_ROUTE        — 入口路由（new/resume/edit）               PERSIST: —
+S_PARSE        — 语义意图提取                               PERSIST: intent.json
+S_CONFIRM_1    — 确认解析结果                               PERSIST: —
+S_RESOLVE      — 映射步骤到 executor 节点                   PERSIST: nodes.json
+S_CONFIRM_2    — 确认节点映射                               PERSIST: —
+S_ENRICH       — 注入 checkpoint + 构建 DAG                 PERSIST: dag.json
+S_CONFIRM_3    — 可视化 pipeline + 用户审批                  PERSIST: —
+S_PERSIST      — 组装 JSON + 保存模板                       PERSIST: template file + index
+</states>
+
+<transitions>
+
+S_ROUTE:
+  → S_PARSE       WHEN: no flags (new design)
+  → S_RESOLVE     WHEN: --resume                           DO: load draft, skip to last incomplete phase
+  → S_CONFIRM_3   WHEN: --edit <path>                      DO: load template, show pipeline, ask edits
+
+S_PARSE:
+  → S_CONFIRM_1   DO: A_PARSE_INTENT
+
+S_CONFIRM_1:
+  → S_RESOLVE     WHEN: user confirms "Looks good"
+  → S_PARSE       WHEN: user selects "Edit steps" or "Add step"
+  → END           WHEN: user cancels                       DO: save draft
+
+S_RESOLVE:
+  → S_CONFIRM_2   DO: A_RESOLVE_NODES (read deferred: node-catalog)
+
+S_CONFIRM_2:
+  → S_ENRICH      WHEN: user confirms "Continue"
+  → S_RESOLVE     WHEN: user changes executor or node type
+  → S_PARSE       WHEN: user selects "Back to intent"
+  → END           WHEN: user cancels                       DO: save draft
+
+S_ENRICH:
+  → S_CONFIRM_3   DO: A_BUILD_DAG
+
+S_CONFIRM_3:
+  → S_PERSIST     WHEN: user confirms "Confirm & Save"
+  → S_CONFIRM_3   WHEN: user edits/adds/removes node       DO: apply change, re-render
+  → S_ENRICH      WHEN: user selects "Re-run checkpoints"
+  → END           WHEN: user cancels                       DO: save draft
+
+S_PERSIST:
+  → END           DO: A_SAVE_TEMPLATE (read deferred: template-schema)
+
+</transitions>
+
+<actions>
+
+### A_PARSE_INTENT
+
+1. Parse description (if empty: ask_user for workflow description)
+2. Extract candidate nodes via semantic signals:
+
+| Signal | Type hint |
+|--------|-----------|
+| "analyze", "review", "explore" | analysis (cli) |
+| "plan", "design", "spec" | planning (skill) |
+| "implement", "build", "code", "fix" | execution (skill) |
+| "test", "validate", "verify" | testing (skill) |
+| "then", "next", "after" | sequential edge |
+| "parallel", "simultaneously" | parallel edge |
+
+3. Extract variables (inputs that vary per run)
+4. Classify: task type + complexity (simple 1-3 / medium 4-7 / complex 8+)
+5. Write `intent.json` to design drafts dir
+6. Display: parsed steps, variables, task type, complexity
+
+### A_RESOLVE_NODES
+
+Read deferred `node-catalog.md` (fallback to built-in mapping):
+
+| Type hint | Default executor |
+|-----------|-----------------|
+| planning | `maestro-plan` |
+| execution | `maestro-execute` |
+| testing | `quality-test` |
+| review | `quality-review` |
+| brainstorm | `maestro-brainstorm` |
+| analysis | `maestro delegate --role analyze` |
+| verify | `maestro-verify` |
+| refactor | `quality-refactor` |
+| debug | `quality-debug` |
+
+Build `args_template` with variable placeholders. Context injection: planning-after-analysis → `--context {prev_output_path}`, execution-after-planning → `--resume-session {prev_session_id}`.
+Write `nodes.json`. Display resolved node list.
+
+### A_BUILD_DAG
+
+1. Build sequential edges (fan-out/fan-in for parallel groups)
+2. Auto-inject checkpoints:
+
+| Rule | Condition |
+|------|-----------|
+| Artifact boundary | Source outputs plan/spec/analysis/review |
+| Execution gate | Target contains `execute` |
+| Long-running | Target is maestro-plan, maestro-roadmap --mode full |
+| Post-testing | Source contains `test` or `auto-test` |
+| User-defined | type_hint == checkpoint |
+
+3. Finalize context_schema from {variable} references
+4. Validate: no cycles, no orphans, all reachable
+5. Write `dag.json`
+6. Display ASCII pipeline visualization
+
+### A_SAVE_TEMPLATE
+
+Read deferred `template-schema.md` (fallback to built-in structure).
+Assemble template JSON: template_id, name, nodes, edges, checkpoints, context_schema, execution_mode.
+Write to `~/.maestro/templates/workflows/<slug>.json`. Update index.json.
+Display: path, ID, node count, variables, execute/edit commands. Clean up draft dir.
+
+</actions>
+
+</state_machine>
+
+<error_codes>
+| Code | Condition | Recovery |
+|------|-----------|----------|
+| E002 | 0 steps extracted | Ask user to rephrase with action verbs |
+| E003 | Node count > 20 | Suggest splitting into sub-workflows |
+| E005 | DAG cycle detected | Show cycle, ask user to resolve |
+| E006 | Edit template not found (--edit) | Show available templates |
+| W001 | Ambiguous step→executor mapping | Show candidates, let user choose |
+</error_codes>
+
+<success_criteria>
+- [ ] Each phase has interactive confirmation gate
+- [ ] Template JSON written with nodes, edges, checkpoints, context_schema
+- [ ] Index updated; deferred specs loaded only when phase needs them
+</success_criteria>