maestro-flow 0.5.35 → 0.5.37

package/.agy/skills/maestro-grill/SKILL.md

@@ -14,164 +14,164 @@ allowed-tools:
   - view_file
   - write_to_file
 ---
-<purpose>
-Socratic stress-testing of plans/ideas against codebase reality. Produces grill-report.md + terminology.md + context-package.json for downstream brainstorm/analyze/roadmap.
-
-Pipeline position: BEFORE brainstorm (stress-test → then elaborate).
-</purpose>
-
-<required_reading>
-@~/.maestro/workflows/grill.md
-</required_reading>
-
-<deferred_reading>
-- [state.json](~/.maestro/templates/state.json) — read when registering artifact
-</deferred_reading>
-
-<context>
-$ARGUMENTS -- topic/plan text for interactive mode, or --from source for upstream input.
-
-**Mode selection:**
-- **Interactive mode** (default): Topic text triggers full Socratic grilling with user Q&A
-- **Auto mode** (`-y`): Code exploration answers questions instead of the user
-- **Resume mode** (`-c` or `--session ID`): Continue from a previous grill session
-
-**Flags:**
-
-| Flag | Effect | Default |
-|------|--------|---------|
-| `-y` / `--yes` | Auto mode — CLI exploration replaces human answers | `false` |
-| `-c` / `--continue` | Resume from last grill session | — |
-| `--session ID` | Resume specific session | — |
-| `--depth shallow\|standard\|deep` | Branch count 3/5/8 | `standard` |
-| `--from <source>` | Load upstream material (`blueprint:ID`, `@file`, or path) | — |
-
-**Output directory**: `.workflow/scratch/{YYYYMMDD}-grill-{slug}/`
-**Produced files**: `grill-report.md`, `terminology.md`, `context-package.json`
-
-### Pre-load
-
-1. **Specs**: `maestro spec load --category arch` — load architecture constraints
-2. **Wiki search**: `maestro search "{topic keywords}"` → load relevant entries before grilling
-3. All optional — proceed without if unavailable
-</context>
-
-<interview_protocol>
-Follows @~/.maestro/workflows/interview-mechanics.md standard.
-
-**Interaction mode override**: adversarial Socratic — NOT menu-driven
-**Question style**:
-  - Reference specific code: "The codebase uses `{symbol}` at `{file:line}` — your proposal calls it `{term}`. Which wins?"
-  - Concrete scenarios: "What happens when {action} while {condition}?"
-  - Challenge contradictions: immediately surface conflicts with code evidence or prior answers
-  - Escalating depth: per branch basic → specific → adversarial
-**Branch traversal** (depth-gated, --depth controls count): Scope & Boundaries → Data Model & State → Edge Cases & Failure Modes → Integration & Dependencies → Scale & Performance → Security & Access Control → Observability & Operations → Migration & Rollback
-**Writeback target**: grill-report.md (Q&A append per question) + terminology.md (term crystallization)
-**Additional skip conditions**: none beyond standard (-y, -c)
-**Exit condition**: all depth-selected branches fully walked → finalize report + context-package.json
-</interview_protocol>
-
-<execution>
-Follow '~/.maestro/workflows/grill.md' completely.
-
-### Phase Gates (MANDATORY, BLOCKING)
-
-**GATE 1: Setup → Branch Walking** (Step 1 → Step 2)
-- REQUIRED: Topic parsed and output directory created.
-- REQUIRED: Initial codebase scan completed — at least one code reference identified for grounding.
-- BLOCKED if missing: cannot grill without code reality baseline.
-
-**GATE 2: Branch Walking → Synthesis** (Step 2 → Step 3)
-- REQUIRED: All depth-selected branches walked (shallow=3, standard=5, deep=8).
-- REQUIRED: Each branch has ≥2 Q&A pairs with evidence (code reference or explicit user input).
-- REQUIRED: Every locked decision has evidence — NOT just orchestrator inference.
-- BLOCKED if branches incomplete: continue walking before synthesizing.
-
-**GATE 3: Synthesis → Completion** (Step 3 → Report)
-- REQUIRED: `grill-report.md` written with Branch Log table + all Q&A entries + synthesis section.
-- REQUIRED: `terminology.md` written with ≥5 terms.
-- REQUIRED: `context-package.json` generated.
-- BLOCKED if any artifact missing: produce it before reporting completion.
-
-### Evidence Requirement
-
-Grill questions MUST reference specific code (`file:line`) when challenging the user's proposal. Generic questions without code grounding are INVALID.
-
-If codebase scan failed (W001): flag ALL subsequent locked decisions as LOW CONFIDENCE.
-
-### Artifact Verification (before completion)
-
-```
-REQUIRED_ARTIFACTS = [
-  "grill-report.md",        // Branch Log + Q&A + synthesis
-  "terminology.md",         // ≥5 terms with code refs
-  "context-package.json"    // Schema "context-package/1.0"
-]
-```
-If any missing: DO NOT report completion. Go back and produce the missing artifact.
-</execution>
-
-<completion>
-### Standalone report
-
-```
-=== GRILL READY ===
-Topic: {topic}
-Branches walked: {count}/{depth_target}
-Decisions locked: {locked_count}
-Open risks: {risk_count}
-Output: {output_dir}
-Artifact: GRL-{id}
-=== END GRILL ===
-```
-
-### Ralph-invoked completion
-
-End the step by calling the CLI (no text block output):
-```
-maestro ralph complete <idx> --status {STATUS} [--evidence {path}]
-```
-
-Status verdicts:
-- **DONE** — Normal completion
-- **DONE_WITH_CONCERNS** — Completed with caveats; pass `--concerns`
-- **NEEDS_RETRY** — Tooling error / transient issue; ralph will retry
-- **BLOCKED** — External hard blocker; pass `--reason`
-
-### Next-step routing
-
-| Condition | Suggestion |
-|-----------|-----------|
-| Need multi-role elaboration | `view_file(AbsolutePath="<agy-skills-dir>/maestro-brainstorm/SKILL.md") + execute inline (args: "{topic} --from grill:{artifact_id}")` |
-| Need deep technical analysis | `view_file(AbsolutePath="<agy-skills-dir>/maestro-analyze/SKILL.md") + execute inline (args: "{topic} --from grill:{artifact_id}")` |
-| Scope is clear, ready for roadmap | `view_file(AbsolutePath="<agy-skills-dir>/maestro-roadmap/SKILL.md") + execute inline (args: "--from grill:{artifact_id}")` |
-| Need formal spec package | `view_file(AbsolutePath="<agy-skills-dir>/maestro-blueprint/SKILL.md") + execute inline (args: "--from grill:{artifact_id}")` |
-| More branches to walk | `view_file(AbsolutePath="<agy-skills-dir>/maestro-grill/SKILL.md") + execute inline (args: "{topic} -c")` |
-</completion>
-
-<error_codes>
-| Code | Severity | Condition | Recovery |
-|------|----------|-----------|----------|
-| E001 | error | No topic/plan and no --from/--continue flag | Prompt user for topic text |
-| E002 | error | --session ID not found | Show available sessions |
-| W001 | warning | Codebase scan failed or returned empty | Continue without code grounding, note limitation |
-| W002 | warning | CLI exploration timeout in auto mode | Skip question, mark as open |
-| W003 | warning | Max branch depth reached without resolution | Force synthesis, offer continuation |
-</error_codes>
-
-<success_criteria>
-- [ ] Interactive mode: all depth-selected branches walked (shallow=3, standard=5, deep=8)
-- [ ] Each branch has >= 2 question-answer pairs with evidence or explicit user input
-- [ ] `grill-report.md` written with Branch Log table, all Q&A entries, synthesis section
-- [ ] `terminology.md` written with >= 5 terms, code references where applicable
-- [ ] Every locked decision has evidence (code reference or explicit user confirmation)
-- [ ] Contradictions between answers and code surfaced and resolved (or logged as risks)
-- [ ] Risk register captures all unresolved tensions
-- [ ] `context-package.json` generated with schema "context-package/1.0"
-- [ ] Artifact registered in state.json (type=grill, id=GRL-xxx)
-- [ ] Session sealed via finish-work
-</success_criteria>
-
-<on_complete>
-@~/.maestro/workflows/finish-work.md — SESSION_DIR={output_dir}, SESSION_TYPE=grill, SESSION_ID={artifact_id}, LINKED_MILESTONE=null
-</on_complete>
+<purpose>
+Socratic stress-testing of plans/ideas against codebase reality. Produces grill-report.md + terminology.md + context-package.json for downstream brainstorm/analyze/roadmap.
+
+Pipeline position: BEFORE brainstorm (stress-test → then elaborate).
+</purpose>
+
+<required_reading>
+@~/.maestro/workflows/grill.md
+</required_reading>
+
+<deferred_reading>
+- [state.json](~/.maestro/templates/state.json) — read when registering artifact
+</deferred_reading>
+
+<context>
+$ARGUMENTS -- topic/plan text for interactive mode, or --from source for upstream input.
+
+**Mode selection:**
+- **Interactive mode** (default): Topic text triggers full Socratic grilling with user Q&A
+- **Auto mode** (`-y`): Code exploration answers questions instead of the user
+- **Resume mode** (`-c` or `--session ID`): Continue from a previous grill session
+
+**Flags:**
+
+| Flag | Effect | Default |
+|------|--------|---------|
+| `-y` / `--yes` | Auto mode — CLI exploration replaces human answers | `false` |
+| `-c` / `--continue` | Resume from last grill session | — |
+| `--session ID` | Resume specific session | — |
+| `--depth shallow\|standard\|deep` | Branch count 3/5/8 | `standard` |
+| `--from <source>` | Load upstream material (`blueprint:ID`, `@file`, or path) | — |
+
+**Output directory**: `.workflow/scratch/{YYYYMMDD}-grill-{slug}/`
+**Produced files**: `grill-report.md`, `terminology.md`, `context-package.json`
+
+### Pre-load
+
+1. **Specs**: `maestro load --type spec --category arch` — load architecture constraints
+2. **Wiki search**: `maestro search "{topic keywords}"` → load relevant entries before grilling
+3. All optional — proceed without if unavailable
+</context>
+
+<interview_protocol>
+Follows @~/.maestro/workflows/interview-mechanics.md standard.
+
+**Interaction mode override**: adversarial Socratic — NOT menu-driven
+**Question style**:
+  - Reference specific code: "The codebase uses `{symbol}` at `{file:line}` — your proposal calls it `{term}`. Which wins?"
+  - Concrete scenarios: "What happens when {action} while {condition}?"
+  - Challenge contradictions: immediately surface conflicts with code evidence or prior answers
+  - Escalating depth: per branch basic → specific → adversarial
+**Branch traversal** (depth-gated, --depth controls count): Scope & Boundaries → Data Model & State → Edge Cases & Failure Modes → Integration & Dependencies → Scale & Performance → Security & Access Control → Observability & Operations → Migration & Rollback
+**Writeback target**: grill-report.md (Q&A append per question) + terminology.md (term crystallization)
+**Additional skip conditions**: none beyond standard (-y, -c)
+**Exit condition**: all depth-selected branches fully walked → finalize report + context-package.json
+</interview_protocol>
+
+<execution>
+Follow '~/.maestro/workflows/grill.md' completely.
+
+### Phase Gates (MANDATORY, BLOCKING)
+
+**GATE 1: Setup → Branch Walking** (Step 1 → Step 2)
+- REQUIRED: Topic parsed and output directory created.
+- REQUIRED: Initial codebase scan completed — at least one code reference identified for grounding.
+- BLOCKED if missing: cannot grill without code reality baseline.
+
+**GATE 2: Branch Walking → Synthesis** (Step 2 → Step 3)
+- REQUIRED: All depth-selected branches walked (shallow=3, standard=5, deep=8).
+- REQUIRED: Each branch has ≥2 Q&A pairs with evidence (code reference or explicit user input).
+- REQUIRED: Every locked decision has evidence — NOT just orchestrator inference.
+- BLOCKED if branches incomplete: continue walking before synthesizing.
+
+**GATE 3: Synthesis → Completion** (Step 3 → Report)
+- REQUIRED: `grill-report.md` written with Branch Log table + all Q&A entries + synthesis section.
+- REQUIRED: `terminology.md` written with ≥5 terms.
+- REQUIRED: `context-package.json` generated.
+- BLOCKED if any artifact missing: produce it before reporting completion.
+
+### Evidence Requirement
+
+Grill questions MUST reference specific code (`file:line`) when challenging the user's proposal. Generic questions without code grounding are INVALID.
+
+If codebase scan failed (W001): flag ALL subsequent locked decisions as LOW CONFIDENCE.
+
+### Artifact Verification (before completion)
+
+```
+REQUIRED_ARTIFACTS = [
+  "grill-report.md",        // Branch Log + Q&A + synthesis
+  "terminology.md",         // ≥5 terms with code refs
+  "context-package.json"    // Schema "context-package/1.0"
+]
+```
+If any missing: DO NOT report completion. Go back and produce the missing artifact.
+</execution>
+
+<completion>
+### Standalone report
+
+```
+=== GRILL READY ===
+Topic: {topic}
+Branches walked: {count}/{depth_target}
+Decisions locked: {locked_count}
+Open risks: {risk_count}
+Output: {output_dir}
+Artifact: GRL-{id}
+=== END GRILL ===
+```
+
+### Ralph-invoked completion
+
+End the step by calling the CLI (no text block output):
+```
+maestro ralph complete <idx> --status {STATUS} [--evidence {path}]
+```
+
+Status verdicts:
+- **DONE** — Normal completion
+- **DONE_WITH_CONCERNS** — Completed with caveats; pass `--concerns`
+- **NEEDS_RETRY** — Tooling error / transient issue; ralph will retry
+- **BLOCKED** — External hard blocker; pass `--reason`
+
+### Next-step routing
+
+| Condition | Suggestion |
+|-----------|-----------|
+| Need multi-role elaboration | `view_file(AbsolutePath="<agy-skills-dir>/maestro-brainstorm/SKILL.md") + execute inline (args: "{topic} --from grill:{artifact_id}")` |
+| Need deep technical analysis | `view_file(AbsolutePath="<agy-skills-dir>/maestro-analyze/SKILL.md") + execute inline (args: "{topic} --from grill:{artifact_id}")` |
+| Scope is clear, ready for roadmap | `view_file(AbsolutePath="<agy-skills-dir>/maestro-roadmap/SKILL.md") + execute inline (args: "--from grill:{artifact_id}")` |
+| Need formal spec package | `view_file(AbsolutePath="<agy-skills-dir>/maestro-blueprint/SKILL.md") + execute inline (args: "--from grill:{artifact_id}")` |
+| More branches to walk | `view_file(AbsolutePath="<agy-skills-dir>/maestro-grill/SKILL.md") + execute inline (args: "{topic} -c")` |
+</completion>
+
+<error_codes>
+| Code | Severity | Condition | Recovery |
+|------|----------|-----------|----------|
+| E001 | error | No topic/plan and no --from/--continue flag | Prompt user for topic text |
+| E002 | error | --session ID not found | Show available sessions |
+| W001 | warning | Codebase scan failed or returned empty | Continue without code grounding, note limitation |
+| W002 | warning | CLI exploration timeout in auto mode | Skip question, mark as open |
+| W003 | warning | Max branch depth reached without resolution | Force synthesis, offer continuation |
+</error_codes>
+
+<success_criteria>
+- [ ] Interactive mode: all depth-selected branches walked (shallow=3, standard=5, deep=8)
+- [ ] Each branch has >= 2 question-answer pairs with evidence or explicit user input
+- [ ] `grill-report.md` written with Branch Log table, all Q&A entries, synthesis section
+- [ ] `terminology.md` written with >= 5 terms, code references where applicable
+- [ ] Every locked decision has evidence (code reference or explicit user confirmation)
+- [ ] Contradictions between answers and code surfaced and resolved (or logged as risks)
+- [ ] Risk register captures all unresolved tensions
+- [ ] `context-package.json` generated with schema "context-package/1.0"
+- [ ] Artifact registered in state.json (type=grill, id=GRL-xxx)
+- [ ] Session sealed via finish-work
+</success_criteria>
+
+<on_complete>
+@~/.maestro/workflows/finish-work.md — SESSION_DIR={output_dir}, SESSION_TYPE=grill, SESSION_ID={artifact_id}, LINKED_MILESTONE=null
+</on_complete>

package/.agy/skills/maestro-guard/SKILL.md

@@ -8,96 +8,96 @@ allowed-tools:
   - view_file
   - write_to_file
 ---
-<purpose>
-Configure directory-level write boundaries enforced by the workflow-guard PreToolUse hook.
-Subcommands: on, off, status, allow `<path>`, deny `<path>`.
-</purpose>
-
-<context>
-$ARGUMENTS — Parse subcommand and optional path argument.
-
-**Config location:** `.workflow/config.json` → `guard` section
-
-```json
-{
-  "guard": {
-    "enabled": false,
-    "mode": "allow",
-    "paths": []
-  }
-}
-```
-
-**Enforcement:** The `workflow-guard` hook (PreToolUse on Write/Edit) reads this config
-and blocks operations targeting files outside boundaries. Requires hooks level >= `full`.
-</context>
-
-<execution>
-
-**Step 1: Parse subcommand**
-
-Extract from $ARGUMENTS:
-- `on` / `off` / `status` / `allow <path>` / `deny <path>`
-- If no subcommand, default to `status`
-
-**Step 2: Read config**
-
-Read `.workflow/config.json`. If file missing, initialize with empty guard section.
-
-**Step 3: Execute subcommand**
-
-**`status`:**
-- Display: enabled/disabled, mode (allow/deny), paths list
-- Check if workflow-guard hook is active (read `.claude/settings.json` for hook presence)
-- If guard enabled but hook not active, warn: "⚠ PathGuard enabled but workflow-guard hook not installed. Run `maestro hooks level full` to activate."
-
-**`on`:**
-- Set `guard.enabled = true`
-- If `guard.paths` is empty, set default: `["src/", "tests/", ".workflow/"]`
-- Check hook level, warn if < full
-- Write config
-
-**`off`:**
-- Set `guard.enabled = false`
-- Preserve existing paths and mode
-- Write config
-
-**`allow <path>`:**
-- Normalize path to forward slashes, ensure trailing slash for directories
-- If `guard.mode` is `deny`, switch to `allow` and clear paths with warning
-- 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`, switch to `deny` and clear paths with warning
-- 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)
-- Write config
-
-**Step 4: Confirm**
-
-Display updated guard configuration.
-
-</execution>
-
-<error_codes>
-- E001: `.workflow/config.json` not found and cannot be created (not a maestro project)
-- W001: PathGuard enabled but workflow-guard hook not installed
-</error_codes>
-
-<success_criteria>
-- [ ] Config read/written correctly
-- [ ] Hook level warning displayed when applicable
-- [ ] Updated configuration shown after changes
-</success_criteria>
-
-<completion>
-### Next-step routing
-| Condition | Suggestion |
-|-----------|-----------|
-| Guard enabled, hook not installed | `maestro hooks level full` |
-| Want to verify guard works | Edit a file outside allowed paths |
-</completion>
+<purpose>
+Configure directory-level write boundaries enforced by the workflow-guard PreToolUse hook.
+Subcommands: on, off, status, allow `<path>`, deny `<path>`.
+</purpose>
+
+<context>
+$ARGUMENTS — Parse subcommand and optional path argument.
+
+**Config location:** `.workflow/config.json` → `guard` section
+
+```json
+{
+  "guard": {
+    "enabled": false,
+    "mode": "allow",
+    "paths": []
+  }
+}
+```
+
+**Enforcement:** The `workflow-guard` hook (PreToolUse on Write/Edit) reads this config
+and blocks operations targeting files outside boundaries. Requires hooks level >= `full`.
+</context>
+
+<execution>
+
+**Step 1: Parse subcommand**
+
+Extract from $ARGUMENTS:
+- `on` / `off` / `status` / `allow <path>` / `deny <path>`
+- If no subcommand, default to `status`
+
+**Step 2: Read config**
+
+Read `.workflow/config.json`. If file missing, initialize with empty guard section.
+
+**Step 3: Execute subcommand**
+
+**`status`:**
+- Display: enabled/disabled, mode (allow/deny), paths list
+- Check if workflow-guard hook is active (read `.claude/settings.json` for hook presence)
+- If guard enabled but hook not active, warn: "⚠ PathGuard enabled but workflow-guard hook not installed. Run `maestro hooks level full` to activate."
+
+**`on`:**
+- Set `guard.enabled = true`
+- If `guard.paths` is empty, set default: `["src/", "tests/", ".workflow/"]`
+- Check hook level, warn if < full
+- Write config
+
+**`off`:**
+- Set `guard.enabled = false`
+- Preserve existing paths and mode
+- Write config
+
+**`allow <path>`:**
+- Normalize path to forward slashes, ensure trailing slash for directories
+- If `guard.mode` is `deny`, switch to `allow` and clear paths with warning
+- 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`, switch to `deny` and clear paths with warning
+- 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)
+- Write config
+
+**Step 4: Confirm**
+
+Display updated guard configuration.
+
+</execution>
+
+<error_codes>
+- E001: `.workflow/config.json` not found and cannot be created (not a maestro project)
+- W001: PathGuard enabled but workflow-guard hook not installed
+</error_codes>
+
+<success_criteria>
+- [ ] Config read/written correctly
+- [ ] Hook level warning displayed when applicable
+- [ ] Updated configuration shown after changes
+</success_criteria>
+
+<completion>
+### Next-step routing
+| Condition | Suggestion |
+|-----------|-----------|
+| Guard enabled, hook not installed | `maestro hooks level full` |
+| Want to verify guard works | Edit a file outside allowed paths |
+</completion>

package/.agy/skills/maestro-help/index/catalog.json

@@ -126,7 +126,7 @@
     {"name": "scholar-ideation", "category": "scholar", "description": "研究构思 — 文献搜索到研究规划", "source": "../scholar-ideation/SKILL.md"},
     {"name": "scholar-latex-organizer", "category": "scholar", "description": "LaTeX 模板整理 — 会议模板 .zip 清理为 Overleaf 就绪结构", "source": "../scholar-latex-organizer/SKILL.md"},
     {"name": "scholar-publish", "category": "scholar", "description": "会议发表准备 — 演示文稿、学术海报、推广内容", "source": "../scholar-publish/SKILL.md"},
-    {"name": "scholar-rebuttal-pro", "category": "scholar", "description": "审稿回复 — Gemini/CLI 协作分析 + 多视角讨论 + 证据策略", "source": "../scholar-rebuttal-pro/SKILL.md"},
+    {"name": "scholar-rebuttal-pro", "category": "scholar", "description": "审稿回复 — Agy/CLI 协作分析 + 多视角讨论 + 证据策略", "source": "../scholar-rebuttal-pro/SKILL.md"},
     {"name": "scholar-review", "category": "scholar", "description": "学术论文审查 — 投稿前自审 + 收到评审后的回复写作", "source": "../scholar-review/SKILL.md"},
     {"name": "scholar-thesis-docx", "category": "scholar", "description": "学位论文 Word 文档 — 生成、修订、格式化严格学术排版", "source": "../scholar-thesis-docx/SKILL.md"},
     {"name": "scholar-writing", "category": "scholar", "description": "端到端学术论文写作 — 从研究仓库到出版级 LaTeX 手稿", "source": "../scholar-writing/SKILL.md"}

package/.agy/skills/maestro-help/phases/03-workflow-guide.md

@@ -179,7 +179,7 @@ Odyssey:  odyssey-debug / odyssey-improve / odyssey-planex / odyssey-ui → (自
 - **Analyze 双层**: 宏观(文本参数)探索影响面产出 scope_verdict；微观(数字参数)Phase 级深入分析
 - **scope_verdict**: analyze 宏观完成后的路由建议 — large→roadmap, medium/small→直达 plan
 - **Overlay**: 非侵入式命令补丁，扩展命令行为而不修改源文件
-- **Delegate**: 将子任务委派给外部 AI 工具（Gemini/Claude/Codex）
+- **Delegate**: 将子任务委派给外部 AI 工具（Agy/Claude/Codex）
 - **Spec**: 项目约束规则（coding/arch/debug/test），自动注入到工作流
 - **Wiki**: 知识图谱，存储详细技术文档
 - **Ralph**: 自适应决策引擎，动态调整执行链