autosnippet 2.19.8 → 3.0.0

package/skills/autosnippet-intent/SKILL.md

@@ -34,19 +34,18 @@ Use this skill when the user's intent is unclear or overlaps multiple capabiliti
 - `autosnippet-batch-scan` / `autosnippet-recipe-candidates` → merged into autosnippet-candidates
 - `autosnippet-dep-graph` → merged into autosnippet-structure
 
-## MCP tools (reference only)
+## MCP tools (reference only — 12 个整合工具)
 
 - System: `autosnippet_health`, `autosnippet_capabilities`
-- Search: `autosnippet_search`, `autosnippet_context_search`, `autosnippet_keyword_search`, `autosnippet_semantic_search`
-- Browse: `autosnippet_list_recipes`, `autosnippet_get_recipe`, `autosnippet_list_rules`, `autosnippet_list_patterns`, `autosnippet_list_facts`
-- Insights: `autosnippet_recipe_insights`, `autosnippet_compliance_report`
-- Graph: `autosnippet_graph_query`, `autosnippet_graph_impact`, `autosnippet_graph_path`, `autosnippet_graph_stats`
-- Structure: `autosnippet_get_targets`, `autosnippet_get_target_files`, `autosnippet_get_target_metadata`
-- Candidates: `autosnippet_validate_candidate`, `autosnippet_check_duplicate`, `autosnippet_submit_knowledge`, `autosnippet_submit_knowledge_batch`, `autosnippet_submit_knowledge_batch`, `autosnippet_enrich_candidates`
-- Guard: `autosnippet_guard_check`, `autosnippet_guard_audit_files`, `autosnippet_scan_project`
-- Telemetry: `autosnippet_confirm_usage`
-- Bootstrap: `autosnippet_bootstrap_knowledge`, `autosnippet_bootstrap_refine`
-- Skills: `autosnippet_list_skills`, `autosnippet_load_skill`, `autosnippet_create_skill`, `autosnippet_update_skill`, `autosnippet_delete_skill`, `autosnippet_suggest_skills`
+- Search: `autosnippet_search` (mode: auto / context / keyword / semantic)
+- Knowledge: `autosnippet_knowledge` (operation: list / get / insights / confirm_usage)
+- Graph: `autosnippet_graph` (operation: query / impact / path / stats)
+- Structure: `autosnippet_structure` (operation: targets / files / metadata)
+- Submit: `autosnippet_submit_knowledge`, `autosnippet_submit_knowledge_batch`
+- Document: `autosnippet_save_document`
+- Guard: `autosnippet_guard` (code 单文件 / files[] 批量)
+- Bootstrap: `autosnippet_bootstrap` (operation: knowledge / refine / scan)
+- Skills: `autosnippet_skill` (operation: list / load / create / update / delete / suggest)
 
 This skill is a router only; it does not perform actions itself.
 

package/skills/autosnippet-lifecycle/SKILL.md

@@ -37,24 +37,21 @@ This skill documents the Recipe lifecycle and clarifies what Agent can and canno
 ## Agent Role: What You CAN Do
 
 ### 1. Submit Candidates
-- `autosnippet_submit_knowledge` - single structured candidate
+- `autosnippet_submit_knowledge` - single structured candidate (built-in auto-validate + dedup)
 - `autosnippet_submit_knowledge_batch` - batch structured candidates
-- `autosnippet_submit_knowledge_batch` - submit .md files as candidates
 
 ### 2. Validate and Enhance Candidates
-- `autosnippet_validate_candidate` - pre-validate quality
-- `autosnippet_check_duplicate` - check for duplicates
+- Submit via `autosnippet_submit_knowledge` which auto-validates and checks duplicates
 - Add structured content: rationale, steps, codeChanges, knowledgeType, complexity, tags, constraints, headers
 
 ### 3. Search and Query Recipes
-- `autosnippet_list_recipes` - list with filters (kind/language/category/knowledgeType/status/complexity)
-- `autosnippet_get_recipe` - get full Recipe details
-- `autosnippet_list_rules` / `autosnippet_list_patterns` / `autosnippet_list_facts` - query by kind
-- `autosnippet_context_search` / `autosnippet_keyword_search` / `autosnippet_semantic_search` - search
-- `autosnippet_graph_query` / `autosnippet_graph_impact` - knowledge graph
+- `autosnippet_knowledge(operation=list)` - list with filters (kind/language/category/knowledgeType/status/complexity)
+- `autosnippet_knowledge(operation=get, id)` - get full Recipe details
+- `autosnippet_search` - unified search (mode=auto/context/keyword/semantic)
+- `autosnippet_graph(operation=query/impact)` - knowledge graph
 
 ### 4. Record Usage Telemetry
-- `autosnippet_confirm_usage` - record when user adopts/applies a Recipe
+- `autosnippet_knowledge(operation=confirm_usage)` - record when user adopts/applies a Recipe
   - `usageType: "adoption"` - user adopted the Recipe
   - `usageType: "application"` - user applied the Recipe in code
 
@@ -79,20 +76,18 @@ This skill documents the Recipe lifecycle and clarifies what Agent can and canno
 ### Workflow 1: User asks to add a code pattern
 1. Analyze the code pattern
 2. Generate structured candidate with rationale, steps, etc.
-3. `autosnippet_check_duplicate` - verify no duplicate exists
-4. `autosnippet_validate_candidate` - pre-validate quality
-5. `autosnippet_submit_knowledge` - submit to candidate pool
-6. Tell user: "Candidate submitted. Review in Dashboard Candidates page."
+3. `autosnippet_submit_knowledge` - submit to candidate pool (auto-validates + dedup check)
+4. Tell user: "Candidate submitted. Review in Dashboard Candidates page."
 
 ### Workflow 2: User asks about an existing Recipe
-1. `autosnippet_context_search` or `autosnippet_list_recipes` to find it
-2. `autosnippet_get_recipe` to get full details
+1. `autosnippet_search` or `autosnippet_knowledge(operation=list)` to find it
+2. `autosnippet_knowledge(operation=get, id)` to get full details
 3. Present the Recipe content to user
-4. If user adopts it: `autosnippet_confirm_usage` with usageType=adoption
+4. If user adopts it: `autosnippet_knowledge(operation=confirm_usage)` with usageType=adoption
 
 ### Workflow 3: User asks to update a Recipe
 1. Explain: "I cannot modify Recipes directly. I can submit an improved version as a new candidate."
-2. `autosnippet_get_recipe` to read current content
+2. `autosnippet_knowledge(operation=get, id)` to read current content
 3. Generate improved candidate based on user's feedback
 4. `autosnippet_submit_knowledge` - submit improved version
 5. Tell user: "Improved version submitted as candidate. Update the Recipe in Dashboard."

package/skills/autosnippet-recipes/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: autosnippet-recipes
-description: Provides this project's Recipe-based context to the agent. Recipes are the project's standard knowledge (code patterns + usage guides + structured relations). Use when answering about project standards, Guard, conventions, or when suggesting code. Supports in-context lookup, terminal search (asd search), and on-demand semantic search via MCP tool autosnippet_context_search.
+description: Provides this project's Recipe-based context to the agent. Recipes are the project's standard knowledge (code patterns + usage guides + structured relations). Use when answering about project standards, Guard, conventions, or when suggesting code. Supports in-context lookup, terminal search (asd search), and on-demand semantic search via MCP tool autosnippet_search (mode=context).
 ---
 
 # AutoSnippet Recipe Context (Project Context)
 
-> Self-check and Fallback: MCP tools return unified JSON Envelope. Before heavy ops call autosnippet_health/autosnippet_capabilities. On failure do not retry in same turn; use static context or narrow scope.
+> Self-check and Fallback: MCP tools return unified JSON Envelope. Before heavy ops call `autosnippet_health`. On failure do not retry in same turn; use static context or narrow scope.
 
 This skill provides the agent with this project's context from AutoSnippet Recipes. Recipes are the project's standard knowledge base: code patterns, usage guides, and structured relations.
 
@@ -44,7 +44,7 @@ Recipe is the core knowledge unit. V3 uses a unified structured model:
 
 ## Instructions for the agent
 
-1. **Project context**: Read `references/project-recipes-context.md` in this skill folder for **Recipe 轻量索引**（title/trigger/category/summary 表格）。如需 Recipe 全文，调用 MCP `autosnippet_get_recipe(id)` 或 `autosnippet_search(query)`。索引缺失时，可直接读 `AutoSnippet/recipes/` 目录。
+1. **Project context**: Read `references/project-recipes-context.md` in this skill folder for **Recipe 轻量索引**（title/trigger/category/summary 表格）。如需 Recipe 全文，调用 MCP `autosnippet_knowledge(operation=get, id)` 或 `autosnippet_search(query)`。索引缺失时，可直接读 `AutoSnippet/recipes/` 目录。
 
 2. **Finding code on demand**: Look up matching Recipe by title/summary/usage guide, use its code as standard to suggest. Cite the Recipe title.
 
@@ -53,14 +53,14 @@ Recipe is the core knowledge unit. V3 uses a unified structured model:
 4. **Search - three ways**:
    - In-context: `references/project-recipes-context.md` 轻量索引按 title/trigger/summary 匹配
    - Terminal: `asd search <keyword>` or `asd search --semantic <keyword>`
-   - MCP: `autosnippet_context_search` with query and optional limit
+   - MCP: `autosnippet_search` (mode=auto 或 mode=context) with query and optional limit
 
 5. **Browsing Recipes via MCP**:
-   - `autosnippet_list_recipes` - list with kind/language/category/knowledgeType/status/complexity filters
-   - `autosnippet_get_recipe` - get single Recipe by ID (full content/relations/constraints)
-   - `autosnippet_list_facts` - list kind=fact structural knowledge
+   - `autosnippet_knowledge(operation=list)` - list with kind/language/category/knowledgeType/status/complexity filters
+   - `autosnippet_knowledge(operation=get, id)` - get single Recipe by ID (full content/relations/constraints)
+   - `autosnippet_knowledge(operation=list, kind=fact)` - list kind=fact structural knowledge
 
-6. **Confirming usage**: Call `autosnippet_confirm_usage` with recipeId and usageType (adoption/application) when user adopts a Recipe. Telemetry only.
+6. **Confirming usage**: Call `autosnippet_knowledge(operation=confirm_usage, id, usageType)` when user adopts a Recipe. Telemetry only.
 
 7. **Updating context**: After user changes Recipes, tell them to run `asd install:cursor-skill` to regenerate references.
 
@@ -78,71 +78,38 @@ Recipe is the core knowledge unit. V3 uses a unified structured model:
 
 ---
 
-## MCP Tools Reference (38 tools)
+## MCP Tools Reference (12 个整合工具)
 
 ### Query (Agent can freely use)
 
 | Tool | Description |
 |------|-------------|
-| autosnippet_health | Health check |
-| autosnippet_capabilities | List all tool capabilities |
-| autosnippet_search | Unified search (auto: BM25+semantic fusion) |
-| autosnippet_context_search | Smart context retrieval (intent → multi-agent → 4-layer funnel) |
-| autosnippet_keyword_search | SQL LIKE exact keyword search |
-| autosnippet_semantic_search | Vector semantic search |
-| autosnippet_list_rules | List kind=rule |
-| autosnippet_list_patterns | List kind=pattern |
-| autosnippet_list_facts | List kind=fact |
-| autosnippet_list_recipes | General list (multi-filter) |
-| autosnippet_get_recipe | Get Recipe details |
-| autosnippet_recipe_insights | Recipe quality insights (scores, usage stats, relations summary) |
-| autosnippet_compliance_report | Compliance assessment report |
-| autosnippet_graph_query | Knowledge graph query |
-| autosnippet_graph_impact | Graph impact analysis |
-| autosnippet_graph_path | Graph path finding (BFS shortest path between Recipes) |
-| autosnippet_graph_stats | Graph global statistics (edge count, relation distribution) |
-| autosnippet_get_targets | List project Targets |
-| autosnippet_get_target_files | Get Target file list |
-| autosnippet_get_target_metadata | Get Target metadata |
-
-### Candidate Submit/Validate (Agent core capability)
+| `autosnippet_health` | Health check + KB stats |
+| `autosnippet_search` | Unified search (`mode`: auto/context/keyword/semantic) |
+| `autosnippet_knowledge` | Knowledge browse (`operation`: list/get/insights/confirm_usage) |
+| `autosnippet_graph` | Knowledge graph (`operation`: query/impact/path/stats) |
+| `autosnippet_structure` | Project structure (`operation`: targets/files/metadata) |
 
-| Tool | Description |
-|------|-------------|
-| autosnippet_submit_knowledge | Submit single candidate (supports structured content) |
-| autosnippet_submit_knowledge_batch | Batch submit candidates |
-| autosnippet_submit_knowledge_batch | Submit draft .md files as candidates |
-| autosnippet_save_document | Save development document (design doc, debug report, ADR) — title + markdown only |
-| autosnippet_validate_candidate | Validate candidate quality |
-| autosnippet_check_duplicate | Dedup check |
-| autosnippet_enrich_candidates | AI semantic field enrichment for candidates |
-
-### Guard & Scan
+### Candidate Submit (Agent core capability)
 
 | Tool | Description |
 |------|-------------|
-| autosnippet_guard_check | Single code Guard rule check |
-| autosnippet_guard_audit_files | Multi-file batch Guard audit |
-| autosnippet_scan_project | Lightweight project scan + Guard audit |
-| autosnippet_bootstrap_knowledge | Cold-start knowledge base initialization (9 dimensions) |
-| autosnippet_bootstrap_refine | AI refinement of bootstrap candidates (Phase 6) |
+| `autosnippet_submit_knowledge` | Submit single candidate (**strict validation** — missing required fields rejected immediately, no fallback). Must provide ALL fields in one call: title, language, content(+rationale), kind, doClause, category, trigger, description, headers, usageGuide, knowledgeType |
+| `autosnippet_submit_knowledge_batch` | Batch submit candidates (per-item strict validation + dedup + rate-limit) |
+| `autosnippet_save_document` | Save development document (design doc, debug report, ADR) — title + markdown only |
 
-### Skills Management
+### Guard & Scan & Bootstrap
 
 | Tool | Description |
 |------|-------------|
-| autosnippet_list_skills | List all available Agent Skills |
-| autosnippet_load_skill | Load Skill document for domain guidance |
-| autosnippet_create_skill | Create project-level Skill |
-| autosnippet_update_skill | Update project-level Skill |
-| autosnippet_delete_skill | Delete project-level Skill |
-| autosnippet_suggest_skills | AI-powered Skill creation suggestions |
+| `autosnippet_guard` | Code Guard check (`code` single / `files[]` batch — auto-routed) |
+| `autosnippet_bootstrap` | Cold-start + scan (`operation`: knowledge/refine/scan) |
 
-### Usage Telemetry
+### Skills Management
 
 | Tool | Description |
 |------|-------------|
-| autosnippet_confirm_usage | Confirm Recipe adopted/applied |
+| `autosnippet_skill` | Skill management (`operation`: list/load/create/update/delete/suggest) |
 
 ---
 
@@ -150,20 +117,20 @@ Recipe is the core knowledge unit. V3 uses a unified structured model:
 
 | Use | How |
 |-----|-----|
-| Audit | `// as:audit` in source; `asd watch` runs AI review against Recipes. Or MCP `autosnippet_guard_check` / `autosnippet_guard_audit_files` |
-| Search | `asd search keyword` or MCP `autosnippet_search` / `autosnippet_context_search` |
+| Audit | `// as:audit` in source; `asd watch` runs AI review against Recipes. Or MCP `autosnippet_guard` |
+| Search | `asd search keyword` or MCP `autosnippet_search` (mode=auto/context/keyword/semantic) |
 | AI Assistant | Dashboard RAG and AI chat use Recipes as context |
 | Xcode | Recipes linked to Snippets; synced to Xcode CodeSnippets |
 | Guard | kind=rule Recipes enforced by Guard checks during audit |
-| Insights | `autosnippet_recipe_insights` for quality scores, usage stats, and relation summary |
-| Graph | `autosnippet_graph_query` / `autosnippet_graph_impact` / `autosnippet_graph_path` for relationship analysis |
+| Insights | `autosnippet_knowledge(operation=insights, id)` for quality scores, usage stats, and relation summary |
+| Graph | `autosnippet_graph(operation=query/impact/path)` for relationship analysis |
 
 ---
 
 ## Auto-Extracting Headers for New Candidates
 
 1. From code (Recommended): Extract all import statements from user's code
-2. From existing Recipes: Check `references/project-recipes-context.md` index for matching modules, then call MCP `autosnippet_get_recipe(id)` for full content
-3. Via semantic search: Call `autosnippet_context_search` with query like "import ModuleName headers"
+2. From existing Recipes: Check `references/project-recipes-context.md` index for matching modules, then call MCP `autosnippet_knowledge(operation=get, id)` for full content
+3. Via semantic search: Call `autosnippet_search(mode=context)` with query like "import ModuleName headers"
 
 Use Option 1 first, then verify with Option 2 for consistency.

package/skills/autosnippet-structure/SKILL.md

@@ -5,7 +5,7 @@ description: Discover project structure (targets, files, dependency graph) and b
 
 # AutoSnippet — Structure & Dependencies & Knowledge Graph
 
-> Self-check & Fallback: MCP 工具返回统一 JSON Envelope（{ success, errorCode?, message?, data?, meta }）。重操作前调用 autosnippet_health/autosnippet_capabilities；失败时不在同一轮重试，转用静态上下文或缩小范围后再试。
+> Self-check & Fallback: MCP 工具返回统一 JSON Envelope（{ success, errorCode?, message?, data?, meta }）。重操作前调用 `autosnippet_health`；失败时不在同一轮重试，转用静态上下文或缩小范围后再试。
 
 Use this skill when the user asks about **project structure**, **SPM targets**, **dependency graph**, or **knowledge graph relationships**.
 
@@ -25,14 +25,14 @@ Use this skill when the user asks about **project structure**, **SPM targets**,
 
 | Tool | Purpose | Key Input |
 |------|---------|-----------|
-| `autosnippet_get_targets` | List all SPM Targets (with file count, language stats, inferred role) | `includeSummary` (default true) |
-| `autosnippet_get_target_files` | Get source files for a Target | `targetName` (required), `includeContent`, `contentMaxLines`, `maxFiles` |
-| `autosnippet_get_target_metadata` | Get Target metadata (dependencies, package info, inferred role, graph edges) | `targetName` (required) |
+| `autosnippet_structure(operation=targets)` | List all SPM Targets (with file count, language stats, inferred role) | `includeSummary` (default true) |
+| `autosnippet_structure(operation=files)` | Get source files for a Target | `targetName` (required), `includeContent`, `contentMaxLines`, `maxFiles` |
+| `autosnippet_structure(operation=metadata)` | Get Target metadata (dependencies, package info, inferred role, graph edges) | `targetName` (required) |
 
 ### Workflow: Discover project structure
-1. `autosnippet_get_targets` → see all Targets with roles
-2. `autosnippet_get_target_files(targetName)` → drill into specific Target
-3. `autosnippet_get_target_metadata(targetName)` → get dependencies and relations
+1. `autosnippet_structure(operation=targets)` → see all Targets with roles
+2. `autosnippet_structure(operation=files, targetName)` → drill into specific Target
+3. `autosnippet_structure(operation=metadata, targetName)` → get dependencies and relations
 
 ---
 
@@ -42,22 +42,22 @@ The knowledge graph captures **relationships between Recipes** (dependencies, ex
 
 | Tool | Purpose | Key Input |
 |------|---------|-----------|
-| `autosnippet_graph_query` | Get all relations for a Recipe node | `nodeId` (Recipe ID), `relation` (filter), `direction` (out/in/both) |
-| `autosnippet_graph_impact` | Impact analysis: what downstream depends on this Recipe | `nodeId`, `maxDepth` (default 3) |
-| `autosnippet_graph_path` | Find shortest path between two Recipes (BFS) | `fromId`, `toId`, `maxDepth` (1-10) |
-| `autosnippet_graph_stats` | Global graph statistics: edge count, relation type distribution | (none) |
+| `autosnippet_graph(operation=query)` | Get all relations for a Recipe node | `nodeId` (Recipe ID), `relation` (filter), `direction` (out/in/both) |
+| `autosnippet_graph(operation=impact)` | Impact analysis: what downstream depends on this Recipe | `nodeId`, `maxDepth` (default 3) |
+| `autosnippet_graph(operation=path)` | Find shortest path between two Recipes (BFS) | `fromId`, `toId`, `maxDepth` (1-10) |
+| `autosnippet_graph(operation=stats)` | Global graph statistics: edge count, relation type distribution | (none) |
 
 ### Workflow: Explore knowledge graph
-1. `autosnippet_graph_stats` → overview: how many edges, relation types
-2. `autosnippet_graph_query(nodeId)` → see all connections for a specific Recipe
-3. `autosnippet_graph_impact(nodeId)` → before changing a Recipe, check downstream impact
-4. `autosnippet_graph_path(fromId, toId)` → discover indirect relationships between Recipes
+1. `autosnippet_graph(operation=stats)` → overview: how many edges, relation types
+2. `autosnippet_graph(operation=query, nodeId)` → see all connections for a specific Recipe
+3. `autosnippet_graph(operation=impact, nodeId)` → before changing a Recipe, check downstream impact
+4. `autosnippet_graph(operation=path, fromId, toId)` → discover indirect relationships between Recipes
 
 ### When to use graph tools
-- User asks "修改这个 Recipe 会影响什么？" → `autosnippet_graph_impact`
-- User asks "这两个模块有什么关联？" → `autosnippet_graph_path`
-- User wants overview of knowledge connections → `autosnippet_graph_stats`
-- User wants to see all dependencies/extends/conflicts for a Recipe → `autosnippet_graph_query`
+- User asks "修改这个 Recipe 会影响什么？" → `autosnippet_graph(operation=impact)`
+- User asks "这两个模块有什么关联？" → `autosnippet_graph(operation=path)`
+- User wants overview of knowledge connections → `autosnippet_graph(operation=stats)`
+- User wants to see all dependencies/extends/conflicts for a Recipe → `autosnippet_graph(operation=query)`
 
 ---
 

package/templates/copilot-instructions.md

@@ -2,7 +2,7 @@
 
 ## 项目概览
 - 项目名称：AutoSnippet
-- 版本：V2（ESM, SQLite, MCP 31 工具）
+- 版本：V3（ESM, SQLite, MCP 11 工具 — 整合版）
 - 目标：通过 Recipe 知识库、Guard 规则检查、语义检索构建团队知识管理与代码复用工作流。
 - 项目根：包含 `boxspec.json` 的目录。
 
@@ -25,50 +25,51 @@
 1. **禁止直接修改** 知识库目录内容（`AutoSnippet/recipes/`、`.autosnippet/` 等）。
 2. 创建或入库必须走 **Dashboard** 或 MCP 工具流程（`autosnippet_submit_knowledge`、`autosnippet_submit_knowledge_batch`）。
 3. **优先使用 Recipe** 作为项目标准；源代码仅作补充。
-4. MCP 检索优先：使用 `autosnippet_search` 或 `autosnippet_context_search` 获取语义检索结果。
+4. MCP 检索优先：使用 `autosnippet_search`（默认 auto 融合模式，也可指定 mode=context 做上下文感知检索）。
 5. MCP 调用失败时，**不要在同一轮重复重试**，回退到已读文档或静态上下文。
 6. Skills 负责语义与流程，MCP 负责能力与调用；不要在 Skill 内硬编码 URL/HTTP。
 
-## MCP 工具速查
+## MCP 工具速查（12 个整合工具）
 
-### 检索（首选 search / context_search）
-- `autosnippet_search` — 统合搜索入口（auto 模式 BM25 + 语义融合去重）
-- `autosnippet_context_search` — 智能上下文检索（意图识别 + 4 层漏斗 + 会话连续性）
-- `autosnippet_keyword_search` — SQL LIKE 精确关键词
-- `autosnippet_semantic_search` — 向量语义搜索
+### 检索
+- `autosnippet_search` — 统合搜索入口（通过 `mode` 参数切换）
+  - `mode=auto`（默认）— BM25 + 语义融合去重
+  - `mode=context` — 智能上下文检索（4 层漏斗 + 会话连续性），支持 `sessionHistory`/`language`
+  - `mode=keyword` — SQL LIKE 精确关键词
+  - `mode=semantic` — 向量语义搜索
 
-### 知识列表 & 详情
-- `autosnippet_list_recipes` / `autosnippet_get_recipe` / `autosnippet_recipe_insights`
-- `autosnippet_list_rules` / `autosnippet_list_patterns` / `autosnippet_list_facts`
+### 知识浏览
+- `autosnippet_knowledge` — 统一知识访问入口（通过 `operation` 参数切换）
+  - `operation=list` — 列出 Recipe/Rule/Pattern/Fact（支持 `kind`/`language`/`category`/`status` 多条件过滤）
+  - `operation=get` — 按 ID 获取单个 Recipe 详情
+  - `operation=insights` — 获取 Recipe 质量洞察（分数/统计/关系）
+  - `operation=confirm_usage` — 确认 Recipe 被采纳/应用
+
+### 项目结构
+- `autosnippet_structure` — SPM Target 结构发现（`operation`: targets / files / metadata）
 
 ### 知识图谱
-- `autosnippet_graph_query` / `autosnippet_graph_impact` / `autosnippet_graph_path` / `autosnippet_graph_stats`
+- `autosnippet_graph` — 图谱查询（`operation`: query / impact / path / stats）
 
-### 候选提交 & 校验
-- `autosnippet_validate_candidate` — 提交前预校验（5 层）
-- `autosnippet_check_duplicate` — 相似度检测
-- `autosnippet_submit_knowledge` — 单条提交（reasoning 必填）
-- `autosnippet_submit_knowledge_batch` — 批量提交（含去重 + 限流）
-- `autosnippet_submit_knowledge_batch` — 解析草稿 Markdown 文件
-- `autosnippet_enrich_candidates` — AI 补全缺失语义字段
+### 候选提交
+- `autosnippet_submit_knowledge` — 单条提交（严格前置校验，缺少必要字段直接拒绝不入库。必填: title, language, content(+rationale), kind, doClause, category, trigger, description, headers, usageGuide, knowledgeType。所有字段必须在单次调用中一次性提供）
+- `autosnippet_submit_knowledge_batch` — 批量提交（含去重 + 限流 + 逐条严格校验，缺字段的条目被拒绝）
 
-### 项目扫描 & 冷启动
-- `autosnippet_get_targets` / `autosnippet_get_target_files` / `autosnippet_get_target_metadata`
-- `autosnippet_scan_project` — 轻量探查（文件清单 + Guard 审计）
-- `autosnippet_bootstrap_knowledge` — 冷启动知识库初始化（9 维度 + 自动生成 Project Skills）
-- `autosnippet_bootstrap_refine` — Bootstrap 候选 AI 润色（summary/insight/relations）
+### 开发文档
+- `autosnippet_save_document` — 保存开发文档（title + markdown，自动发布）
 
-### Guard & 治理
-- `autosnippet_guard_check` / `autosnippet_guard_audit_files` / `autosnippet_compliance_report`
+### Guard
+- `autosnippet_guard` — 代码规范检查（传 `code` 单文件 / 传 `files[]` 批量审计，自动路由）
 
 ### Skills
-- `autosnippet_list_skills` — 列出所有可用 Skills（内置 + 项目级）
-- `autosnippet_load_skill` — 加载 Skill 完整文档
-- `autosnippet_create_skill` — 创建项目级 Skill（写入 `AutoSnippet/skills/`）
-- `autosnippet_suggest_skills` — 基于使用模式推荐创建 Skill
+- `autosnippet_skill` — Skill 管理（`operation`: list / load / create / update / delete / suggest）
+
+### 冷启动 & 扫描
+- `autosnippet_bootstrap` — 项目冷启动与扫描（`operation`: knowledge / refine / scan）
 
-### 其它
-- `autosnippet_health` / `autosnippet_capabilities` / `autosnippet_confirm_usage`
+### 系统
+- `autosnippet_health` — 服务健康状态与知识库统计（可检测空 KB 触发冷启动）
+- `autosnippet_capabilities` — 服务能力清单（列出所有可用 MCP 工具，供 Agent 自发现）
 
 ## Recipe 结构要点
 - 必须包含：Frontmatter（`title`、`trigger` 必填）+ `## Snippet / Code Reference` + `## AI Context / Usage Guide`。
@@ -76,19 +77,19 @@
 - Usage Guide 必须用 `###` 三级标题分段，列表式书写，禁止一行文字墙。
 
 ## Project Skills
-- **发现**：`autosnippet_list_skills` — 列出所有可用 Skills（内置 + 项目级）
-- **加载**：`autosnippet_load_skill(skillName)` — 获取 Skill 完整操作指南
-- **创建**：`autosnippet_create_skill(name, description, content)` — 创建项目级 Skill
-- **推荐**：`autosnippet_suggest_skills` — 基于使用模式推荐创建 Skill
+- **发现**：`autosnippet_skill` — `operation=list` 列出所有可用 Skills（内置 + 项目级）
+- **加载**：`autosnippet_skill` — `operation=load, name=<skillName>` 获取 Skill 完整操作指南
+- **创建**：`autosnippet_skill` — `operation=create, name, description, content` 创建项目级 Skill
+- **推荐**：`autosnippet_skill` — `operation=suggest` 基于使用模式推荐创建 Skill
 - **Bootstrap 自动生成**：冷启动 Phase 5.5 自动生成 4 个 Project Skills（code-standard, architecture, project-profile, agent-guidelines）
 - **优先级**：项目级 Skill 同名覆盖内置；宏观知识查 Skill，微观代码模式查 Recipe
 
 ## 推荐工作流
-- **查找**：`autosnippet_search`（推荐）或 `autosnippet_context_search`（上下文感知）。
-- **产出候选**：`autosnippet_validate_candidate` 预校验 → `autosnippet_submit_knowledge` 提交。
-- **冷启动**：`autosnippet_bootstrap_knowledge` → `autosnippet_enrich_candidates` → `autosnippet_bootstrap_refine` → 逐 Target 深入 → `autosnippet_submit_knowledge_batch`。
-- **Skills 创建**：`autosnippet_suggest_skills` 分析 → `autosnippet_create_skill` 固化知识。
-- **采纳反馈**：`autosnippet_confirm_usage`（记录使用量影响排序权重）。
+- **查找**：`autosnippet_search`（推荐 mode=auto）或 `autosnippet_search` mode=context（上下文感知）。
+- **产出候选**：`autosnippet_submit_knowledge` 提交（严格前置校验，必须一次性提供所有必填字段，缺字段直接拒绝不入库）。
+- **冷启动**：`autosnippet_bootstrap` op=knowledge → `autosnippet_bootstrap` op=refine → 逐 Target 深入 → `autosnippet_submit_knowledge_batch`。
+- **Skills 创建**：`autosnippet_skill` op=suggest 分析 → `autosnippet_skill` op=create 固化知识。
+- **采纳反馈**：`autosnippet_knowledge` op=confirm_usage（记录使用量影响排序权重）。
 
 ## 与 Cursor 规则联动
 - 本文件与 `templates/cursor-rules/autosnippet-conventions.mdc` 保持一致。

package/templates/recipes-setup/README.md

@@ -157,14 +157,11 @@ V2 知识库中的 Recipe 按 `knowledgeType` 自动归入三类 kind，影响
 
 | 工具 | 说明 |
 |------|------|
-| `autosnippet_search` | 统合搜索（BM25 + 语义融合） |
-| `autosnippet_context_search` | 智能上下文检索 |
-| `autosnippet_validate_candidate` | 候选结构化预校验 |
-| `autosnippet_submit_knowledge` | 单条候选提交（reasoning 必填） |
+| `autosnippet_search` | 统合搜索（mode=auto: BM25 + 语义融合，mode=context: 智能上下文检索） |
+| `autosnippet_submit_knowledge` | 单条候选提交（严格前置校验，缺少必要字段直接拒绝不入库。必填: title, language, content(+rationale), kind, doClause, category, trigger, description, headers, usageGuide, knowledgeType） |
 | `autosnippet_submit_knowledge_batch` | 批量候选提交 |
-| `autosnippet_submit_knowledge_batch` | 解析草稿 Markdown 为候选 |
-| `autosnippet_confirm_usage` | 确认 Recipe 被采纳/应用 |
-| `autosnippet_recipe_insights` | 获取 Recipe 质量洞察（只读） |
+| `autosnippet_knowledge(operation=confirm_usage)` | 确认 Recipe 被采纳/应用 |
+| `autosnippet_knowledge(operation=insights)` | 获取 Recipe 质量洞察（只读） |
 
 ---