# kodelyth-ecc - Doramagic AI Context Pack

> 定位：安装前体验与判断资产。它帮助宿主 AI 有一个好的开始，但不代表已经安装、执行或验证目标项目。

## 充分原则

- **充分原则，不是压缩原则**：AI Context Pack 应该充分到让宿主 AI 在开工前理解项目价值、能力边界、使用入口、风险和证据来源；它可以分层组织，但不以最短摘要为目标。
- **压缩策略**：只压缩噪声和重复内容，不压缩会影响判断和开工质量的上下文。

## 给宿主 AI 的使用方式

你正在读取 Doramagic 为 kodelyth-ecc 编译的 AI Context Pack。请把它当作开工前上下文：帮助用户理解适合谁、能做什么、如何开始、哪些必须安装后验证、风险在哪里。不要声称你已经安装、运行或执行了目标项目。

## Claim 消费规则

- **事实来源**：Repo Evidence + Claim/Evidence Graph；Human Wiki 只提供显著性、术语和叙事结构。
- **事实最低状态**：`supported`
- `supported`：可以作为项目事实使用，但回答中必须引用 claim_id 和证据路径。
- `weak`：只能作为低置信度线索，必须要求用户继续核实。
- `inferred`：只能用于风险提示或待确认问题，不能包装成项目事实。
- `unverified`：不得作为事实使用，应明确说证据不足。
- `contradicted`：必须展示冲突来源，不得替用户强行选择一个版本。

## 它最适合谁

- **正在使用 Claude/Codex/Cursor/Gemini 等宿主 AI 的开发者**：README 或插件配置提到多个宿主 AI。 证据：`README.md` Claim：`clm_0003` supported 0.86
- **希望把专业流程带进宿主 AI 的用户**：仓库包含 Skill 文档。 证据：`skills/agent-eval/SKILL.md`, `skills/agent-handoff/SKILL.md`, `skills/agent-harness-construction/SKILL.md`, `skills/agent-introspection-debugging/SKILL.md` 等 Claim：`clm_0004` supported 0.86

## 它能做什么

- **AI Skill / Agent 指令资产库**（可做安装前预览）：项目包含可被宿主 AI 读取的 Skill 或 Agent 指令文件，可用于把专业流程带入 Claude、Codex、Cursor 等宿主。 证据：`skills/agent-eval/SKILL.md`, `skills/agent-handoff/SKILL.md`, `skills/agent-harness-construction/SKILL.md`, `skills/agent-introspection-debugging/SKILL.md` 等 Claim：`clm_0001` supported 0.86
- **命令行启动或安装流程**（需要安装后验证）：项目文档中存在可执行命令，真实使用需要在本地或宿主环境中运行这些命令。 证据：`README.md` Claim：`clm_0002` supported 0.86

## 怎么开始

- `npx kodelyth-ecc                              # Claude Code (default)` 证据：`README.md` Claim：`clm_0005` supported 0.86
- `npx kodelyth-ecc --target windsurf-project    # Windsurf (per-project)` 证据：`README.md` Claim：`clm_0006` supported 0.86
- `npx kodelyth-ecc --target windsurf-home       # Windsurf (global)` 证据：`README.md` Claim：`clm_0007` supported 0.86
- `npx kodelyth-ecc --target cursor-project      # Cursor IDE` 证据：`README.md` Claim：`clm_0008` supported 0.86
- `npx kodelyth-ecc --target codex-home          # Codex CLI` 证据：`README.md` Claim：`clm_0009` supported 0.86
- `npx kodelyth-ecc --target antigravity         # Google Antigravity` 证据：`README.md` Claim：`clm_0010` supported 0.86
- `npx kodelyth-ecc --target opencode            # OpenCode` 证据：`README.md` Claim：`clm_0011` supported 0.86
- `npx kodelyth-ecc --target cline               # Cline (VS Code)` 证据：`README.md` Claim：`clm_0012` supported 0.86
- `npx kodelyth-ecc --target roocode             # Roo Code (VS Code)` 证据：`README.md` Claim：`clm_0013` supported 0.86
- `npx kodelyth-ecc --target aider               # Aider terminal agent` 证据：`README.md` Claim：`clm_0014` supported 0.86

## 继续前判断卡

- **当前建议**：先做权限沙盒试用
- **为什么**：项目存在安装命令、宿主配置或本地写入线索，不建议直接进入主力环境，应先在隔离环境试装。

### 30 秒判断

- **现在怎么做**：先做权限沙盒试用
- **最小安全下一步**：先跑 Prompt Preview；若仍要安装，只在隔离环境试装
- **先别相信**：工具权限边界不能在安装前相信。
- **继续会触碰**：命令执行、宿主 AI 配置、本地环境或项目文件

### 现在可以相信

- **适合人群线索：正在使用 Claude/Codex/Cursor/Gemini 等宿主 AI 的开发者**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`README.md` Claim：`clm_0003` supported 0.86
- **适合人群线索：希望把专业流程带进宿主 AI 的用户**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`skills/agent-eval/SKILL.md`, `skills/agent-handoff/SKILL.md`, `skills/agent-harness-construction/SKILL.md`, `skills/agent-introspection-debugging/SKILL.md` 等 Claim：`clm_0004` supported 0.86
- **能力存在：AI Skill / Agent 指令资产库**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`skills/agent-eval/SKILL.md`, `skills/agent-handoff/SKILL.md`, `skills/agent-harness-construction/SKILL.md`, `skills/agent-introspection-debugging/SKILL.md` 等 Claim：`clm_0001` supported 0.86
- **能力存在：命令行启动或安装流程**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`README.md` Claim：`clm_0002` supported 0.86
- **存在 Quick Start / 安装命令线索**（supported）：可以相信项目文档出现过启动或安装入口；不要因此直接在主力环境运行。 证据：`README.md` Claim：`clm_0005` supported 0.86

### 现在还不能相信

- **工具权限边界不能在安装前相信。**（unverified）：MCP/tool 类项目通常会触碰文件、网络、浏览器或外部 API，必须真实检查权限和日志。
- **真实输出质量不能在安装前相信。**（unverified）：Prompt Preview 只能展示引导方式，不能证明真实项目中的结果质量。
- **宿主 AI 版本兼容性不能在安装前相信。**（unverified）：Claude、Cursor、Codex、Gemini 等宿主加载规则和版本差异必须在真实环境验证。
- **不会污染现有宿主 AI 行为，不能直接相信。**（inferred）：Skill、plugin、AGENTS/CLAUDE/GEMINI 指令可能改变宿主 AI 的默认行为。 证据：`AGENTS.md`, `CLAUDE.md`, `skills/agent-eval/SKILL.md`, `skills/agent-handoff/SKILL.md` 等
- **可安全回滚不能默认相信。**（unverified）：除非项目明确提供卸载和恢复说明，否则必须先在隔离环境验证。
- **真实安装后是否与用户当前宿主 AI 版本兼容？**（unverified）：兼容性只能通过实际宿主环境验证。
- **项目输出质量是否满足用户具体任务？**（unverified）：安装前预览只能展示流程和边界，不能替代真实评测。
- **安装命令是否需要网络、权限或全局写入？**（unverified）：这影响企业环境和个人环境的安装风险。 证据：`README.md`

### 继续会触碰什么

- **命令执行**：包管理器、网络下载、本地插件目录、项目配置或用户主目录。 原因：运行第一条命令就可能产生环境改动；必须先判断是否值得跑。 证据：`README.md`
- **宿主 AI 配置**：Claude/Codex/Cursor/Gemini/OpenCode 等宿主的 plugin、Skill 或规则加载配置。 原因：宿主配置会改变 AI 后续工作方式，可能和用户已有规则冲突。 证据：`AGENTS.md`, `CLAUDE.md`, `skills/agent-eval/SKILL.md`, `skills/agent-handoff/SKILL.md` 等
- **本地环境或项目文件**：安装结果、插件缓存、项目配置或本地依赖目录。 原因：安装前无法证明写入范围和回滚方式，需要隔离验证。 证据：`README.md`
- **宿主 AI 上下文**：AI Context Pack、Prompt Preview、Skill 路由、风险规则和项目事实。 原因：导入上下文会影响宿主 AI 后续判断，必须避免把未验证项包装成事实。

### 最小安全下一步

- **先跑 Prompt Preview**：用安装前交互式试用判断工作方式是否匹配，不需要授权或改环境。（适用：任何项目都适用，尤其是输出质量未知时。）
- **只在隔离目录或测试账号试装**：避免安装命令污染主力宿主 AI、真实项目或用户主目录。（适用：存在命令执行、插件配置或本地写入线索时。）
- **先备份宿主 AI 配置**：Skill、plugin、规则文件可能改变 Claude/Cursor/Codex 的默认行为。（适用：存在插件 manifest、Skill 或宿主规则入口时。）
- **安装后只验证一个最小任务**：先验证加载、兼容、输出质量和回滚，再决定是否深用。（适用：准备从试用进入真实工作流时。）

### 退出方式

- **保留安装前状态**：记录原始宿主配置和项目状态，后续才能判断是否可恢复。
- **准备移除宿主 plugin / Skill / 规则入口**：如果试装后行为异常，可以把宿主 AI 恢复到试装前状态。
- **记录安装命令和写入路径**：没有明确卸载说明时，至少要知道哪些目录或配置需要手动清理。
- **如果没有回滚路径，不进入主力环境**：不可回滚是继续前阻断项，不应靠信任或运气继续。

## 哪些只能预览

- 解释项目适合谁和能做什么
- 基于项目文档演示典型对话流程
- 帮助用户判断是否值得安装或继续研究

## 哪些必须安装后验证

- 真实安装 Skill、插件或 CLI
- 执行脚本、修改本地文件或访问外部服务
- 验证真实输出质量、性能和兼容性

## 边界与风险判断卡

- **把安装前预览误认为真实运行**：用户可能高估项目已经完成的配置、权限和兼容性验证。 处理方式：明确区分 prompt_preview_can_do 与 runtime_required。 Claim：`clm_0029` inferred 0.45
- **命令执行会修改本地环境**：安装命令可能写入用户主目录、宿主插件目录或项目配置。 处理方式：先在隔离环境或测试账号中运行。 证据：`README.md` Claim：`clm_0030` supported 0.86, `clm_0031` supported 0.86, `clm_0032` supported 0.86, `clm_0033` contradicted 0.20 等
- **源文档冲突：skill_count**：项目文档中存在数量表述不一致，AI Context Pack 必须提示用户不要把单一数字当作已验证事实。 处理方式：在 Human Manual 和 AI Context Pack 中共同标记为待核实，而不是强行选择一个数字。 证据：`skills/configure-ecc/SKILL.md`, `CHANGELOG.md`, `CHANGELOG.md`, `README.md` 等 Claim：`clm_0030` supported 0.86, `clm_0031` supported 0.86, `clm_0032` supported 0.86, `clm_0033` contradicted 0.20 等
- **源文档冲突：agent_count**：项目文档中存在数量表述不一致，AI Context Pack 必须提示用户不要把单一数字当作已验证事实。 处理方式：在 Human Manual 和 AI Context Pack 中共同标记为待核实，而不是强行选择一个数字。 证据：`CHANGELOG.md`, `CHANGELOG.md`, `CHANGELOG.md`, `CHANGELOG.md` 等 Claim：`clm_0030` supported 0.86, `clm_0031` supported 0.86, `clm_0032` supported 0.86, `clm_0033` contradicted 0.20 等
- **源文件冲突 skill_count**：发现多个值 `45, 187, 188, 194`，应在真实使用前核实。
- **源文件冲突 agent_count**：发现多个值 `10, 50, 58, 61, 62, 70`，应在真实使用前核实。
- **待确认**：真实安装后是否与用户当前宿主 AI 版本兼容？。原因：兼容性只能通过实际宿主环境验证。
- **待确认**：项目输出质量是否满足用户具体任务？。原因：安装前预览只能展示流程和边界，不能替代真实评测。
- **待确认**：安装命令是否需要网络、权限或全局写入？。原因：这影响企业环境和个人环境的安装风险。

## 开工前工作上下文

### 加载顺序

- 先读取 how_to_use.host_ai_instruction，建立安装前判断资产的边界。
- 读取 claim_graph_summary，确认事实来自 Claim/Evidence Graph，而不是 Human Wiki 叙事。
- 再读取 intended_users、capabilities 和 quick_start_candidates，判断用户是否匹配。
- 需要执行具体任务时，优先查 role_skill_index，再查 evidence_index。
- 遇到真实安装、文件修改、网络访问、性能或兼容性问题时，转入 risk_card 和 boundaries.runtime_required。

### 任务路由

- **AI Skill / Agent 指令资产库**：先基于 role_skill_index / evidence_index 帮用户挑选可用角色、Skill 或工作流。 边界：可做安装前 Prompt 体验。 证据：`skills/agent-eval/SKILL.md`, `skills/agent-handoff/SKILL.md`, `skills/agent-harness-construction/SKILL.md`, `skills/agent-introspection-debugging/SKILL.md` 等 Claim：`clm_0001` supported 0.86
- **命令行启动或安装流程**：先说明这是安装后验证能力，再给出安装前检查清单。 边界：必须真实安装或运行后验证。 证据：`README.md` Claim：`clm_0002` supported 0.86

### 上下文规模

- 文件总数：822
- 重要文件覆盖：40/822
- 证据索引条目：180
- 角色 / Skill 条目：192

### 证据不足时的处理

- **missing_evidence**：说明证据不足，要求用户提供目标文件、README 段落或安装后验证记录；不要补全事实。
- **out_of_scope_request**：说明该任务超出当前 AI Context Pack 证据范围，并建议用户先查看 Human Manual 或真实安装后验证。
- **runtime_request**：给出安装前检查清单和命令来源，但不要替用户执行命令或声称已执行。
- **source_conflict**：同时展示冲突来源，标记为待核实，不要强行选择一个版本。

## Prompt Recipes

### 适配判断

- 目标：判断这个项目是否适合用户当前任务。
- 预期输出：适配结论、关键理由、证据引用、安装前可预览内容、必须安装后验证内容、下一步建议。

```text
请基于 kodelyth-ecc 的 AI Context Pack，先问我 3 个必要问题，然后判断它是否适合我的任务。回答必须包含：适合谁、能做什么、不能做什么、是否值得安装、证据来自哪里。所有项目事实必须引用 evidence_refs、source_paths 或 claim_id。
```

### 安装前体验

- 目标：让用户在安装前感受核心工作流，同时避免把预览包装成真实能力或营销承诺。
- 预期输出：一段带边界标签的体验剧本、安装后验证清单和谨慎建议；不含真实运行承诺或强营销表述。

```text
请把 kodelyth-ecc 当作安装前体验资产，而不是已安装工具或真实运行环境。

请严格输出四段：
1. 先问我 3 个必要问题。
2. 给出一段“体验剧本”：用 [安装前可预览]、[必须安装后验证]、[证据不足] 三种标签展示它可能如何引导工作流。
3. 给出安装后验证清单：列出哪些能力只有真实安装、真实宿主加载、真实项目运行后才能确认。
4. 给出谨慎建议：只能说“值得继续研究/试装”“先补充信息后再判断”或“不建议继续”，不得替项目背书。

硬性边界：
- 不要声称已经安装、运行、执行测试、修改文件或产生真实结果。
- 不要写“自动适配”“确保通过”“完美适配”“强烈建议安装”等承诺性表达。
- 如果描述安装后的工作方式，必须使用“如果安装成功且宿主正确加载 Skill，它可能会……”这种条件句。
- 体验剧本只能写成“示例台词/假设流程”：使用“可能会询问/可能会建议/可能会展示”，不要写“已写入、已生成、已通过、正在运行、正在生成”。
- Prompt Preview 不负责给安装命令；如用户准备试装，只能提示先阅读 Quick Start 和 Risk Card，并在隔离环境验证。
- 所有项目事实必须来自 supported claim、evidence_refs 或 source_paths；inferred/unverified 只能作风险或待确认项。

```

### 角色 / Skill 选择

- 目标：从项目里的角色或 Skill 中挑选最匹配的资产。
- 预期输出：候选角色或 Skill 列表，每项包含适用场景、证据路径、风险边界和是否需要安装后验证。

```text
请读取 role_skill_index，根据我的目标任务推荐 3-5 个最相关的角色或 Skill。每个推荐都要说明适用场景、可能输出、风险边界和 evidence_refs。
```

### 风险预检

- 目标：安装或引入前识别环境、权限、规则冲突和质量风险。
- 预期输出：环境、权限、依赖、许可、宿主冲突、质量风险和未知项的检查清单。

```text
请基于 risk_card、boundaries 和 quick_start_candidates，给我一份安装前风险预检清单。不要替我执行命令，只说明我应该检查什么、为什么检查、失败会有什么影响。
```

### 宿主 AI 开工指令

- 目标：把项目上下文转成一次对话开始前的宿主 AI 指令。
- 预期输出：一段边界明确、证据引用明确、适合复制给宿主 AI 的开工前指令。

```text
请基于 kodelyth-ecc 的 AI Context Pack，生成一段我可以粘贴给宿主 AI 的开工前指令。这段指令必须遵守 not_runtime=true，不能声称项目已经安装、运行或产生真实结果。
```


## 角色 / Skill 索引

- 共索引 192 个角色 / Skill / 项目文档条目。

- **agent-eval**（skill）：Head-to-head comparison of coding agents Claude Code, Aider, Codex, etc. on custom tasks with pass rate, cost, time, and consistency metrics 激活提示：当用户任务与“agent-eval”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/agent-eval/SKILL.md`
- **agent-handoff**（skill）： 激活提示：当用户任务与“agent-handoff”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/agent-handoff/SKILL.md`
- **agent-harness-construction**（skill）：Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. 激活提示：当用户任务与“agent-harness-construction”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/agent-harness-construction/SKILL.md`
- **agent-introspection-debugging**（skill）：Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. 激活提示：当用户任务与“agent-introspection-debugging”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/agent-introspection-debugging/SKILL.md`
- **agent-payment-x402**（skill）：Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents. 激活提示：当用户任务与“agent-payment-x402”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/agent-payment-x402/SKILL.md`
- **agent-sort**（skill）：Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle. 激活提示：当用户任务与“agent-sort”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/agent-sort/SKILL.md`
- **agentic-engineering**（skill）：Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. 激活提示：当用户任务与“agentic-engineering”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/agentic-engineering/SKILL.md`
- **ai-first-engineering**（skill）：Engineering operating model for teams where AI agents generate a large share of implementation output. 激活提示：当用户任务与“ai-first-engineering”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/ai-first-engineering/SKILL.md`
- **ai-regression-testing**（skill）：Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. 激活提示：当用户任务与“ai-regression-testing”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/ai-regression-testing/SKILL.md`
- **android-clean-architecture**（skill）：Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. 激活提示：当用户任务与“android-clean-architecture”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/android-clean-architecture/SKILL.md`
- **api-connector-builder**（skill）：Build a new API connector or provider by matching the target repo's existing integration pattern exactly. Use when adding one more integration without inventing a second architecture. 激活提示：当用户任务与“api-connector-builder”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/api-connector-builder/SKILL.md`
- **api-design**（skill）：REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs. 激活提示：当用户任务与“api-design”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/api-design/SKILL.md`
- **architecture-decision-records**（skill）：Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is. 激活提示：当用户任务与“architecture-decision-records”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/architecture-decision-records/SKILL.md`
- **article-writing**（skill）：Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter. 激活提示：当用户任务与“article-writing”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/article-writing/SKILL.md`
- **automation-audit-ops**（skill）：Evidence-first automation inventory and overlap audit workflow for ECC. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything. 激活提示：当用户任务与“automation-audit-ops”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/automation-audit-ops/SKILL.md`
- **autonomous-agent-harness**（skill）：Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks Hermes, AutoGPT by leveraging Claude Code's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop. 激活提示：当用户任务与“autonomous-agent-harness”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/autonomous-agent-harness/SKILL.md`
- **autonomous-loops**（skill）：Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems. 激活提示：当用户任务与“autonomous-loops”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/autonomous-loops/SKILL.md`
- **backend-patterns**（skill）：Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. 激活提示：当用户任务与“backend-patterns”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/backend-patterns/SKILL.md`
- **benchmark**（skill）：Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives. 激活提示：当用户任务与“benchmark”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/benchmark/SKILL.md`
- **blueprint**（skill）：- 激活提示：当用户任务与“blueprint”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/blueprint/SKILL.md`
- **brand-voice**（skill）：Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes. 激活提示：当用户任务与“brand-voice”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/brand-voice/SKILL.md`
- **browser-qa**（skill）：Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features. 激活提示：当用户任务与“browser-qa”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/browser-qa/SKILL.md`
- **bun-runtime**（skill）：Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support. 激活提示：当用户任务与“bun-runtime”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/bun-runtime/SKILL.md`
- **canary-watch**（skill）：Use this skill to monitor a deployed URL for regressions after deploys, merges, or dependency upgrades. 激活提示：当用户任务与“canary-watch”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/canary-watch/SKILL.md`
- **carrier-relationship-management**（skill）： 激活提示：当用户任务与“carrier-relationship-management”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/carrier-relationship-management/SKILL.md`
- **ck**（skill）：Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions. 激活提示：当用户任务与“ck”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/ck/SKILL.md`
- **claude-api**（skill）：Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs. 激活提示：当用户任务与“claude-api”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/claude-api/SKILL.md`
- **claude-devfleet**（skill）：Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports. 激活提示：当用户任务与“claude-devfleet”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/claude-devfleet/SKILL.md`
- **click-path-audit**（skill）：Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores. 激活提示：当用户任务与“click-path-audit”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/click-path-audit/SKILL.md`
- **clickhouse-io**（skill）：ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads. 激活提示：当用户任务与“clickhouse-io”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/clickhouse-io/SKILL.md`
- **code-tour**（skill）：Create CodeTour .tour files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured "explain how this works" requests. 激活提示：当用户任务与“code-tour”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/code-tour/SKILL.md`
- **codebase-onboarding**（skill）：Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo. 激活提示：当用户任务与“codebase-onboarding”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/codebase-onboarding/SKILL.md`
- **coding-standards**（skill）：Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns. 激活提示：当用户任务与“coding-standards”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/coding-standards/SKILL.md`
- **compose-multiplatform-patterns**（skill）：Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI. 激活提示：当用户任务与“compose-multiplatform-patterns”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/compose-multiplatform-patterns/SKILL.md`
- **configure-ecc**（skill）：Interactive installer for Kodelyth ECC — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files. 激活提示：当用户任务与“configure-ecc”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/configure-ecc/SKILL.md`
- **connections-optimizer**（skill）：Reorganize the user's X and LinkedIn network with review-first pruning, add/follow recommendations, and channel-specific warm outreach drafted in the user's real voice. Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph around higher-signal relationships. 激活提示：当用户任务与“connections-optimizer”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/connections-optimizer/SKILL.md`
- **content-engine**（skill）：Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms. 激活提示：当用户任务与“content-engine”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/content-engine/SKILL.md`
- **content-hash-cache-pattern**（skill）：Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation. 激活提示：当用户任务与“content-hash-cache-pattern”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/content-hash-cache-pattern/SKILL.md`
- **context-budget**（skill）：Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations. 激活提示：当用户任务与“context-budget”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/context-budget/SKILL.md`
- **continuous-agent-loop**（skill）：Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. 激活提示：当用户任务与“continuous-agent-loop”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/continuous-agent-loop/SKILL.md`
- **continuous-learning-v2**（skill）：Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination. 激活提示：当用户任务与“continuous-learning-v2”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/continuous-learning-v2/SKILL.md`
- **continuous-learning**（skill）：Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use. 激活提示：当用户任务与“continuous-learning”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/continuous-learning/SKILL.md`
- **cost-aware-llm-pipeline**（skill）：Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching. 激活提示：当用户任务与“cost-aware-llm-pipeline”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/cost-aware-llm-pipeline/SKILL.md`
- **cost-aware-model-routing**（skill）：Pick the right model tier trivial/standard/hard for each ECC session task. Companion to the cost-aware-model-routing rule and the token-budget safety hook. Use when the user asks "what model should I use" or when a session is burning frontier-model tokens on routine work. 激活提示：当用户任务与“cost-aware-model-routing”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/cost-aware-model-routing/SKILL.md`
- **council**（skill）：Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing. 激活提示：当用户任务与“council”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/council/SKILL.md`
- **cpp-coding-standards**（skill）：C++ coding standards based on the C++ Core Guidelines isocpp.github.io . Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices. 激活提示：当用户任务与“cpp-coding-standards”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/cpp-coding-standards/SKILL.md`
- **cpp-testing**（skill）：Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers. 激活提示：当用户任务与“cpp-testing”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/cpp-testing/SKILL.md`
- **crosspost**（skill）：Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms. 激活提示：当用户任务与“crosspost”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/crosspost/SKILL.md`
- **csharp-testing**（skill）：C and .NET testing patterns with xUnit, FluentAssertions, mocking, integration tests, and test organization best practices. 激活提示：当用户任务与“csharp-testing”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/csharp-testing/SKILL.md`
- **customer-billing-ops**（skill）：Operate customer billing workflows such as subscriptions, refunds, churn triage, billing-portal recovery, and plan analysis using connected billing tools like Stripe. Use when the user needs to help a customer, inspect subscription state, or manage revenue-impacting billing operations. 激活提示：当用户任务与“customer-billing-ops”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/customer-billing-ops/SKILL.md`
- **customs-trade-compliance**（skill）： 激活提示：当用户任务与“customs-trade-compliance”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/customs-trade-compliance/SKILL.md`
- **dart-flutter-patterns**（skill）：Production-ready Dart and Flutter patterns covering null safety, immutable state, async composition, widget architecture, popular state management frameworks BLoC, Riverpod, Provider , GoRouter navigation, Dio networking, Freezed code generation, and clean architecture. 激活提示：当用户任务与“dart-flutter-patterns”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/dart-flutter-patterns/SKILL.md`
- **dashboard-builder**（skill）：Build monitoring dashboards that answer real operator questions for Grafana, SigNoz, and similar platforms. Use when turning metrics into a working dashboard instead of a vanity board. 激活提示：当用户任务与“dashboard-builder”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/dashboard-builder/SKILL.md`
- **data-scraper-agent**（skill）：Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM Gemini Flash , stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically. 激活提示：当用户任务与“data-scraper-agent”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/data-scraper-agent/SKILL.md`
- **database-migrations**（skill）：Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate . 激活提示：当用户任务与“database-migrations”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/database-migrations/SKILL.md`
- **deep-research**（skill）：Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations. 激活提示：当用户任务与“deep-research”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/deep-research/SKILL.md`
- **defi-amm-security**（skill）：Security checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, CEI ordering, donation or inflation attacks, oracle manipulation, slippage, admin controls, and integer math. 激活提示：当用户任务与“defi-amm-security”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/defi-amm-security/SKILL.md`
- **deployment-patterns**（skill）：Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. 激活提示：当用户任务与“deployment-patterns”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/deployment-patterns/SKILL.md`
- **design-system**（skill）：Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling. 激活提示：当用户任务与“design-system”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/design-system/SKILL.md`
- **django-patterns**（skill）：Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps. 激活提示：当用户任务与“django-patterns”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/django-patterns/SKILL.md`
- **django-security**（skill）：Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations. 激活提示：当用户任务与“django-security”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/django-security/SKILL.md`
- **django-tdd**（skill）：Django testing strategies with pytest-django, TDD methodology, factory boy, mocking, coverage, and testing Django REST Framework APIs. 激活提示：当用户任务与“django-tdd”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/django-tdd/SKILL.md`
- **dmux-workflows**（skill）：Multi-agent orchestration using dmux tmux pane manager for AI agents . Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows. 激活提示：当用户任务与“dmux-workflows”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/dmux-workflows/SKILL.md`
- **documentation-lookup**（skill）：Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework e.g. React, Next.js, Prisma . 激活提示：当用户任务与“documentation-lookup”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/documentation-lookup/SKILL.md`
- **dotnet-patterns**（skill）：Idiomatic C and .NET patterns, conventions, dependency injection, async/await, and best practices for building robust, maintainable .NET applications. 激活提示：当用户任务与“dotnet-patterns”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/dotnet-patterns/SKILL.md`
- **e2e-testing**（skill）：Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. 激活提示：当用户任务与“e2e-testing”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/e2e-testing/SKILL.md`
- **ecc-tools-cost-audit**（skill）：Evidence-first ECC Tools burn and billing audit workflow. Use when investigating runaway PR creation, quota bypass, premium-model leakage, duplicate jobs, or GitHub App cost spikes in the ECC Tools repo. 激活提示：当用户任务与“ecc-tools-cost-audit”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/ecc-tools-cost-audit/SKILL.md`
- **email-ops**（skill）：Evidence-first mailbox triage, drafting, send verification, and sent-mail-safe follow-up workflow for ECC. Use when the user wants to organize email, draft or send through the real mail surface, or prove what landed in Sent. 激活提示：当用户任务与“email-ops”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/email-ops/SKILL.md`
- **energy-procurement**（skill）： 激活提示：当用户任务与“energy-procurement”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/energy-procurement/SKILL.md`
- **enterprise-agent-ops**（skill）：Operate long-lived agent workloads with observability, security boundaries, and lifecycle management. 激活提示：当用户任务与“enterprise-agent-ops”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/enterprise-agent-ops/SKILL.md`
- **eval-harness**（skill）：Formal evaluation framework for Claude Code sessions implementing eval-driven development EDD principles 激活提示：当用户任务与“eval-harness”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/eval-harness/SKILL.md`
- **evm-token-decimals**（skill）：Prevent silent decimal mismatch bugs across EVM chains. Covers runtime decimal lookup, chain-aware caching, bridged-token precision drift, and safe normalization for bots, dashboards, and DeFi tools. 激活提示：当用户任务与“evm-token-decimals”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/evm-token-decimals/SKILL.md`
- **exa-search**（skill）：Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine. 激活提示：当用户任务与“exa-search”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/exa-search/SKILL.md`
- **fal-ai-media**（skill）：Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image Nano Banana , text/image-to-video Seedance, Kling, Veo 3 , text-to-speech CSM-1B , and video-to-audio ThinkSound . Use when the user wants to generate images, videos, or audio with AI. 激活提示：当用户任务与“fal-ai-media”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/fal-ai-media/SKILL.md`
- **finance-billing-ops**（skill）：Evidence-first revenue, pricing, refunds, team-billing, and billing-model truth workflow for ECC. Use when the user wants a sales snapshot, pricing comparison, duplicate-charge diagnosis, or code-backed billing reality instead of generic payments advice. 激活提示：当用户任务与“finance-billing-ops”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/finance-billing-ops/SKILL.md`
- **flutter-dart-code-review**（skill）：Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns BLoC, Riverpod, Provider, GetX, MobX, Signals , Dart idioms, performance, accessibility, security, and clean architecture. 激活提示：当用户任务与“flutter-dart-code-review”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/flutter-dart-code-review/SKILL.md`
- **foundation-models-on-device**（skill）：Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+. 激活提示：当用户任务与“foundation-models-on-device”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/foundation-models-on-device/SKILL.md`
- **frontend-design**（skill）：Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality. 激活提示：当用户任务与“frontend-design”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/frontend-design/SKILL.md`
- **frontend-patterns**（skill）：Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices. 激活提示：当用户任务与“frontend-patterns”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/frontend-patterns/SKILL.md`
- **frontend-slides**（skill）：Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices. 激活提示：当用户任务与“frontend-slides”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`skills/frontend-slides/SKILL.md`
- 其余 112 个条目见 `AI_CONTEXT_PACK.json`。

## 证据索引

- 共索引 180 条证据。

- **AGENTS.md**（documentation）：This file is read by AI agents Cascade, Cursor, Codex, etc. on every session. It tells them how to work in this repo and how to use the 70 specialist agents and 194 skills shipped with Kodelyth ECC. 证据：`AGENTS.md`
- **Why ECC ≠ Another Agent Collection**（documentation）：! npm version https://img.shields.io/npm/v/kodelyth-ecc.svg https://www.npmjs.com/package/kodelyth-ecc ! npm downloads https://img.shields.io/npm/dm/kodelyth-ecc.svg https://www.npmjs.com/package/kodelyth-ecc ! GitHub Stars https://img.shields.io/github/stars/sifxprime/kodelyth-ecc?style=social https://github.com/sifxprime/kodelyth-ecc/stargazers ! License https://img.shields.io/badge/license-MIT-blue.svg LICENSE ! Tests https://img.shields.io/badge/tests-373%20passing-brightgreen ! Claude Code https://img.shields.io/badge/Claude%20Code-Ready-8A2BE2 ! Windsurf https://img.shields.io/badge/Windsurf-Ready-06b6d4 ! Antigravity https://img.shields.io/badge/Antigravity-Ready-00ADD8 ! Cursor http… 证据：`README.md`
- **Hooks**（documentation）：Hooks are event-driven automations that fire before or after Claude Code tool executions. They enforce code quality, catch mistakes early, and automate repetitive checks. 证据：`hooks/README.md`
- **Rules**（documentation）：Rules are organized into a common layer plus language-specific directories: 证据：`rules/README.md`
- **Kodelyth ECC — PR Review GitHub Action**（documentation）：Kodelyth ECC — PR Review GitHub Action 证据：`actions/ecc-review/README.md`
- **Kodelyth ECC — Safety Hooks**（documentation）：Two production-ready safety primitives that ride on the existing ECC hook pipeline. Both are off by default — explicitly opt in via env vars so existing users see zero behavior change unless they ask for it. 证据：`hooks/safety/README.md`
- **Agent Orchestration**（documentation）：70 specialist agents are available. Intent routing is always-on — describe your problem in plain words and the right agent is invoked automatically. You can also invoke explicitly: use . 证据：`rules/common/agents.md`
- **规则**（documentation）：- common/ 包含通用原则 — 无语言特定的代码示例。 - zh/ 包含 common 目录的中文翻译版本。 - 语言目录 扩展通用规则，包含框架特定的模式、工具和代码示例。每个文件引用其对应的通用版本。 证据：`rules/zh/README.md`
- **代理编排**（documentation）：代理 用途 何时使用 ------- --------- ------------ planner 实现规划 复杂功能、重构 architect 系统设计 架构决策 tdd-guide 测试驱动开发 新功能、bug 修复 code-reviewer 代码审查 编写代码后 security-reviewer 安全分析 提交前 build-error-resolver 修复构建错误 构建失败时 e2e-runner E2E 测试 关键用户流程 refactor-cleaner 死代码清理 代码维护 doc-updater 文档 更新文档 rust-reviewer Rust 代码审查 Rust 项目 证据：`rules/zh/agents.md`
- **Visa Document Translator**（documentation）：Automatically translate visa application documents from images to professional English PDFs. 证据：`skills/visa-doc-translate/README.md`
- **Package**（package_manifest）：{ "name": "kodelyth-brand", "version": "1.0.0", "private": true, "description": "Brand asset conversion tools for Kodelyth", "scripts": { "convert": "node convert.js" }, "dependencies": { "puppeteer-core": "^24.43.1" } } 证据：`brand/package.json`
- **Package**（package_manifest）：{ "name": "kodelyth-ecc", "version": "1.8.1", "description": "Production-grade AI coding toolkit — 70 agents incl. devil-mode adversarial crew , 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server 16 tools / 6 prompts / 377 resources that bridges to Claude Desktop, LangGraph, AutoGen, CrewAI, and OpenAI Agents SDK. Works with Claude Code, Windsurf, Cursor, Codex, Antigravity, OpenCode, Cline, RooCode, Aider, Kimi, and Gemini CLI.", "author": "Kodelyth ", "license": "MIT", "repository": { "type": "git", "url": "https://github.com/sifxprime/kodelyth-ecc.git" }, "homepage": "https://github.com/sifxprime/kodelyth-ecc",… 证据：`package.json`
- **Package**（package_manifest）：{ "name": "openclaw-twitter", "version": "1.0.0", "description": "OpenClaw autonomous Twitter agent for @sifxprime / kodelyth-ecc", "private": true, "type": "commonjs", "scripts": { "setup": "node setup.js", "start": "node index.js", "post": "node index.js --once", "engage": "node engagement.js --once", "preview": "node index.js --preview" }, "dependencies": { "@anthropic-ai/sdk": "^0.52.0", "node-cron": "^3.0.3", "playwright": "^1.52.0", "dotenv": "^16.4.5" } } 证据：`scripts/openclaw-twitter/package.json`
- **Agent Eval Skill**（skill_instruction）：A lightweight CLI tool for comparing coding agents head-to-head on reproducible tasks. Every "which coding agent is best?" comparison runs on vibes — this tool systematizes it. 证据：`skills/agent-eval/SKILL.md`
- **Agent Handoff Protocol**（skill_instruction）：Single agents handle single concerns. Real engineering tasks span multiple concerns. Handoffs are how ECC chains agents without losing context. 证据：`skills/agent-handoff/SKILL.md`
- **Agent Harness Construction**（skill_instruction）：Use this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion. 证据：`skills/agent-harness-construction/SKILL.md`
- **Agent Introspection Debugging**（skill_instruction）：Use this skill when an agent run is failing repeatedly, consuming tokens without progress, looping on the same tools, or drifting away from the intended task. 证据：`skills/agent-introspection-debugging/SKILL.md`
- **Agent Payment Execution x402**（skill_instruction）：Enable AI agents to make autonomous payments with built-in spending controls. Uses the x402 HTTP payment protocol and MCP tools so agents can pay for external services, APIs, or other agents without custodial risk. 证据：`skills/agent-payment-x402/SKILL.md`
- **Agent Sort**（skill_instruction）：Use this skill when a repo needs a project-specific ECC surface instead of the default full install. 证据：`skills/agent-sort/SKILL.md`
- **Agentic Engineering**（skill_instruction）：Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls. 证据：`skills/agentic-engineering/SKILL.md`
- **AI-First Engineering**（skill_instruction）：Use this skill when designing process, reviews, and architecture for teams shipping with AI-assisted code generation. 证据：`skills/ai-first-engineering/SKILL.md`
- **AI Regression Testing**（skill_instruction）：Testing patterns specifically designed for AI-assisted development, where the same model writes code and reviews it — creating systematic blind spots that only automated tests can catch. 证据：`skills/ai-regression-testing/SKILL.md`
- **Android Clean Architecture**（skill_instruction）：Clean Architecture patterns for Android and KMP projects. Covers module boundaries, dependency inversion, UseCase/Repository patterns, and data layer design with Room, SQLDelight, and Ktor. 证据：`skills/android-clean-architecture/SKILL.md`
- **API Connector Builder**（skill_instruction）：Use this when the job is to add a repo-native integration surface, not just a generic HTTP client. 证据：`skills/api-connector-builder/SKILL.md`
- **API Design Patterns**（skill_instruction）：Conventions and best practices for designing consistent, developer-friendly REST APIs. 证据：`skills/api-design/SKILL.md`
- **Architecture Decision Records**（skill_instruction）：Capture architectural decisions as they happen during coding sessions. Instead of decisions living only in Slack threads, PR comments, or someone's memory, this skill produces structured ADR documents that live alongside the code. 证据：`skills/architecture-decision-records/SKILL.md`
- **Article Writing**（skill_instruction）：Write long-form content that sounds like an actual person with a point of view, not an LLM smoothing itself into paste. 证据：`skills/article-writing/SKILL.md`
- **Automation Audit Ops**（skill_instruction）：Use this when the user asks what automations are live, which jobs are broken, where overlap exists, or what tooling and connectors are actually doing useful work right now. 证据：`skills/automation-audit-ops/SKILL.md`
- **Autonomous Agent Harness**（skill_instruction）：Turn Claude Code into a persistent, self-directing agent system using only native features and MCP servers. 证据：`skills/autonomous-agent-harness/SKILL.md`
- **Autonomous Loops Skill**（skill_instruction）：Compatibility note v1.8.0 : autonomous-loops is retained for one release. The canonical skill name is now continuous-agent-loop . New loop guidance should be authored there, while this skill remains available to avoid breaking existing workflows. 证据：`skills/autonomous-loops/SKILL.md`
- **Backend Development Patterns**（skill_instruction）：Backend architecture patterns and best practices for scalable server-side applications. 证据：`skills/backend-patterns/SKILL.md`
- **Benchmark — Performance Baseline & Regression Detection**（skill_instruction）：Benchmark — Performance Baseline & Regression Detection 证据：`skills/benchmark/SKILL.md`
- **Blueprint — Construction Plan Generator**（skill_instruction）：Blueprint — Construction Plan Generator 证据：`skills/blueprint/SKILL.md`
- **Brand Voice**（skill_instruction）：Build a durable voice profile from real source material, then use that profile everywhere instead of re-deriving style from scratch or defaulting to generic AI copy. 证据：`skills/brand-voice/SKILL.md`
- **Browser QA — Automated Visual Testing & Interaction**（skill_instruction）：Browser QA — Automated Visual Testing & Interaction 证据：`skills/browser-qa/SKILL.md`
- **Bun Runtime**（skill_instruction）：Bun is a fast all-in-one JavaScript runtime and toolkit: runtime, package manager, bundler, and test runner. 证据：`skills/bun-runtime/SKILL.md`
- **Canary Watch — Post-Deploy Monitoring**（skill_instruction）：Canary Watch — Post-Deploy Monitoring 证据：`skills/canary-watch/SKILL.md`
- **Carrier Relationship Management**（skill_instruction）：You are a senior transportation manager with 15+ years managing carrier portfolios ranging from 40 to 200+ active carriers across truckload, LTL, intermodal, and brokerage. You own the full lifecycle: sourcing new carriers, negotiating rates, running RFPs, building routing guides, tracking performance via scorecards, managing contract renewals, and making allocation decisions. Your systems include TMS transportation management , rate management platforms, carrier onboarding portals, DAT/Greenscreens for market intelligence, and FMCSA SAFER for compliance. You balance cost reduction pressure against service quality, capacity security, and carrier relationship health — because when the market… 证据：`skills/carrier-relationship-management/SKILL.md`
- **ck — Context Keeper**（skill_instruction）：You are the Context Keeper assistant. When the user invokes any /ck: command, run the corresponding Node.js script and present its stdout to the user verbatim. Scripts live at: ~/.claude/skills/ck/commands/ expand ~ with $HOME . 证据：`skills/ck/SKILL.md`
- **Claude API**（skill_instruction）：Build applications with the Anthropic Claude API and SDKs. 证据：`skills/claude-api/SKILL.md`
- **Claude DevFleet Multi-Agent Orchestration**（skill_instruction）：Claude DevFleet Multi-Agent Orchestration 证据：`skills/claude-devfleet/SKILL.md`
- **/click-path-audit — Behavioural Flow Audit**（skill_instruction）：/click-path-audit — Behavioural Flow Audit 证据：`skills/click-path-audit/SKILL.md`
- **ClickHouse Analytics Patterns**（skill_instruction）：ClickHouse-specific patterns for high-performance analytics and data engineering. 证据：`skills/clickhouse-io/SKILL.md`
- **Code Tour**（skill_instruction）：Create CodeTour .tour files for codebase walkthroughs that open directly to real files and line ranges. Tours live in .tours/ and are meant for the CodeTour format, not ad hoc Markdown notes. 证据：`skills/code-tour/SKILL.md`
- **Codebase Onboarding**（skill_instruction）：Systematically analyze an unfamiliar codebase and produce a structured onboarding guide. Designed for developers joining a new project or setting up Claude Code in an existing repo for the first time. 证据：`skills/codebase-onboarding/SKILL.md`
- **Coding Standards & Best Practices**（skill_instruction）：Baseline coding conventions applicable across projects. 证据：`skills/coding-standards/SKILL.md`
- **Compose Multiplatform Patterns**（skill_instruction）：Patterns for building shared UI across Android, iOS, Desktop, and Web using Compose Multiplatform and Jetpack Compose. Covers state management, navigation, theming, and performance. 证据：`skills/compose-multiplatform-patterns/SKILL.md`
- **Configure Kodelyth ECC ECC**（skill_instruction）：An interactive, step-by-step installation wizard for the Kodelyth ECC project. Uses AskUserQuestion to guide users through selective installation of skills and rules, then verifies correctness and offers optimization. 证据：`skills/configure-ecc/SKILL.md`
- **Connections Optimizer**（skill_instruction）：Reorganize the user's network instead of treating outbound as a one-way prospecting list. 证据：`skills/connections-optimizer/SKILL.md`
- **Content Engine**（skill_instruction）：Build platform-native content without flattening the author's real voice into platform slop. 证据：`skills/content-engine/SKILL.md`
- **Content-Hash File Cache Pattern**（skill_instruction）：Cache expensive file processing results PDF parsing, text extraction, image analysis using SHA-256 content hashes as cache keys. Unlike path-based caching, this approach survives file moves/renames and auto-invalidates when content changes. 证据：`skills/content-hash-cache-pattern/SKILL.md`
- **Context Budget**（skill_instruction）：Analyze token overhead across every loaded component in a Claude Code session and surface actionable optimizations to reclaim context space. 证据：`skills/context-budget/SKILL.md`
- **Continuous Agent Loop**（skill_instruction）：This is the v1.8+ canonical loop skill name. It supersedes autonomous-loops while keeping compatibility for one release. 证据：`skills/continuous-agent-loop/SKILL.md`
- **Continuous Learning v2.1 - Instinct**（skill_instruction）：Continuous Learning v2.1 - Instinct -Based Architecture 证据：`skills/continuous-learning-v2/SKILL.md`
- **Continuous Learning Skill**（skill_instruction）：Automatically evaluates Claude Code sessions on end to extract reusable patterns that can be saved as learned skills. 证据：`skills/continuous-learning/SKILL.md`
- **Cost-Aware LLM Pipeline**（skill_instruction）：Patterns for controlling LLM API costs while maintaining quality. Combines model routing, budget tracking, retry logic, and prompt caching into a composable pipeline. 证据：`skills/cost-aware-llm-pipeline/SKILL.md`
- **Cost-Aware Model Routing — Explicit Skill**（skill_instruction）：Cost-Aware Model Routing — Explicit Skill 证据：`skills/cost-aware-model-routing/SKILL.md`
- **Council**（skill_instruction）：Convene four advisors for ambiguous decisions: - the in-context Claude voice - a Skeptic subagent - a Pragmatist subagent - a Critic subagent 证据：`skills/council/SKILL.md`
- **C++ Coding Standards C++ Core Guidelines**（skill_instruction）：C++ Coding Standards C++ Core Guidelines 证据：`skills/cpp-coding-standards/SKILL.md`
- **C++ Testing Agent Skill**（skill_instruction）：Agent-focused testing workflow for modern C++ C++17/20 using GoogleTest/GoogleMock with CMake/CTest. 证据：`skills/cpp-testing/SKILL.md`
- 其余 120 条证据见 `AI_CONTEXT_PACK.json` 或 `EVIDENCE_INDEX.json`。

## 宿主 AI 必须遵守的规则

- **把本资产当作开工前上下文，而不是运行环境。**：AI Context Pack 只包含证据化项目理解，不包含目标项目的可执行状态。 证据：`AGENTS.md`, `README.md`, `hooks/README.md`
- **回答用户时区分可预览内容与必须安装后才能验证的内容。**：安装前体验的消费者价值来自降低误装和误判，而不是伪装成真实运行。 证据：`AGENTS.md`, `README.md`, `hooks/README.md`

## 用户开工前应该回答的问题

- 你准备在哪个宿主 AI 或本地环境中使用它？
- 你只是想先体验工作流，还是准备真实安装？
- 你最在意的是安装成本、输出质量、还是和现有规则的冲突？

## 验收标准

- 所有能力声明都能回指到 evidence_refs 中的文件路径。
- AI_CONTEXT_PACK.md 没有把预览包装成真实运行。
- 用户能在 3 分钟内看懂适合谁、能做什么、如何开始和风险边界。

---

## Doramagic Context Augmentation

下面内容用于强化 Repomix/AI Context Pack 主体。Human Manual 只提供阅读骨架；踩坑日志会被转成宿主 AI 必须遵守的工作约束。

## Human Manual 骨架

使用规则：这里只是项目阅读路线和显著性信号，不是事实权威。具体事实仍必须回到 repo evidence / Claim Graph。

宿主 AI 硬性规则：
- 不得把页标题、章节顺序、摘要或 importance 当作项目事实证据。
- 解释 Human Manual 骨架时，必须明确说它只是阅读路线/显著性信号。
- 能力、安装、兼容性、运行状态和风险判断必须引用 repo evidence、source path 或 Claim Graph。

- **首页 - Kodelyth ECC 概览**：importance `high`
  - source_paths: README.md, KODELYTH.md, SOUL.md, package.json
- **安装指南**：importance `high`
  - source_paths: install.sh, install.ps1, GITHUB_SETUP.md, scripts/lib/install-executor.js, scripts/lib/install-manifests.js
- **快速开始**：importance `high`
  - source_paths: skills/kodelyth-quickstart/SKILL.md, commands/loop-start.md, commands/onboard.md
- **系统架构**：importance `high`
  - source_paths: rules/common/agent-intent-routing.md, rules/common/agents.md, rules/common/memory-protocol.md, scripts/lib/orchestration-session.js
- **意图路由系统**：importance `high`
  - source_paths: rules/common/agent-intent-routing.md, skills/intent-routing/SKILL.md, scripts/router/classify.js
- **智能体索引**：importance `high`
  - source_paths: agents/kodelyth-advisor.md, agents/pair-programmer.md, agents/debug-detective.md, agents/planner.md, wiki/Agent-Reference.md
- **Devil Mode - 红队对抗模式**：importance `medium`
  - source_paths: agents/prompt-injection-hunter.md, agents/supply-chain-auditor.md, agents/secret-hunter.md, agents/backdoor-hunter.md, agents/chaos-engineer.md
- **代码审查类智能体**：importance `medium`
  - source_paths: agents/code-reviewer.md, agents/typescript-reviewer.md, agents/python-reviewer.md, agents/go-reviewer.md, agents/rust-reviewer.md

## Repo Inspection Evidence / 源码检查证据

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `2e22435af4886e92f8a51ed320861ec561fe624c`
- inspected_files: `package.json`, `README.md`, `docs/supply-chain.md`, `docs/swarm.md`, `docs/evolve.md`, `docs/mcp-clients.md`, `docs/replay.md`, `docs/mcp.md`, `docs/dashboard.md`

宿主 AI 硬性规则：
- 没有 repo_clone_verified=true 时，不得声称已经读过源码。
- 没有 repo_inspection_verified=true 时，不得把 README/docs/package 文件判断写成事实。
- 没有 quick_start_verified=true 时，不得声称 Quick Start 已跑通。

## Doramagic Pitfall Constraints / 踩坑约束

这些规则来自 Doramagic 发现、验证或编译过程中的项目专属坑点。宿主 AI 必须把它们当作工作约束，而不是普通说明文字。

### Constraint 1: 可能修改宿主 AI 配置

- Trigger: 项目面向 Claude/Cursor/Codex/Gemini/OpenCode 等宿主，或安装命令涉及用户配置目录。
- Host AI rule: 列出会写入的配置文件、目录和卸载/回滚步骤。
- Why it matters: 安装可能改变本机 AI 工具行为，用户需要知道写入位置和回滚方法。
- Evidence: capability.host_targets | github_repo:1214171652 | https://github.com/sifxprime/kodelyth-ecc | host_targets=mcp_host, claude, claude_code, cursor
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 2: 能力判断依赖假设

- Trigger: README/documentation is current enough for a first validation pass.
- Host AI rule: 将假设转成下游验证清单。
- Why it matters: 假设不成立时，用户拿不到承诺的能力。
- Evidence: capability.assumptions | github_repo:1214171652 | https://github.com/sifxprime/kodelyth-ecc | README/documentation is current enough for a first validation pass.
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 3: 维护活跃度未知

- Trigger: 未记录 last_activity_observed。
- Host AI rule: 补 GitHub 最近 commit、release、issue/PR 响应信号。
- Why it matters: 新项目、停更项目和活跃项目会被混在一起，推荐信任度下降。
- Evidence: evidence.maintainer_signals | github_repo:1214171652 | https://github.com/sifxprime/kodelyth-ecc | last_activity_observed missing
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 4: 下游验证发现风险项

- Trigger: no_demo
- Host AI rule: 进入安全/权限治理复核队列。
- Why it matters: 下游已经要求复核，不能在页面中弱化。
- Evidence: downstream_validation.risk_items | github_repo:1214171652 | https://github.com/sifxprime/kodelyth-ecc | no_demo; severity=medium
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 5: 存在评分风险

- Trigger: no_demo
- Host AI rule: 把风险写入边界卡，并确认是否需要人工复核。
- Why it matters: 风险会影响是否适合普通用户安装。
- Evidence: risks.scoring_risks | github_repo:1214171652 | https://github.com/sifxprime/kodelyth-ecc | no_demo; severity=medium
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 6: issue/PR 响应质量未知

- Trigger: issue_or_pr_quality=unknown。
- Host AI rule: 抽样最近 issue/PR，判断是否长期无人处理。
- Why it matters: 用户无法判断遇到问题后是否有人维护。
- Evidence: evidence.maintainer_signals | github_repo:1214171652 | https://github.com/sifxprime/kodelyth-ecc | issue_or_pr_quality=unknown
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。

### Constraint 7: 发布节奏不明确

- Trigger: release_recency=unknown。
- Host AI rule: 确认最近 release/tag 和 README 安装命令是否一致。
- Why it matters: 安装命令和文档可能落后于代码，用户踩坑概率升高。
- Evidence: evidence.maintainer_signals | github_repo:1214171652 | https://github.com/sifxprime/kodelyth-ecc | release_recency=unknown
- Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。