在当前项目初始化 L1-L2-L3 三级记忆骨架(CLAUDE.md 常驻层、.agents/INDEX.md 索引、.agents/ 详情目录、门禁清单、模板)。当用户说"初始化 harness"、"装上三级记忆"、"init harness"、"给这个项目上记忆系统",或新项目希望启用本插件方法论时使用。
Scanned 9/5/2026
Install to Claude Code
npx -y skills add reatcat/l123-harness --skill init-harness --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Init Harness?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/reatcat-init-harness)More formats (shields.io, HTML) on the badges page.
---
name: init-harness
description: 在当前项目初始化 L1-L2-L3 三级记忆骨架(CLAUDE.md 常驻层、.agents/INDEX.md 索引、.agents/ 详情目录、门禁清单、模板)。当用户说"初始化 harness"、"装上三级记忆"、"init harness"、"给这个项目上记忆系统",或新项目希望启用本插件方法论时使用。
---
# Init Harness —— 装机程序
把 L1-L2-L3 方法论骨架装进当前项目。骨架是**引擎生成的数据**:装完后项目自己积累知识,插件不再参与。
## 步骤
### 1. 前置检查
- 确认当前工作目录就是目标项目根(用户没指定就用 cwd)。
- 如果项目已有 `CLAUDE.md` 或 `.agents/`,**不要覆盖**:脚本本身永不覆盖已存在文件,但你要先看一眼现状,向用户说明哪些会新建、哪些会跳过。
### 2. 执行装机脚本
```bash
bash "${CLAUDE_PLUGIN_ROOT}/skills/init-harness/init.sh" "<项目根绝对路径>"
```
脚本会创建(不覆盖):
- `CLAUDE.md` —— L1 常驻层模板
- `.agents/INDEX.md` —— L2 索引模板
- `.agents/gate.conf` —— 门禁保护清单
- `.agents/{current,inbox,events,knowledge,pitfalls,runbooks,templates,archive}/`
- `.agents/templates/` —— spec/plan/pitfall/knowledge/runbook 模板
- `.agents/README.md`、`.agents/inbox/README.md`
### 3. 陪同用户完成三件事(不要跳过)
1. **审 L1 安全底线**:打开新生成的 `CLAUDE.md`,把「安全底线」一节逐条读给用户,按项目实际补充专有红线(例如:专用设备、禁止触碰的分支、数据不可编造的具体口径)。
2. **审门禁清单**:展示 `.agents/gate.conf` 默认保护项,问用户要不要增删。
3. **建议首个 git 提交**:骨架应入库,建议 `git add CLAUDE.md .agents` 并提交(提交信息由用户确认)。
### 4. 说明日常循环(一段话讲完即可)
- 干活:读 L2 索引按指针走;过程状态写 `.agents/current/notes.md`。
- 踩坑:修完用 `.agents/templates/pitfall-template.md` 记录,**提议**加入 L2 索引(需审批,改受保护文件要门禁令牌)。
- 提炼:定期跑 `event-review` 技能(/l123-harness:event-review)做周审。
## 纪律
- 绝不覆盖已有文件;冲突一律报告给用户裁决。
- 不在骨架里预填任何项目知识——空的表头就是对的。
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.