Using Agent Skills
addyosmani/agent-skills
Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.
为任意项目初始化 Claude 持久化记忆系统(v3.0 搜索引擎模型)。自动扫描项目结构、技术栈、代码规范,生成完整的记忆文件和 CLAUDE.md 指令。
$ npx skills add LeoYeAI/openclaw-master-skills --skill init-memory -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills init-memory --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/init-memory .claude/skills/init-memory && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "init-memory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/init-memory into .claude/skills/init-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "init-memory", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/init-memoryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill init-memory -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills init-memory --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/init-memory .agents/skills/init-memory && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "init-memory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/init-memory into .agents/skills/init-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "init-memory", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill init-memory -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills init-memory --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/init-memory .cursor/skills/init-memory && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "init-memory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/init-memory into .cursor/skills/init-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "init-memory", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/init-memory--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill init-memory -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills init-memory --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/init-memory .gemini/skills/init-memory && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "init-memory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/init-memory into .gemini/skills/init-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "init-memory", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills init-memoryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill init-memory -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/init-memory .github/skills/init-memory && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "init-memory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/init-memory into .github/skills/init-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "init-memory", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill init-memory -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills init-memory --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/init-memory .opencode/skills/init-memory && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "init-memory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/init-memory into .opencode/skills/init-memory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "init-memory", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
init-memory为任意项目初始化 Claude 持久化记忆系统(v3.0 搜索引擎模型)。自动扫描项目结构、技术栈、代码规范,生成完整的记忆文件和 CLAUDE.md 指令。
Init Memory is an agent skill from LeoYeAI/openclaw-master-skills. 为任意项目初始化 Claude 持久化记忆系统(v3.0 搜索引擎模型)。自动扫描项目结构、技术栈、代码规范,生成完整的记忆文件和 CLAUDE.md 指令。
Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `_meta.json`).
It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are json, bash and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Init Memory loads about 3.2k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 325 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 325 words, ~3,186 tokens.
.claude/skills/init-memory/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.记忆系统 v3.0 — "搜索引擎"模型:启动只读摘要,详情按需检索
核心理念: Claude 不需要"记住一切",只需要"知道去哪找"。
用户输入参数: $ARGUMENTS
解析参数:
--force: 覆盖已有的记忆文件(默认跳过已存在的文件)--minimal: 只创建核心文件(SUMMARY.md, architecture.json, conventions.json, semantic-index.json, changelog.json)--lang zh: 注释和描述使用中文(默认)--lang en: 注释和描述使用英文如果 .claude/memory/SUMMARY.md 已存在且没有 --force 参数,停止执行并提示用户:
⚠️ 记忆系统已存在。使用
--force覆盖,或手动删除.claude/memory/目录后重试。
Glob "**/{package.json,tsconfig.json,Cargo.toml,go.mod,pyproject.toml,setup.py,requirements.txt,pom.xml,build.gradle,Gemfile,composer.json,CMakeLists.txt,Makefile,.csproj,pubspec.yaml,mix.exs,deno.json}" (忽略 node_modules、vendor、target、dist、build、.git)读取找到的配置文件,提取:
find . -maxdepth 3 -type d \
! -path '*/node_modules/*' ! -path '*/.git/*' ! -path '*/dist/*' \
! -path '*/build/*' ! -path '*/.next/*' ! -path '*/target/*' \
! -path '*/vendor/*' ! -path '*/__pycache__/*' ! -path '*/.claude/*' \
! -path '*/.venv/*' ! -path '*/venv/*' ! -path '*/.tox/*' \
| head -80 | sort根据项目语言类型选择合适的扫描模式:
TypeScript/JavaScript 项目:
Grep "^export (class|function|const|interface|type|enum)" --type ts,tsx,js,jsxPython 项目:
Grep "^(class |def )" --type pyGo 项目:
Grep "^(func |type .* struct)" --type goRust 项目:
Grep "^(pub fn |pub struct |pub enum |pub trait )" --type rsJava/Kotlin 项目:
Grep "^(public class|public interface|public enum|class |fun )" --type java,kt取前 100 个结果,识别核心模块和它们的位置。
find . \( -name '*.ts' -o -name '*.tsx' -o -name '*.js' -o -name '*.jsx' \
-o -name '*.py' -o -name '*.go' -o -name '*.rs' -o -name '*.java' \
-o -name '*.kt' -o -name '*.vue' -o -name '*.svelte' -o -name '*.rb' \
-o -name '*.ex' -o -name '*.exs' -o -name '*.dart' -o -name '*.swift' \
-o -name '*.cpp' -o -name '*.c' -o -name '*.h' \) \
! -path '*/node_modules/*' ! -path '*/dist/*' ! -path '*/build/*' \
! -path '*/target/*' ! -path '*/vendor/*' ! -path '*/.git/*' \
-exec wc -l {} + 2>/dev/null | sort -rn | head -20对超过 500 行的文件进行逻辑分区扫描(扫描 function/class/section 定义及其行号)。 如果项目源文件较少,可降低阈值到 300 行。
读取 3-5 个核心源文件的前 50 行,推断:
同时检查是否存在以下配置文件:
.eslintrc*, .prettierrc*, rustfmt.toml, .editorconfig, pyproject.toml [tool.black], setup.cfg [flake8], .rubocop.yml, biome.json
检查是否已有:
CLAUDE.md — 已有的 Claude 指令.claude/ 目录 — 已有的 Claude 配置CONTRIBUTING.md — 贡献指南中的规范.github/ — CI/CD 配置中的约束创建 .claude/memory/ 目录,然后基于 Step 1 的扫描结果创建以下文件。
重要规则:
$schema 字段使用实际项目名称(从配置文件推断),不要硬编码{
"$schema": "<项目名> Architecture",
"$version": "1.0.0",
"$updated": "<今天日期>",
"$description": "项目架构概览",
"project": {
"name": "<项目名>",
"description": "<从配置文件推断的项目描述>",
"monorepo": false,
"packageManager": "<npm|yarn|pnpm|pip|cargo|go modules|...>"
},
"techStack": {
"language": "<主要语言及版本>",
"framework": "<主要框架及版本>",
"buildTool": "<构建工具>",
"runtime": "<运行时环境>",
"uiLibrary": "<UI 库(如适用)>",
"testFramework": "<测试框架>"
},
"packages": {
"<包名>": {
"path": "<路径>",
"role": "<职责描述>",
"entry": "<入口文件>",
"format": "<ESM|CJS|mixed>"
}
},
"mainModules": {
"<模块名>": {
"file": "<文件路径>",
"lines": "<行数>",
"role": "<职责描述>",
"warning": "<注意事项(可选)>",
"keyDataStructures": ["<核心数据结构>"]
}
},
"keyDependencies": [
{ "name": "<包名>", "version": "<版本>", "purpose": "<用途>" }
]
}monorepo 项目: packages 字段列出所有子包及其角色。
单包项目: packages 只有一个条目或省略。
{
"$schema": "<项目名> Code Conventions",
"$version": "1.0.0",
"$updated": "<今天日期>",
"$description": "代码规范和约定。新增代码必须遵守这些规范",
"codeStyle": {
"language": "<TypeScript (strict)|Python 3.x|Go|...>",
"indent": "<2 spaces|4 spaces|tabs>",
"quotes": "<single|double>",
"semicolons": "<true|false|N/A>",
"trailingComma": "<none|es5|all|N/A>",
"formatter": "<Prettier|Black|gofmt|rustfmt|...>",
"linter": "<ESLint|Ruff|golint|clippy|...>"
},
"namingConventions": {
"files": { "<类型>": "<命名规则>" },
"code": {
"classes": "<PascalCase>",
"interfaces": "<规则>",
"functions": "<camelCase|snake_case>",
"constants": "<UPPER_SNAKE_CASE>",
"variables": "<camelCase|snake_case>"
}
},
"patterns": {
"<模式名>": {
"description": "<描述>",
"template": "<代码模板(可选)>",
"steps": ["<步骤>"]
}
},
"commitMessageStyle": {
"language": "<项目注释语言>",
"prefix": "feat:/fix:/refactor:/chore:/docs:/test:",
"examples": ["<示例>"]
},
"importOrder": ["<导入分组规则>"],
"criticalRules": [
"<从代码和配置中推断出的关键规则>"
]
}{
"$schema": "<项目名> Semantic Index",
"$version": "1.0.0",
"$updated": "<今天日期>",
"$description": "关键词索引——从功能域/关键词到相关文件的映射",
"index": {
"<关键词|别名|同义词>": {
"description": "<功能域描述>",
"files": [
{ "path": "<文件路径>", "sections": ["<逻辑区域>"], "lineRange": [0, 0] }
],
"quickRules": ["<该领域的快速提示/规则>"]
}
}
}基于 Step 1.3 的扫描结果填充。将相关的导出按功能域分组。
每个索引条目可以有多个关键词别名(用 | 分隔)。
{
"$schema": "<项目名> Hotspot Map",
"$version": "1.0.0",
"$updated": "<今天日期>",
"$description": "热点文件的逻辑分区图。修改大文件前先查此文件定位行号范围",
"files": {
"<文件名>": {
"path": "<完整相对路径>",
"totalLines": 0,
"touchFrequency": 0,
"sections": [
{
"name": "<逻辑分区名>",
"lineRange": [0, 0],
"description": "<该分区的功能描述>",
"keySymbols": ["<重要函数/类名>"],
"touchCount": 0,
"subSections": []
}
]
}
}
}仅包含超过 500 行(小项目 300 行)的文件。每个文件最多 15 个分区。
{
"$schema": "<项目名> Task Context",
"$version": "1.0.0",
"$updated": "<今天日期>",
"$description": "当前任务上下文。帮助 Claude 理解未完成的工作",
"currentTasks": [],
"recentCompleted": [],
"pendingIssues": [],
"completedTasks": [],
"knownLimitations": []
}{
"$schema": "<项目名> Session Changelog",
"$version": "1.0.0",
"$updated": "<今天日期>",
"$description": "增量变更日志。每次会话修改代码后追加记录",
"sessions": [
{
"id": "SESSION-001",
"date": "<今天日期>",
"summary": "初始化 Claude 记忆系统",
"changes": [
{
"action": "create",
"files": [".claude/memory/*", "CLAUDE.md"],
"reason": "建立持久化记忆系统,实现跨会话知识保持"
}
],
"decisions": ["采用 v3.0 搜索引擎模型:启动只读 SUMMARY.md,详情按需 Grep 检索"],
"lessonsLearned": [],
"ripples": { "description": "纯新增文件,无代码影响", "affectedModules": [], "sideEffects": [] },
"rejectedAlternatives": []
}
]
}{
"$schema": "<项目名> Bug & Fix Registry",
"$version": "1.0.0",
"$updated": "<今天日期>",
"$description": "已知 Bug 和修复记录。避免相同问题重复犯错",
"bugs": [],
"commonMistakes": [],
"predictions": []
}{
"$schema": "<项目名> Causality Graph",
"$version": "1.0.0",
"$updated": "<今天日期>",
"$description": "因果图谱——记录 Bug 的完整因果链。新 Bug 出现时沿已知链反向推导",
"chains": [],
"chainIndex": {}
}如果使用了 --minimal 参数,跳过: hotspot-map.json, task-context.json, bugs-and-fixes.json, causality-graph.json
# <项目名> — Claude 记忆摘要
> 记忆系统 v3.0 — 本文件是固定大小的"缓存",详细数据在各 JSON 文件中
## 🏗️ 架构速览
- **技术栈**: <语言 + 框架 + 构建工具>
- **项目结构**: <简要描述目录布局>
- **核心模块**: <列出 3-5 个最重要的模块>
## 📊 热点文件
<列出行数最多的 3-5 个文件及其行数>
## 🔄 最近 3 次变更
1. SESSION-001: 初始化 Claude 记忆系统
## 📋 当前状态
- **进行中**: 无
- **待处理**: 无
## ⚠️ 高频陷阱(Top 5)
暂无记录
## 🔍 检索指南
| 需要什么 | 怎么查 |
|----------|--------|
| 功能域→文件映射 | `Grep "关键词" .claude/memory/semantic-index.json` |
| 大文件行号定位 | `Grep "section名" .claude/memory/hotspot-map.json` |
| Bug 因果链 | `Grep "症状" .claude/memory/causality-graph.json` |
| 已知 Bug/预判 | `Grep "症状" .claude/memory/bugs-and-fixes.json` |
| 历史决策 | `Grep "功能" .claude/memory/changelog.json` |
| 代码规范 | `Read .claude/memory/conventions.json` |
| 完整架构 | `Read .claude/memory/architecture.json` |以下内容用 <!-- MEMORY-SYSTEM-START --> 和 <!-- MEMORY-SYSTEM-END --> 标记包裹:
<!-- MEMORY-SYSTEM-START -->
## 📖 启动时只读一个文件
\```
Read .claude/memory/SUMMARY.md
\```
**不要**在启动时读取其他记忆文件。SUMMARY.md 包含架构速览、当前状态、高频陷阱和检索指南。
## 🔍 按需检索(改代码/修 Bug 前查询)
需要详情时,用 Grep/Read **精准查询**对应文件,不要全量加载:
| 场景 | 做什么 |
|------|--------|
| **改代码前** — 定位文件和行号 | `Grep "关键词" .claude/memory/semantic-index.json` |
| **改核心文件** — 查逻辑分区行号 | `Grep "section名" .claude/memory/hotspot-map.json` |
| **修 Bug 前** — 匹配已知症状 | `Grep "症状关键词" .claude/memory/causality-graph.json` |
| **修 Bug 前** — 查是否已预判 | `Grep "症状" .claude/memory/bugs-and-fixes.json` |
| **查历史决策** — 为什么这样做 | `Grep "功能关键词" .claude/memory/changelog.json` |
| **查代码规范** — 命名/风格/模式 | `Read .claude/memory/conventions.json` |
| **查完整架构** — 模块/IPC/技术栈 | `Read .claude/memory/architecture.json` |
## ⚡ 关键规则
> 以下规则从项目扫描中自动生成,请根据实际情况补充
1. **热点文件** — 修改超过 500 行的文件前,必须先 Grep semantic-index + hotspot-map 定位
2. **修 Bug** — 先 Grep causality-graph 的 chainIndex 匹配症状
3. 提交信息推荐 `feat:/fix:/refactor:/chore:` 前缀
## 🔄 任务完成后必须更新
每次完成代码修改后,按需更新以下文件(只更新涉及到的):
### 必更新
- **changelog.json** — 在 `sessions` 数组末尾追加:
```json
{
"id": "SESSION-xxx", "date": "YYYY-MM-DD", "summary": "...",
"changes": [{ "action": "create|modify|delete", "files": [...], "reason": "..." }],
"decisions": [...], "lessonsLearned": [...],
"ripples": { "description": "...", "affectedModules": [...], "sideEffects": [...] },
"rejectedAlternatives": [{ "option": "...", "reason": "..." }]
}从各详细文件中提取最新信息,重写(非追加)SUMMARY.md:
最近 3 次变更 ← changelog.json 最后 3 条的 summary当前状态 ← task-context.json 的 currentTasks + pendingIssues高频陷阱 ← bugs-and-fixes.json 的 commonMistakes(Top 5)💡 设计理念:SUMMARY.md 是固定大小的"缓存",详细数据永远保留在原文件中。 Claude 不需要"记住一切",只需要"知道去哪找"。
<!-- MEMORY-SYSTEM-END -->
### 注入逻辑
1. **如果 CLAUDE.md 不存在**:
创建新文件,内容为:
```markdown
# <项目名> — Claude 工程指令
> 记忆系统 v3.0 — "搜索引擎"模型:启动只读摘要,详情按需检索
<记忆系统指令块><!-- MEMORY-SYSTEM-START --> 标记,替换标记之间的内容扫描创建的所有文件,统计大小,输出如下格式的报告:
✅ Claude 记忆系统初始化完成!
📁 创建的文件:
.claude/memory/SUMMARY.md (xxx bytes)
.claude/memory/architecture.json (xxx bytes)
.claude/memory/conventions.json (xxx bytes)
.claude/memory/semantic-index.json (xxx bytes)
.claude/memory/hotspot-map.json (xxx bytes)
.claude/memory/task-context.json (xxx bytes)
.claude/memory/changelog.json (xxx bytes)
.claude/memory/bugs-and-fixes.json (xxx bytes)
.claude/memory/causality-graph.json(xxx bytes)
CLAUDE.md (已更新/已创建)
📊 项目分析摘要:
- 技术栈: <语言> + <框架>
- 核心模块: <数量>个
- 热点文件(>500行): <数量>个
- 语义索引域: <数量>个
🧠 记忆系统设计:
- 启动加载: ~3KB(仅 SUMMARY.md)
- 详情存储: 按需 Grep 检索
- 增长模型: 启动负载永远 O(1)
💡 下一步建议:
1. 审查 architecture.json 中的模块描述是否准确
2. 检查 conventions.json 是否符合团队规范
3. 在 task-context.json 中添加当前进行中的任务
4. 将 .claude/memory/ 加入版本控制(推荐)
5. 根据项目特点补充 CLAUDE.md 中的关键规则关键规则 部分应自适应生成(如 Go 项目不需要 IPC 规则)© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/init-memory of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Init Memory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Init Memory this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~3.2k | Automated safety check: Pass | MIT | |
| Using Agent Skillsaddyosmani/agent-skills | 102k | 4 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Claude ReflectBayramAnnakov/claude-reflect | 1.7k | 2 repos | ~627 | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 | |
| Writing For Agentsbestofjs/bestofjs | 3.1k | 17 repos | ~2.7k | Automated safety check: Pass | MIT |
addyosmani/agent-skills
Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.
BayramAnnakov/claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
bestofjs/bestofjs
Writing documents for agents. An agent skill from bestofjs/bestofjs.
microsoft/SkillOpt
Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Categories
为任意项目初始化 Claude 持久化记忆系统(v3.0 搜索引擎模型)。自动扫描项目结构、技术栈、代码规范,生成完整的记忆文件和 CLAUDE.md 指令。. Init Memory is an agent skill from LeoYeAI/openclaw-master-skills.
Init Memory fits situations like: tasks that involve Agent instruction files.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill init-memory -a claude-code`. Or copy the skill folder (skills/init-memory in LeoYeAI/openclaw-master-skills) into .claude/skills/init-memory in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill init-memory -a codex`. Or copy the skill folder (skills/init-memory in LeoYeAI/openclaw-master-skills) into .agents/skills/init-memory in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill init-memory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/init-memory, .gemini/skills/init-memory, .github/skills/init-memory and .opencode/skills/init-memory in your project.
SKILL.md names no scripts, command-line tools or credentials: Init Memory is instructions for the agent only. Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Init Memory is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Init Memory: Using Agent Skills (addyosmani/agent-skills, 102k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars) and Task Observer (rebelytics/one-skill-to-rule-them-all, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,158 GitHub stars. The repository holds 1,215 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.