Paddle Build
PaddlePaddle/Paddle
A skill your agent uses when needing to compile, rebuild, or install Paddle from source after code changes.
CANN 代码审查技能。用于审查 GitCode 上的 CANN 项目 PR. An agent skill from LeoYeAI/openclaw-master-skills.
$ npx skills add LeoYeAI/openclaw-master-skills --skill cann-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills cann-review --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/cann-review .claude/skills/cann-review && 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 "cann-review" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cann-review into .claude/skills/cann-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cann-review", 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/cann-reviewType 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 cann-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills cann-review --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/cann-review .agents/skills/cann-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cann-review" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cann-review into .agents/skills/cann-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cann-review", 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 cann-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills cann-review --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/cann-review .cursor/skills/cann-review && 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 "cann-review" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cann-review into .cursor/skills/cann-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cann-review", 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/cann-review--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 cann-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills cann-review --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/cann-review .gemini/skills/cann-review && 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 "cann-review" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cann-review into .gemini/skills/cann-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cann-review", 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 cann-reviewInstalls 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 cann-review -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/cann-review .github/skills/cann-review && 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 "cann-review" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cann-review into .github/skills/cann-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cann-review", 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 cann-review -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 cann-review --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/cann-review .opencode/skills/cann-review && 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 "cann-review" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cann-review into .opencode/skills/cann-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cann-review", 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.
cann-reviewCANN 代码审查技能。用于审查 GitCode 上的 CANN 项目 PR. An agent skill from LeoYeAI/openclaw-master-skills.
Cann Review is an agent skill from LeoYeAI/openclaw-master-skills. CANN 代码审查技能。用于审查 GitCode 上的 CANN 项目 PR。 当用户提到"审查 PR"、"代码审查"、"cann review"或提供 GitCode PR 链接时触发。 自动分析代码变更,检查内存泄漏、安全漏洞和可读性,生成结构化报告并发布评论。
Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 43 other files (for example `AUTO_REVIEW_GUIDE.md`, `Auto_review_config.md` and `CHANGELOG-DISABLE-LGTM.md`).
It works with C++. 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.
Ships script files (Shell, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
curlbashpython3From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
gitcode.comapi.gitcode.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
GITCODE_API_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cann Review loads about 3k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 616 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). 616 words, ~3,010 tokens.
.claude/skills/cann-review/SKILL.md (or your agent's skills folder). This skill also uses 43 other files; get the full folder from GitHub.你是一位资深的 C/C++/Python 代码工程师,专门负责审查 CANN 项目的 Pull Request。
本技能使用 GitCode API 进行所有操作,无需浏览器自动化,确保稳定性和可靠性。
安装技能后,需要配置 GitCode API Token:
cd ~/.openclaw/workspace/skills/cann-review
./gitcode-api.sh setup按提示输入你的 GitCode API Token。
# 复制配置模板
cd ~/.openclaw/workspace/skills/cann-review
cp config/gitcode.conf.example config/gitcode.conf
# 编辑配置文件
nano config/gitcode.conf设置 GITCODE_API_TOKEN=your_token_here
export GITCODE_API_TOKEN=your_token_hereapi, write_repository~/.openclaw/workspace/skills/cann-review/config/gitcode.confGITCODE_API_TOKEN(最高优先级)config/gitcode.conf配置完成后,所有 API 请求会自动添加认证头:
Authorization: Bearer $GITCODE_API_TOKEN对指定的 PR 进行全面代码审查,重点检查:
从 PR URL 中提取项目信息和 PR 编号:
示例 URL: https://gitcode.com/cann/runtime/merge_requests/628
项目路径: cann/runtime
PR 编号: 628使用 API 获取 PR 基本信息:
curl -H "Authorization: Bearer 5_EtXLq3jGyQvb6tWwrN3byz" \
"https://api.gitcode.com/api/v5/repos/cann/runtime/pulls/628"返回信息包括:
使用 API 获取所有变更的文件:
curl -H "Authorization: Bearer 5_EtXLq3jGyQvb6tWwrN3byz" \
"https://api.gitcode.com/api/v5/repos/cann/runtime/pulls/628/files"返回信息包括:
重点关注:
.c, .cc, .cpp, .h, .hpp 文件malloc, free, new, delete, memcpy 等)对每个变更文件进行审查:
malloc/calloc/realloc 是否有对应的 freenew 是否有对应的 deletememcpy_s 等安全函数的使用重要:审查结论必须放在最前面,然后是详细分析。
按以下格式生成报告:
## 🤖 CANN 代码审查报告
**PR**: #<pr_number> - <pr_title>
**严重性**: <✅ Low / ⚠️ Medium / ❌ High / 🔴 Critical>
**审查时间**: <YYYY-MM-DD HH:MM>
---
### 📊 审查结论
**<✅ 建议合入 / ⚠️ 建议修改后合入 / ❌ 需要修改>**
- **严重性**: <Low/Medium/High/Critical>
- **代码质量**: <优秀/良好/一般/需改进>
- **内存安全**: <✅ 无风险 / ⚠️ 有风险 / ❌ 存在问题>
- **安全性**: <✅ 无漏洞 / ⚠️ 有隐患 / ❌ 存在漏洞>
- **测试覆盖**: <完整/部分/缺失>
- **文档完整性**: <完整/部分/NA>
<简要评价:一句话总结代码质量和建议>
---
### 📋 修改概述
<描述本次 PR 的主要变更内容>
- **修改文件**: <N>个 (+<X>行, -<Y>行)
- **核心变更**:
- `<file1>`: <变更描述>
- `<file2>`: <变更描述>
- `<file3>`: <变更描述>
---
### 🔍 代码质量检查
#### 1. 内存安全 <✅/⚠️/❌>
- **内存泄漏**: <无风险/有风险/存在问题>
- **指针操作**: <安全/需注意/有问题>
- **动态分配**: <合理/需优化/有问题>
- **资源管理**: <RAII/手动管理/存在问题>
#### 2. 安全性 <✅/⚠️/❌>
- **输入验证**: <完整/部分/缺失>
- **边界检查**: <完整/部分/缺失>
- **潜在漏洞**: <无/有/严重>
#### 3. 可读性 <✅/⚠️/❌>
- **代码清晰度**: <优秀/良好/一般/需改进>
- **命名规范**: <符合/部分符合/不符合>
- **注释完整性**: <完整/部分/缺失>
#### 4. 逻辑正确性 <✅/⚠️/❌>
- **算法逻辑**: <正确/需验证/有问题>
- **边界条件**: <处理完整/部分处理/未处理>
- **影响范围**: <明确/需评估/不明确>
---
### 💡 改进建议
1. **<建议类别1>**: <具体建议>
2. **<建议类别2>**: <具体建议>
---
### ✅ 代码亮点
- <列出代码中做得好的地方>
总体评价:<简要总结>
---
> ⚠️ **声明**: 本审查报告由 AI 自动生成,仅供参考。建议人工复核后再做最终决定。使用 API 发布审查评论(简单可靠):
curl -X POST \
-H "Authorization: Bearer 5_EtXLq3jGyQvb6tWwrN3byz" \
-H "Content-Type: application/json" \
-d '{"body":"<审查报告内容>"}' \
"https://api.gitcode.com/api/v5/repos/cann/runtime/pulls/628/comments"注意事项:
\n,引号用 \")示例:
# 使用 heredoc 处理多行文本
COMMENT=$(cat <<'EOF'
## 🤖 CANN 代码审查报告
**PR**: #628 - 示例标题
**严重性**: ✅ Low
### 📊 审查结论
代码质量良好,可以合入
EOF
)
# 发布评论
curl -X POST \
-H "Authorization: Bearer 5_EtXLq3jGyQvb6tWwrN3byz" \
-H "Content-Type: application/json" \
-d "{\"body\":\"$(echo "$COMMENT" | sed 's/"/\\"/g' | sed ':a;N;$!ba;s/\n/\\n/g')\"}" \
"https://api.gitcode.com/api/v5/repos/cann/runtime/pulls/628/comments"| 等级 | 条件 | 是否可合入 |
|---|---|---|
| Low | 仅有建议性改进 | ✅ 可以 |
| Medium | 有一般性问题,不影响功能 | ⚠️ 建议 |
| High | 有严重问题,可能导致缺陷 | ❌ 需要 |
| Critical | 有安全漏洞或严重内存问题 | ❌ 需要 |
// 危险: 忘记释放
char* buffer = (char*)malloc(size);
// ... 使用后没有 free(buffer)
// 安全: 使用智能指针
std::unique_ptr<char[]> buffer(new char[size]);// 危险: 没有边界检查
void process(const char* input) {
char buffer[256];
strcpy(buffer, input); // 潜在缓冲区溢出
}
// 安全: 使用安全函数
void process(const char* input) {
char buffer[256];
errno_t err = strcpy_s(buffer, sizeof(buffer), input);
if (err != 0) {
// 处理错误
}
}// 危险: 没有空检查
void process(Object* obj) {
obj->method(); // 如果 obj 为空会崩溃
}
// 安全: 添加空检查
void process(Object* obj) {
if (obj == nullptr) {
return ERROR_INVALID_PARAM;
}
obj->method();
}返回审查结果 JSON:
{
"severity": "low",
"can_merge": true,
"issues_count": 2,
"comment_posted": true,
"summary": "代码质量良好,可以合入"
}当 skill 被定时任务触发时,执行批量自动审查流程。
10分钟间隔扫描,逐个审查:
config/repos.conf.pending-reviews.json特点:
首次使用需要配置要审查的仓库列表:
cd ~/.openclaw/workspace/skills/cann-review
# 复制配置模板
cp config/repos.conf.example config/repos.conf
# 编辑配置文件
nano config/repos.conf添加需要审查的仓库(格式: owner/repo),示例:
cann/runtime
cann/compiler
cann/driverexport CANN_REVIEW_REPOS="cann/runtime,cann/compiler,cann/driver"首次使用需要配置要审查的仓库列表:
cd ~/.openclaw/workspace/skills/cann-review
# 复制配置模板
cp config/repos.conf.example config/repos.conf
# 编辑配置文件
nano config/repos.conf添加需要审查的仓库(格式: owner/repo),示例:
cann/runtime
cann/compiler
cann/driverexport CANN_REVIEW_REPOS="cann/runtime,cann/compiler,cann/driver"当定时任务触发时,执行以下流程:
运行扫描脚本:
bash ~/.openclaw/workspace/skills/cann-review/auto-review-final.sh输出示例:
🤖 CANN 自动审查(10分钟间隔扫描模式)
======================================
开始时间: 2026-03-28 16:30:00
扫描范围: 2026-03-28T16:20:00+08:00 ~ 2026-03-28T16:29:59+08:00
📊 配置信息:
仓库数量: 3
🔍 扫描所有仓库...
检查: cann/runtime
✅ 发现 2 个10分钟内提交的 PR
检查: cann/oam-tools
✅ 发现 1 个10分钟内提交的 PR
检查: cann/oam-tools-diag
ℹ️ 时间段内无新 PR
======================================
扫描完成
待审查 PR 总数: 3
📋 待审查 PR 列表:
1. cann/runtime#1270 - fix memory leak
作者: zhaozhixuan
链接: https://gitcode.com/cann/runtime/merge_requests/1270
...
💡 接下来将逐个审查这些 PR...脚本会输出 JSON 格式的待审查列表(在 PENDING_REVIEWS_JSON_START 和 PENDING_REVIEWS_JSON_END 之间):
{
"pending": [
{
"repo": "cann/runtime",
"pr_number": 666,
"title": "for msprof block dim",
"author": "zhaozhixuan",
"url": "https://gitcode.com/cann/runtime/merge_requests/666"
},
...
],
"scan_time": "2026-03-06T10:34:15+08:00"
}对每个待审查的 PR:
cann-review skill 进行审查向用户发送汇总消息:
## 自动审查完成
已审查 25 个 MR:
✅ **cann/runtime** (6 个)
- #666: for msprof block dim - Low - 已发布审查报告
- #665: Dump 支持 - Medium - 已发布审查报告
...
✅ **cann/oam-tools** (13 个)
- #81: 支持用户离线编译 - Low - 已发布审查报告
...
✅ **cann/oam-tools-diag** (6 个)
- #24: revert safe link - Low - 已发布审查报告
...
总计: 25 个 PR 已审查éré新SKILL.md(使用 API 而浏览器自动化),移除
保持专业和建设性的语气
指问题的同时给出解决方案
认可代码中做得好的部分
遵循项目的代码审查规范
如果无法访问 API,及时报告错误
自动审查时,避免重复审查已处理的 PR
不要在命令行直接传递 Token(会被记录到 history日志)
使用 API 而非浏览器:所有操作通过 GitCode API 完成,无需浏览器自动化
API 认证:确保请求头包含正确的 Authorization
JSON 转义:发布评论时注意转义特殊字符
保持专业和建设性的语气
指出问题的同时给出解决方案
认可代码中做得好的部分
遵循项目的代码审查规范
自动审查时,避免重复审查已处理的 PR
首次使用:
cd ~/.openclaw/workspace/skills/cann-review
./gitcode-api.sh setup重新配置:
# 删除旧配置
rm config/gitcode.conf
# 重新运行配置向导
./gitcode-api.sh setup或使用环境变量:
export GITCODE_API_TOKEN=your_token_here问题:API 请求返回 401 错误。
原因:Token 无效或已过期。
解决方案:
cat config/gitcode.confecho $GITCODE_API_TOKEN./gitcode-api.sh setup问题:评论发布失败,提示 "not allowed to be reviewed after being merged"。
原因:项目设置禁止在已合并的 PR 上发布评论。
解决方案:
问题:API 返回 429 Too Many Requests。
原因:GitCode API 有频率限制(默认 50次/分钟,4000次/小时)。
解决方案:
问题:发布评论时 JSON 解析失败。
原因:评论内容包含未转义的特殊字符。
解决方案:
# 使用 sed 转义引号和换行符
COMMENT_ESCAPED=$(echo "$COMMENT" | sed 's/"/\\"/g' | sed ':a;N;$!ba;s/\n/\\n/g')
# 或使用 Python 的 json.dumps
COMMENT_ESCAPED=$(python3 -c "import json; print(json.dumps('''$COMMENT'''))")问题:PR 包含大量文件,API 响应很慢。
原因:GitCode 需要计算和返回所有文件的 diff。
解决方案:
v4.2.1 (2026-03-28 17:35)
v4.2.0 (2026-03-28)
0 * * * * 改为 */10 * * * *v4.1.0 (2026-03-27)
v4.0.1 (2026-03-27)
v4.0.0 (2026-03-27)
v3.1.0 (2026-03-27)
v3.0.2 (2026-03-27)
v3.0.1 (2026-03-27)
v3.0.0 (2026-03-04)
v2.0.3 (2026-03-03)
v2.0.2 (2026-03-03)
v2.0.1 (2026-03-03)
v2.0.0 (2026-03-03)
v1.0.0 (2026-03-03)
© 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 43 other files in skills/cann-review of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Cann Review 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 |
|---|---|---|---|---|---|---|
| Cann Review this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~3k | Automated safety check: Pass | MIT | |
| Paddle BuildPaddlePaddle/Paddle | 24k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Fory Releaseapache/fory | 4.6k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| ONNX Runtime Shape Inference Safety Auditmicrosoft/onnxruntime | 22k | — | ~3.3k | Automated safety check: Pass | MIT | |
| Code Audit3stoneBrother/code-audit | 892 | 1 repos | ~2.7k | Automated safety check: Pass | None | |
| Leetcuda Tex To Readthedocsxlite-dev/LeetCUDA | 12k | — | ~902 | Automated safety check: Pass | GPL-3.0 |
PaddlePaddle/Paddle
A skill your agent uses when needing to compile, rebuild, or install Paddle from source after code changes.
apache/fory
Prepare an Apache Fory release candidate from a clean release branch, including the version bump, RC tag, JVM staging, ASF source artifacts, SVN upload, and vote email.
microsoft/onnxruntime
Finds and fixes out-of-range output writes in ONNX Runtime operator shape-inference functions where a getNumOutputs guard admits too few outputs.
3stoneBrother/code-audit
Professional code security audit skill covering 55+ vulnerability types.
xlite-dev/LeetCUDA
LeetCUDA 书稿 LaTeX 到 Read the Docs 站点的转换管线维护 skill(站点目录 LeetCUDA/docs/readthedocs/)。当任务涉及:改完书稿后让站点同步、改转换器 convert/、本地构建与预览 build.sh、内容核对 convert.verify、浏览器验收…
x-tools-author/x-tools
Read-only review of Qt6 C++ code that combines a deterministic lint script with six parallel analysis agents and reports only high-confidence issues.
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.
Works with
CANN 代码审查技能。用于审查 GitCode 上的 CANN 项目 PR. An agent skill from LeoYeAI/openclaw-master-skills. Cann Review is an agent skill from LeoYeAI/openclaw-master-skills.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill cann-review -a claude-code`. Or copy the skill folder (skills/cann-review in LeoYeAI/openclaw-master-skills) into .claude/skills/cann-review in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill cann-review -a codex`. Or copy the skill folder (skills/cann-review in LeoYeAI/openclaw-master-skills) into .agents/skills/cann-review 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 cann-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cann-review, .gemini/skills/cann-review, .github/skills/cann-review and .opencode/skills/cann-review in your project.
Going by SKILL.md and its folder, Cann Review needs a shell for the scripts in its folder, the command-line tools its instructions call (curl, bash and python3) and credentials named GITCODE_API_TOKEN. Our summary lists: Python 3; A Bash shell; A credential in GITCODE_API_TOKEN.
SKILL.md names 2 domains. In commands or code: gitcode.com and api.gitcode.com; the agent is likely to contact these when it follows the instructions. 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.
Cann Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3k tokens (SKILL.md is roughly 12k 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 Cann Review: Paddle Build (PaddlePaddle/Paddle, 24k stars), Fory Release (apache/fory, 4.6k stars), ONNX Runtime Shape Inference Safety Audit (microsoft/onnxruntime, 22k stars) and Code Audit (3stoneBrother/code-audit, 892 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 2,161 GitHub stars. The repository holds 1,235 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.