Triage
TalAter/annyang
Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang.
从 GitHub 找到最匹配的技术人才,生成个性化触达话术。适用于招聘工程师、寻找技术合伙人、猎头交付候选人等场景. An agent skill from LeoYeAI/openclaw-master-skills.
$ npx skills add LeoYeAI/openclaw-master-skills --skill ai-talent-hunter -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills ai-talent-hunter --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/ai-talent-hunter .claude/skills/ai-talent-hunter && 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 "ai-talent-hunter" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-talent-hunter into .claude/skills/ai-talent-hunter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-talent-hunter", 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/ai-talent-hunterType 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 ai-talent-hunter -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills ai-talent-hunter --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/ai-talent-hunter .agents/skills/ai-talent-hunter && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ai-talent-hunter" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-talent-hunter into .agents/skills/ai-talent-hunter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-talent-hunter", 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 ai-talent-hunter -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills ai-talent-hunter --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/ai-talent-hunter .cursor/skills/ai-talent-hunter && 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 "ai-talent-hunter" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-talent-hunter into .cursor/skills/ai-talent-hunter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-talent-hunter", 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/ai-talent-hunter--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 ai-talent-hunter -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills ai-talent-hunter --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/ai-talent-hunter .gemini/skills/ai-talent-hunter && 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 "ai-talent-hunter" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-talent-hunter into .gemini/skills/ai-talent-hunter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-talent-hunter", 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 ai-talent-hunterInstalls 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 ai-talent-hunter -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/ai-talent-hunter .github/skills/ai-talent-hunter && 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 "ai-talent-hunter" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-talent-hunter into .github/skills/ai-talent-hunter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-talent-hunter", 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 ai-talent-hunter -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 ai-talent-hunter --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/ai-talent-hunter .opencode/skills/ai-talent-hunter && 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 "ai-talent-hunter" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-talent-hunter into .opencode/skills/ai-talent-hunter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-talent-hunter", 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.
ai-talent-hunter从 GitHub 找到最匹配的技术人才,生成个性化触达话术。适用于招聘工程师、寻找技术合伙人、猎头交付候选人等场景. An agent skill from LeoYeAI/openclaw-master-skills.
AI Talent Hunter is an agent skill from LeoYeAI/openclaw-master-skills. 从 GitHub 找到最匹配的技术人才,生成个性化触达话术。适用于招聘工程师、寻找技术合伙人、猎头交付候选人等场景。
Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including scripts and reference files (for example `README.md`, `SECURITY.md` and `_meta.json`).
It sits in AI & LLM Engineering. It works with GitHub. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
5 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 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
GITHUB_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
AI Talent Hunter loads about 3.9k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 19 tokens; SKILL.md has 1,086 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 noted patterns worth knowing about, such as sudo or a known installer.
I access (user-provided, stored in local .env)- ✅ Token 存储在本地 `.env` 文件(不上传到 git)3. 复制 token 到 `.env` 文件(**不要提交到 git!**)# 创建 .env 文件(已在 .gitignore 中,不会被上传)echo "GITHUB_TOKEN=your_token_here" > .env- ✅ 使用 `.env` 文件(已加入 .gitignore)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); the scripts in this folder are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,086 words, ~3,887 tokens.
.claude/skills/ai-talent-hunter/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.从 GitHub 真实代码里找技术人才 — 不看简历看代码,不靠吹嘘靠项目。为 HR、猎头、技术管理者和创业者设计的智能招聘工具。
OpenClaw 安全扫描可能会提示 "Suspicious",这是正常的,原因如下:
prompts/ 文件夹包含 JD 解析和话术生成的 Prompt 模板,这是功能需要,不是恶意 prompt injection合规保证:
.env 文件(不上传到 git)用户可能这样说:
Skill 自动执行:
目标:将用户的口语化需求转译为 GitHub 搜索参数。
操作:
prompts/jd_parser_prompt.md{
"search_queries": [
"language:c++ rocksdb pushed:>2025-01-01",
"language:c++ leveldb lsm-tree pushed:>2025-01-01"
],
"target_languages": ["C++"],
"ecosystem_keywords": ["rocksdb", "leveldb", "lsm-tree"],
"location": "china",
"reasoning": "将'RocksDB 相关'转译为 rocksdb + leveldb + lsm-tree 生态"
}约束规则:详见 prompts/jd_parser_prompt.md(包含查询生成、活跃度过滤、地理位置处理、负向排除等规则)。
目标:从 GitHub 搜索候选人,构建完整画像并全局排序。
操作:
cd ~/.openclaw/workspace/skills/ai-talent-hunter
# 首次搜索(宽松位置匹配,默认)
python scripts/github_search.py \
--queries "language:c++ rocksdb pushed:>2025-01-01" "language:c++ leveldb lsm-tree pushed:>2025-01-01" \
--jd-keywords "rocksdb,lsm-tree,storage" \
--jd-language "C++" \
--location "shenzhen" \
--target 20 \
-o results.json
# 首次搜索(严格位置匹配 — 仅匹配指定城市/省份)
python scripts/github_search.py \
--queries "..." \
--jd-keywords "..." \
--jd-language "C++" \
--location "beijing" \
--location-strict \
--target 20 \
-o results.json
# 继续搜索(当已有结果全部展示完,需要搜更多时)
python scripts/github_search.py --resume SEARCH_ID --target 20 -o results.json需要环境变量:
export GITHUB_TOKEN=ghp_xxxxx # GitHub Personal Access Token地理位置匹配模式(⚠️ OpenClaw 必须根据用户措辞判断使用哪种模式):
| 用户措辞 | 模式 | CLI 参数 | 行为 |
|---|---|---|---|
| "Base 深圳"、"最好在北京"、"深圳优先" | 宽松(默认) | --location "shenzhen" | 城市→省份→国家→中文启发式 层级回落 |
| "必须是北京"、"只要北京的"、"限制北京" | 严格 | --location "beijing" --location-strict | 仅匹配城市/省份,不回落到国家级,Remote 也不通过 |
| "不限地区"、"远程"、不提位置 | 不过滤 | 不加 --location | 不做任何位置过滤 |
注意:宽松模式下 Remote 用户自动通过;严格模式下 Remote 不通过(用户说"必须是北京"就不想看其他城市的人,包括 Remote)。
搜索引擎说明:
funnel 字段)和停止状态(status 字段)搜索结果不佳时的优化建议(⚠️ OpenClaw 必须根据漏斗数据自动判断并给出建议):
搜索脚本输出 funnel 字段(漏斗数据)和 status 字段。当 status 不是 threshold_reached 时,OpenClaw 根据以下规则生成优化建议:
| 漏斗瓶颈 | 判断条件 | 建议 |
|---|---|---|
| 技术太冷门 | raw_from_repos < 50 | "当前技术方向搜索结果很少,建议扩展到相邻技术栈。" 并给出具体扩展建议(如 VisionOS → 加入 ARKit、SceneKit) |
| 地理位置太严格 | after_dedup > 100 但 after_location_filter < 10 | "技术匹配的候选人不少,但目标城市的人很少。建议放宽到省份/全国,或使用宽松模式。" |
| 活跃度过滤过严 | after_location_filter > 50 但高分候选人 < 5 | "候选人数量足够但质量不高(多数不活跃或匹配度低)。建议放宽 pushed 时间范围(如 2024 年)。" |
| 搜索结果耗尽 | status = "exhausted" | "已搜索全部可用结果。建议调整搜索关键词或放宽条件。" |
OpenClaw 给出建议时,必须提供具体的操作指引(如"去掉 --location-strict"、"关键词加入 XX"),而非泛泛而谈。
排序算法 V3(总分 100 分):
设计原则(猎头视角):
| 维度 | 得分规则 | 权重 |
|---|---|---|
| 1. 领域匹配度 | 主语言匹配(15) + 生态关键词分级(10/15/20) | 35 分 |
| 2. 可触达性 | 邮箱(10) + 博客(6) + Twitter(5) + 社交(6) + bio(3) + isHireable(5),可叠加,上限25 | 25 分 |
| 3. 代码影响力 | log₁₀(Star)×3(12) + log₁₀(Fork)×2(4) + log₁₀(Followers)×2(4) | 20 分 |
| 4. 有效活跃度 | 30天(12) / 90天(8) / 180天(4) | 12 分 |
| 5. 开源生态位 | 顶级Owner>500★(8) / 中等>100★(5) / 活跃>20★(3) | 8 分 |
详细评分逻辑:
1. 领域匹配度(Relevance - 35分)
2. 可触达性(Reachability - 25分)
3. 代码影响力(Impact - 20分)
4. 有效活跃度(Activity - 12分)
5. 开源生态位(Ecosystem - 8分)
档位划分:
输出:results.json(完整候选人列表,已排序,含漏斗数据和停止状态)
目标:让用户快速扫描候选人,标记状态(selected / passed / pending)。
为什么需要这一步?
每批展示数量:最多 15 人。不足 15 人时展示全部。
表头固定格式:
# 🎯 [职位名] — 候选人列表
搜索范围: [语言] + [关键词] | [位置] | 共 N 人,展示 Top 15
| # | 匹配 | 候选人 | 简介 | 公司 | 经验 | 📍 | 联系 | 状态 | 代表作 |
|---|------|--------|------|------|------|-----|------|------|--------|
| 1 | 🔥 | 张三 (@zhangsan) | ... | 字节跳动 | 8年 | 深圳 | 📧🌐🐦 | 🟢 | mutative (2.0K) |
| 2 | ⭐ | 李四 (@lisi) | ... | 阿里巴巴 | 5年 | 杭州 | 📧 | 🟢 | ssr (2.7K) |
...
---
回复数字选择:`1,3` = 选中 | `pass 2` = 跳过 | 「继续」查看下一批| 列名 | 数据来源 | 填写规则 |
|---|---|---|
| # | 序号 | 当前批次内的序号(1-15) |
| 匹配 | match_label 字段 | 🔥 极度匹配(≥80) / ⭐ 高度匹配(65-79) / 👍 匹配(50-64) / 📋 参考(<50) |
| 候选人 | name + github_id | 格式:真实姓名 (@github_id)。如果 name 等于 github_id 则只写一个 |
| 简介 | OpenClaw 根据 bio + 代表作 + 公司综合生成 | 见下方「简介生成规则」 |
| 公司 | company 字段 | 去掉 @ 前缀。为空时写「独立开发者」。超过 12 字截断加 .. |
| 经验 | dev_years 字段 | 格式:N年(基于 GitHub 账号创建时间推算,注意是"GitHub 活跃年限"不是"工作经验") |
| 📍 | location 字段 | 翻译为中文城市名。超过 6 字截断。目标城市加 🎯 标记 |
| 联系 | contact_icons 字段 | 图标组合:📧=邮箱 🌐=博客/网站 🐦=Twitter 🔗=其他社交。不展示具体值(Step 2 才展示) |
| 状态 | activity_label 字段 | 🟢=30天内活跃 🟡=90天内 🔵=半年内 ⚪=不活跃。如果 isHireable=true,activity_label 后面会带 " |
| 代表作 | 优先 showcase_repos(候选人自选置顶项目),无置顶时用 top_repos[0] | 格式:项目名 (星数)。星数 ≥1000 用 K 表示。置顶项目加 📌 标记 |
目的:让不懂技术的 HR/猎头 一眼理解这个人是做什么的、为什么值得联系。
生成规则:
| 用户说 | OpenClaw 行为 |
|---|---|
"1, 3, 5" 或 "选 1 3 5" | 标记为 selected,调 candidate_manager.py --action batch-update |
"pass 2, 4" 或 "跳过 2 4" | 标记为 passed |
"继续" / "下一批" / "搜更多" / "继续搜索" / "更多" | 统一逻辑:见下方「继续/搜更多的判断规则」 |
"修改要求" 或 "换个条件" | 回到 Step 0 重新解析 JD |
"就这些了" 或 "完成" | 进入 Step 2 二次确认 |
"看看 zhangsan" | 调 candidate_manager.py --action get-candidate --github-id zhangsan 展示详情 |
⚠️「继续/搜更多」的判断规则(重要!不要让用户区分这两个操作):
当用户说"继续"、"搜更多"、"下一批"、"继续搜索"或任何表达"想看更多人"的意思时,OpenClaw 按以下优先级自动判断:
1. 如果还有未展示的已有结果 → 直接翻页展示下一批 15 人(不调 API)
2. 如果已有结果全部展示完了 → 调 github_search.py --resume SEARCH_ID 搜索新页面
3. 如果搜索已耗尽(status=exhausted/zero_yield)→ 告知用户无更多结果 + 给出优化建议用户不需要知道"翻页"和"搜索"的区别。 这是内部实现细节,OpenClaw 自动判断。
翻页终止规则:
cd ~/.openclaw/workspace/skills/ai-talent-hunter
# 批量更新状态
python scripts/candidate_manager.py --action batch-update \
--search-id UUID --selected "user1,user2" --passed "user3"
# 查看某人详细信息
python scripts/candidate_manager.py --action get-candidate --github-id "zhangsan"数据持久化:
~/.openclaw/workspace/skills/ai-talent-hunter/data/candidates.jsonl目标:用非技术语言展示所有 selected 候选人的完整信息,让 HR/猎头/高管最终确认后再生成触达话术。
⚠️ 核心原则:用户可能不懂技术、无法访问 GitHub。所有信息必须翻译为商业语言。
操作:
cd ~/.openclaw/workspace/skills/ai-talent-hunter
python scripts/candidate_manager.py --action get-selected --search-id UUIDOpenClaw 按以下结构为每位 selected 候选人生成展示内容:
1. 一句话推荐(⚠️ 由 OpenClaw 生成)
2. 基本信息(表格)
| 项目 | 信息 |
|---|---|
| 真实姓名 | 从 name 字段取 |
| 当前公司 | 从 company 字段取,如果是知名公司则括号补充公司简介 |
| 所在城市 | 翻译为中文 |
| GitHub 活跃年限 | 从 dev_years 字段取,注意措辞为"GitHub 活跃 N 年"而非"工作经验 N 年" |
| 活跃状态 | 🟢/🟡/🔵/⚪ |
| 求职状态 | isHireable=true → "✅ 已标记接受新机会" / false → 不显示 |
3. 职业亮点(⚠️ 由 OpenClaw 生成,列表形式)
4. 与岗位匹配度
5. 联系方式与建议(表格)
| 渠道 | 信息 | 建议 |
|---|---|---|
| 📧 邮箱 | 具体邮箱地址 | ✅ 推荐,最直接 |
| 🌐 个人网站 | 具体网址 | 可参考了解更多 |
| 具体链接 | 可作为备选 | |
| 🔗 其他社交 | 具体链接 | — |
6. 风险提示
| 用户说 | OpenClaw 行为 |
|---|---|
| "确认全部" | 进入 Step 3(为所有 selected 生成触达话术) |
| "去掉 2 号" 或 "取消 XX" | 将其从 selected 改为 passed,不再生成话术 |
| "补人" 或 "回去再选" | 回到 Step 1.5 继续筛选 |
目标:为每位确认的候选人生成个性化触达消息。
前置条件:
⚠️ 前置信息收集(如果缺失,OpenClaw 必须先询问用户):
| 信息 | 为什么需要 | 示例 |
|---|---|---|
| 发送人身份 | 决定语气(CTO≠HR≠CEO) | CTO / HR / 猎头 / CEO / 合伙人 |
| 发送人姓名 | 署名 | "李明" |
| 公司名称 | 让对方知道谁在联系 | "字节跳动" / "一家 A 轮 AI 创业公司" |
| 触达目的 | 决定话术方向 | 全职招聘 / 技术顾问 / 开源合作 |
| 触达渠道 | 决定长度和格式 | 邮件 / Twitter DM / 微信 |
操作:
prompts/pitch_writer_prompt.md核心规则(详见 prompts/pitch_writer_prompt.md):
✅ 允许的数据源:
❌ 严禁的行为:
🔒 Human-in-the-Loop 强制要求:
原因:GitHub Token 权限不足或已过期。
解决方案:
# 重新生成 Token(需要 read:user 和 read:org 权限)
export GITHUB_TOKEN=ghp_新的tokenread:user 和 read:org 权限)GitHub Token 获取:
read:user 和 read:org 权限.env 文件(不要提交到 git!)环境变量配置:
# 创建 .env 文件(已在 .gitignore 中,不会被上传)
echo "GITHUB_TOKEN=your_token_here" > .env
# 或者临时使用(不持久化)
export GITHUB_TOKEN=ghp_your_token_here🔒 安全红线:
.env 文件(已加入 .gitignore)ghp_xxxxx 占位符# Step 0: JD 解析(在 OpenClaw 中执行)
# 输入:"找 5 个深圳的 RocksDB C++ 工程师,要求最近 1 年内有活跃贡献"
# 输出:search_params.json
# Step 1: 搜索
cd ~/.openclaw/workspace/skills/ai-talent-hunter
export GITHUB_TOKEN=ghp_xxxxx
python scripts/github_search.py \
--queries "language:c++ rocksdb pushed:>2025-01-01" \
--jd-keywords "rocksdb,lsm-tree,storage" \
--jd-language "C++" \
--location "shenzhen" \
--target 20 \
-o results.json
# Step 1.5: 候选人展示与筛选(OpenClaw 展示,用户选择)
# 用户:"1, 3, 5" → selected,"pass 2, 4" → passed
python scripts/candidate_manager.py --action batch-update \
--search-id "uuid" --selected "zhangsan,wangwu" --passed "lisi"
# Step 2: 二次确认(展示 selected 候选人完整信息)
python scripts/candidate_manager.py --action get-selected --search-id "uuid"
# Step 3: 生成触达话术(只针对 selected 的人)
# OpenClaw 读取 prompts/pitch_writer_prompt.md 生成个性化触达消息© 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 9 other files (scripts, references) in skills/ai-talent-hunter of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
AI Talent Hunter 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 |
|---|---|---|---|---|---|---|
| AI Talent Hunter this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~3.9k | Automated safety check: Notes | MIT | |
| TriageTalAter/annyang | 6.8k | — | ~810 | Automated safety check: Notes | MIT | |
| Esmfold2JimLiu/science-skills | 228 | 4 repos | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| Create Simple Promptpnp/copilot-prompts | 893 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Issue Workflow Guardrailkxn/codex-remote-feishu | 329 | — | ~1.3k | Automated safety check: Pass | None | |
| Gptqmodel Tokenizer NormalizationModelCloud/GPTQModel | 1.3k | — | ~1.1k | Automated safety check: Pass | Custom licence |
TalAter/annyang
Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang.
JimLiu/science-skills
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.
pnp/copilot-prompts
This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…
kxn/codex-remote-feishu
A skill your agent uses when handling a GitHub issue in this repository: raw issue shaping, implementability reassessment, fast/full classification, parent/child orchestration, execution snapshots…
ModelCloud/GPTQModel
Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.
splunk/token-meter
A skill your agent uses when a Token Meter task will produce Slack, GitHub, release, contributor, or user-facing status communication.
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
Categories
从 GitHub 找到最匹配的技术人才,生成个性化触达话术。适用于招聘工程师、寻找技术合伙人、猎头交付候选人等场景. An agent skill from LeoYeAI/openclaw-master-skills. AI Talent Hunter is an agent skill from LeoYeAI/openclaw-master-skills.
AI Talent Hunter fits situations like: AI & LLM Engineering work in your project.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill ai-talent-hunter -a claude-code`. Or copy the skill folder (skills/ai-talent-hunter in LeoYeAI/openclaw-master-skills) into .claude/skills/ai-talent-hunter in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill ai-talent-hunter -a codex`. Or copy the skill folder (skills/ai-talent-hunter in LeoYeAI/openclaw-master-skills) into .agents/skills/ai-talent-hunter 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 ai-talent-hunter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-talent-hunter, .gemini/skills/ai-talent-hunter, .github/skills/ai-talent-hunter and .opencode/skills/ai-talent-hunter in your project.
Going by SKILL.md and its folder, AI Talent Hunter needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named GITHUB_TOKEN. Our summary lists: Python 3; A credential in GITHUB_TOKEN.
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
AI Talent Hunter is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with AI Talent Hunter: Triage (TalAter/annyang, 6.8k stars), Esmfold2 (JimLiu/science-skills, 228 stars), Create Simple Prompt (pnp/copilot-prompts, 893 stars) and Issue Workflow Guardrail (kxn/codex-remote-feishu, 329 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.