Skill 与 AgentSKILLS & AGENTS· CLAUDE-SKILL
yan-labs/yan-skills
让AI助手自动执行SEO、建站和外链任务的技能集合A skill collection for indie developers that combines Google Trends research, backlink building, and browser automation into a single command-line toolkit.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
一句话让电脑把活干完
从调研到上线管好一个项目
安全提交外链并验证效果
自动从网页后台导出数据
一键生成网站全套配图
Research keyword volume and competition with Google Trends.
Submit backlinks to directories and blogs through your own browser.
Generate images for website pages, logos, and social cards.
Run a full project lifecycle from idea to launch and monitoring.
Extract data from behind login pages that have no public interface.
上手GET STARTED
npx skills add yan-labs/yan-skills -g --all选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01执行 Shell 命令Runs shell commandsagent-fleet/skill/SKILL.md
allowed-tools: Bash(fleet-go
02执行 Shell 命令Runs shell commandsagent-fleet/skill/SKILL.md
allowed-tools: Bash(cat
03控制浏览器Controls a browseropencli/SKILL.md
**验收三铁律**:①只用 OpenCLI 驱动真实 Chrome,不用 Playwright、Firefox/Nightly 或沙箱浏览器;②固定验收做成脚本,只输出摘要,截图落盘;③能力缺口必须明说:新扩展支持真实 console/pageerror 捕获与持续 viewpo
The static scan found medium-level risks: the collection can execute shell commands and control your browser via OpenCLI. Review each skill definition before allowing any action.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
09 NOV 202609 NOV 2026
增长GROWTH
+34.9%+34.9%
232 → 313 stars · 13 个快照232 → 313 stars · 13 snapshots
状态STATUS
持续活跃Active
最近一周有96次提交,项目迭代活跃。305 GitHub stars and 116 forks show community interest.
{
"agents": [
{
"agent": "claude-code",
"evidence": "readme: …ub.com/yan-labs),自用打磨,实测可跑。兼容 Claude Code、Codex CLI、Cursor,以及任何读 `SKILL…"
},
{
"agent": "codex",
"evidence": "readme: …abs),自用打磨,实测可跑。兼容 Claude Code、Codex CLI、Cursor,以及任何读 `SKILL.md` 的平台。M…"
}
],
"apiKey": ".env(见 skillsmp/.env.example) SKILLSMP_API_KEY= ``` 大部分都不配也能用:`rankup` 除 `kd` 与 `chat",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 1,
"dev-tools": 1,
"indie-web": 8,
"skill-agent": 10,
"productivity": 1
},
"primary": "skill-agent",
"secondary": "claude-skill"
},
"localRuntime": "用 GitHub Actions workflow。提交前在本地运行与修改相关的校验;数据和引用校验必须通过: ```bash node back",
"skillMdTotal": 11,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 1,
"agent": 0,
"media": 1,
"design": 0,
"browser": 1,
"devtool": 1,
"security": 0,
"marketing": 4,
"productivity": 0
},
"classification": [
{
"signal": "11 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "name contains 'skill'",
"weight": 0.4
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"agent-fleet/skill/SKILL.md",
"autopilot/SKILL.md",
"backlink/SKILL.md",
"blog/SKILL.md",
"cf-cli/SKILL.md",
"codex/SKILL.md",
"imagegen/SKILL.md",
"opencli/SKILL.md",
"rankup/SKILL.md",
"skill-link-check/SKILL.md",
"write/SKILL.md"
],
"skillMdFetched": 11
}