SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL
microsoft/apm
Agent Package Manager
怎么装:Install: git clone <org/repo> && cd <repo>
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+0.1%+0.1%
3.9k → 3.9k stars · 2 个快照3.9k → 3.9k stars · 2 snapshots
状态STATUS
持续活跃Active
03 / 它能帮你做什么03 / What it helps you do
04 / 安装04 / Install
$ README 里给出的安装方式。The installation method given in the README.
$ README 里给出的安装方式。The installation method given in the README.
两种装法选一个即可 —— 上面那条给命令行用户,下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
05 / 限制与风险05 / Limits and risk
风险不是警告,是可信度的一部分。以下结论只基于文档静态扫描,我们不会执行项目里的任何代码。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
存在风险Risk found
静态扫描STATIC SCAN
01执行远程脚本Runs a remote scriptreadme
curl -sSL https://aka.ms/apm-unix | sh
02执行 Shell 命令Runs shell commands.agents/skills/autopilot-pr-review-worker/SKILL.md
`subprocess.run` calls on a path that executes per-package or
03执行 Shell 命令Runs shell commandspackages/autopilot/autopilot-pr-review-worker/SKILL.md
`subprocess.run` calls on a path that executes per-package or
这里只做静态扫描:读 README、SKILL.md 和依赖清单,不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
{
"agents": [
{
"agent": "claude-code",
"evidence": "readme: …figuration. GitHub Copilot | Claude Code | Grok Build | Cursor | OpenC…"
},
{
"agent": "windsurf",
"evidence": "readme: …| OpenCode | Codex | Gemini | Windsurf | Kiro **[Documentation](htt…"
},
{
"agent": "vscode",
"evidence": "readme: …command, no configuration -- VS Code and GitHub Copilot read the f…"
},
{
"agent": "opencode",
"evidence": "readme: …Code | Grok Build | Cursor | OpenCode | Codex | Gemini | Windsurf |…"
},
{
"agent": "copilot",
"evidence": "readme: …for AI agent configuration. GitHub Copilot | Claude Code | Grok Build |…"
}
],
"apiKey": "that reads `GITHUB_APM_PAT`, `GITHUB_TOKEN`, `GH_TOKEN`, `ADO_APM_PAT` - Code usin",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 1,
"dev-tools": 2,
"indie-web": 0,
"skill-agent": 7,
"productivity": 3
},
"primary": "skill-agent",
"secondary": "claude-skill"
},
"localRuntime": null,
"skillMdTotal": 54,
"skillMdErrors": [
{
"path": ".agents/skills/docs-grounding-verifier/SKILL.md",
"error": "Nested mappings are not allowed in compact mappings at line 2, column 14:"
},
{
"path": ".apm/skills/docs-grounding-verifier/SKILL.md",
"error": "Nested mappings are not allowed in compact mappings at line 2, column 14:"
}
],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 1,
"media": 0,
"design": 2,
"browser": 0,
"devtool": 2,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "51 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
".agents/skills/apm-spec-guardian/SKILL.md",
".agents/skills/apm-strategy/SKILL.md",
".agents/skills/auth/SKILL.md",
".agents/skills/autopilot-comment/SKILL.md",
".agents/skills/autopilot-issue-delivery-scheduler/SKILL.md",
".agents/skills/autopilot-issue-delivery-worker/SKILL.md",
".agents/skills/autopilot-issue-triage-scheduler/SKILL.md",
".agents/skills/autopilot-issue-triage-worker/SKILL.md",
".agents/skills/autopilot-pr-merge-worker/SKILL.md",
".agents/skills/autopilot-pr-review-scheduler/SKILL.md",
".agents/skills/autopilot-pr-review-worker/SKILL.md",
".agents/skills/autopilot-pr-triage-scheduler/SKILL.md",
".agents/skills/autopilot-pr-triage-worker/SKILL.md",
".agents/skills/cli-logging-ux/SKILL.md",
".agents/skills/cut-release/SKILL.md",
".agents/skills/devx-ux/SKILL.md",
".agents/skills/docs-corpus-audit/SKILL.md",
".agents/skills/docs-grounding-verifier/SKILL.md",
".agents/skills/docs-impact-architect/SKILL.md",
".agents/skills/docs-impact-classifier/SKILL.md",
".agents/skills/docs-impact-localizer/SKILL.md",
".agents/skills/docs-sync/SKILL.md",
".agents/skills/oss-growth/SKILL.md",
".agents/skills/pr-description-skill/SKILL.md",
".agents/skills/python-architecture/SKILL.md",
".agents/skills/supply-chain-security/SKILL.md",
".apm/skills/apm-spec-guardian/SKILL.md",
".apm/skills/apm-strategy/SKILL.md",
".apm/skills/auth/SKILL.md",
".apm/skills/cli-logging-ux/SKILL.md",
".apm/skills/cut-release/SKILL.md",
".apm/skills/devx-ux/SKILL.md",
".apm/skills/docs-corpus-audit/SKILL.md",
".apm/skills/docs-grounding-verifier/SKILL.md",
".apm/skills/docs-impact-architect/SKILL.md",
".apm/skills/docs-impact-classifier/SKILL.md",
".apm/skills/docs-impact-localizer/SKILL.md",
".apm/skills/docs-sync/SKILL.md",
".apm/skills/oss-growth/SKILL.md",
".apm/skills/python-architecture/SKILL.md",
".apm/skills/supply-chain-security/SKILL.md",
"packages/apm-guide/.apm/skills/apm-usage/SKILL.md",
"packages/autopilot/autopilot-comment/SKILL.md",
"packages/autopilot/autopilot-issue-delivery-scheduler/.apm/skills/autopilot-issue-delivery-scheduler/SKILL.md",
"packages/autopilot/autopilot-issue-delivery-worker/.apm/skills/autopilot-issue-delivery-worker/SKILL.md",
"packages/autopilot/autopilot-issue-triage-scheduler/.apm/skills/autopilot-issue-triage-scheduler/SKILL.md",
"packages/autopilot/autopilot-issue-triage-worker/SKILL.md",
"packages/autopilot/autopilot-pr-merge-worker/SKILL.md",
"packages/autopilot/autopilot-pr-review-scheduler/.apm/skills/autopilot-pr-review-scheduler/SKILL.md",
"packages/autopilot/autopilot-pr-review-worker/SKILL.md",
"packages/autopilot/autopilot-pr-triage-scheduler/.apm/skills/autopilot-pr-triage-scheduler/SKILL.md",
"packages/autopilot/autopilot-pr-triage-worker/.apm/skills/autopilot-pr-triage-worker/SKILL.md",
"packages/pr-description-skill/SKILL.md",
"templates/hello-world/SKILL.md"
],
"skillMdFetched": 54
}