agent-skills (by addyosmani, MIT, ~27.5k stars) is a skills package for engineering agents: 24 engineering skills (SKILL.md, each a repeatable engineering workflow, e.g. brainstorming / planning / systematic-debugging / code-review) + 8 lifecycle slash commands. Skills activate automatically based on the task description: e.g. when the task mentions frontend, it loads frontend-command-and-interface-design; when changing UI, it loads frontend-ui-engineering.

In one sentence: give an Agent "a senior engineer's muscle memory".

Your AI writes code fast, but often "just starts writing": no spec, no plan, no tests after the change. You want it to follow an engineering workflow like a senior engineer — think through the requirements first, split into small tasks, implement step by step, and only merge after tests pass. Agent Skills is an engineering-workflow skill package you install into your AI: 24 skills + 8 slash commands covering define → plan → build → test → review → ship.

This one-liner tries the official skills CLI first and falls back to the codeload mirror manual copy when GitHub is too slow:

# Source: Trove detailed guide · verified 2026-08-28
npx -y skills add addyosmani/agent-skills --yes --global 2>/dev/null || (curl -sL https://codeload.github.com/addyosmani/agent-skills/tar.gz/refs/tags/0.6.7 | tar xz && cp -r agent-skills-0.6.7/skills ~/.claude/skills/agent-skills)

Expected output: skill directory in place (~/.claude/skills/agent-skills/ has subdirectories per skill, 24 in total)

1. ls ~/.claude/skills/agent-skills | wc -l outputs 24;
2. Open a fresh Claude Code session and type /spec — the AI responds with the spec workflow instead of writing code directly;
3. Skill references appear in relevant task hints (auto-activation works).

By default an AI only executes "the one sentence you give it" — it won't walk an engineering workflow on its own. Agent Skills gives the AI a "work manual": each skill is a SKILL.md directory (24 in total), and Agents like Claude Code auto-load the matching skill by task topic, or you can trigger the whole flow manually with slash commands. It doesn't modify the AI itself — it only puts files into the skill directory (~/.claude/skills/agent-skills/ or the project .claude/skills/). No CLI binary, no background process.

Measured command = skills CLI (vercel-labs/skills, npx skills add addyosmani/agent-skills; GitHub clone slow/timeout in this environment, so the codeload tarball took 1.9s to fetch 24 SKILL.md + 8 slash commands, structure confirmed); official quick path = npx skills add addyosmani/agent-skills (installs to 70+ agents, including Claude Code/Cursor/Codex/Copilot); manual path = copy the skills/ directory; write surface = skill directory (~/.claude/skills or project .claude/skills, same surface as superpowers)

Step 1: Install the skill package (manual copy preferred on mainland networks)

Why two methods: Method A is the officially recommended skills CLI (npx -y skills add ...), which supports 70+ agents and puts things in the right place automatically; but it clones from GitHub and often stalls on mainland networks. Method B downloads the tarball from codeload directly — verified reachable in this marketplace, plain directory copy, no Node needed.

Method B (stable on mainland, verified in this marketplace):

# Source: Trove detailed guide · verified 2026-08-28
curl -sL https://codeload.github.com/addyosmani/agent-skills/tar.gz/refs/tags/0.6.7 | tar xz
cp -r agent-skills-0.6.7/skills ~/.claude/skills/agent-skills

Expected output: no errors; 24 skill directories appear under ~/.claude/skills/agent-skills/

After install, confirm:

# Source: Trove detailed guide · verified 2026-08-28
ls ~/.claude/skills/agent-skills | wc -l

Expected output: 24

Stuck? How to recover:

• codeload download failed → retry on another network (campus net/proxy switch); or use Method A skills CLI (npx -y skills add addyosmani/agent-skills --yes --global);
• skills not active → confirm they were copied to the skill directory the Agent actually reads (Claude Code: ~/.claude/skills/; other Agents have their own conventions).

Step 2: Trigger the workflow with slash commands

Why slash commands: they are the lifecycle entry points — /spec requirements → spec (Spec before code), /plan spec → atomic tasks, /build incremental implementation (/build auto plans + implements in one shot), /test tests as evidence, /review review before merge, /ship ship.

# Source: Trove detailed guide · verified 2026-08-28
/spec    # 需求→规格（Spec before code）
/plan    # 规格→原子任务
/build   # 增量实现（/build auto 一键规划+实现）
/test    # 测试即证据
/review  # 合并前审查
/ship    # 上线

Expected output: corresponding workflow activated (related skills auto-loaded)

After install, confirm:

• the slash command invokes the corresponding workflow (skill hints appear in the Agent context).

Stuck? How to recover:

• command not found → confirm the skill directory is in place (Step 1); Claude Code needs a session restart for the skill directory to take effect.

Step 3: Skills auto-activate (no manual command needed)

Why: designing an API auto-activates api-and-interface-design; changing UI activates frontend-ui-engineering, etc. This is the "auto-assemble by task" mechanism — skills don't depend on manual triggers.

# Source: Trove detailed guide · verified 2026-08-28
# 设计 API 时自动激活 api-and-interface-design；改 UI 时激活 frontend-ui-engineering 等

Expected output: the agent context auto-injects the corresponding skill

After install, confirm:

• skill references appear in relevant task hints.

Stuck? How to recover:

• not auto-activated → check whether the skill directory naming and SKILL.md format match the Agent's conventions (each Agent differs slightly).

Startup and entry

No startup needed; skills are auto-loaded by the Agent by task topic. Manual entry points are the slash commands (Step 2) and the skill directory itself.

Common operations

Operation 1: Confirm the skill count

# Source: Trove detailed guide · verified 2026-08-28
ls ~/.claude/skills/agent-skills | wc -l

Expected output: 24

Operation 2: Trigger a workflow with slash commands

# Source: Trove detailed guide · verified 2026-08-28
/spec    # 需求→规格（Spec before code）
/plan    # 规格→原子任务
/build   # 增量实现（/build auto 一键规划+实现）
/test    # 测试即证据
/review  # 合并前审查
/ship    # 上线

Expected output: corresponding workflow activated (related skills auto-loaded)

Operation 3: Update to the latest version (re-download and overwrite)

# Source: Trove detailed guide · verified 2026-08-28
curl -sL https://codeload.github.com/addyosmani/agent-skills/tar.gz/refs/tags/0.6.7 | tar xz
cp -r agent-skills-0.6.7/skills ~/.claude/skills/agent-skills

Expected output: no errors; skill directory refreshed (24 skill directories)

Data and directories

• Skill directory: ~/.claude/skills/agent-skills/ (or project .claude/skills/); no config files, no background process.

Same source as the tool-page matrix — 19 pairs total (3 measured compatible / 14 inferred possibly compatible / 2 inferred possibly conflicting); full pairs, states and evidence: Conflict pairs (co-install matrix).

• No standalone handbook yet; for install/uninstall issues first see the agent-executable guide notes

# Source: Trove detailed guide · verified 2026-08-28
rm -rf ~/.claude/skills/agent-skills .claude/skills/agent-skills; npx -y skills remove addyosmani/agent-skills 2>/dev/null || true

note: pure directory copy — deleting the skill directory is zero-residue; if installed via the skills CLI, remove through it as well

# Source: Trove detailed guide · verified 2026-08-28
# rm -rf ~/.claude/skills/agent-skills .claude/skills/agent-skills
# npx -y skills remove addyosmani/agent-skills   (if installed via the skills CLI)
# test ! -d ~/.claude/skills/agent-skills && echo "agent-skills removed: OK"

Expected output: agent-skills removed: OK

Manual checklist (other harnesses):

• project-level .claude/skills/agent-skills if installed there
• other Agents' skill directories if you copied skills manually

• Runtime preflight (needs Node >= 18; or just copy the skill directory manually)
• Official quick path = skills CLI (vercel-labs/skills); GitHub clone is slow in this environment, structure confirmed via codeload tarball
• Each operation = one command block + expected output; slash commands trigger with /command in Claude Code-like environments
• Skill directory removal (per actual install location); slash commands cleaned as needed
• Shared write surface: skills install into ~/.claude/skills or project .claude/skills — same surface as superpowers; when co-installed mind skill-name conflicts (judged possible-conflict in this marketplace)

• Q: Installed but not working? A: confirm the skill directory is in place (ls counts 24); Claude Code needs a session restart; other Agents follow their own skill directory conventions.
• Q: Method A or Method B? A: A is officially recommended (skills CLI, 70+ agent compatible); when GitHub is slow on mainland networks, B (codeload tarball, structure-confirmed in this environment) is more stable.
• Q: Will it overwrite superpowers if installed together? A: different directory names (agent-skills vs superpowers), no overwrite; both coexist under ~/.claude/skills/.
• Q: Where to report problems? A: install/uninstall issues on this marketplace go through the entry feedback channel; project issues go to the author's repository.

• Version: [0.6.7, 0.6.7] locked (collection structure confirmed version).
• Environment: Method A needs Node >= 18 (skills CLI); Method B has no runtime dependency (plain directory copy).
• Network: GitHub clone is slow (verified), codeload tarball is reachable (verified).
• Write surface: ~/.claude/skills/agent-skills/ (same surface as superpowers — plan the directory layout when installing multiple skill packages).

• Verified: local repro log (2026-08-28, codeload tarball structure confirmed + 24 skills in place).
• Not tested: Method A skills CLI install (official recommended path, commands from official docs); slash commands and auto-activation (need a logged-in Claude Code environment).

Third-party tutorials are not individually verified; check against this page and official docs.

• 博客园：40 个 Agent Skills 精选资源（入门教程 + 实用工具 + 必装推荐）——程序员鱼皮 [博客园 · 程序员鱼皮 · 2026-02-12]
  Agent Skills 生态导航——入门教程（鱼皮保姆级视频/吴恩达×官方课程）、安装管理工具（skills CLI 用法 `npx skills add <owner/repo>`、Skill Seeker 文档转技能、everything-claude-code 配置合集）、推荐安装的技能包（planning-with-files 等）
• 官方仓库 README + 实测：skills CLI 安装布局（与 guide 预期输出对照） ⚠ 与实测冲突，以 Trove 实测为准 [官方文档 · agent-skills 官方 · 2026-08-30（guide 收录版本 0.6.7）]
  官方 skills CLI 安装链路 `npx -y skills add addyosmani/agent-skills --yes --global`（guide 方式 A）——装 24 个工程技能（define/plan/build/test/review/ship 全流程）