using-agent-skills
An agent skill by addyosmani, from addyosmani/agent-skills. Tags: developer-tools, documents.
What it does
Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all other skills are discovered and invoked.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add addyosmani/agent-skills --skill using-agent-skillsOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/addyosmani/agent-skills
cp -r agent-skills/skills/using-agent-skills ~/.claude/skills/using-agent-skillsSafety box score
Grade A, minimal risk: 4 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This is a markdown-only meta-skill that routes the agent to other workflow skills and enforces general working rules. It does not run commands, touch files, or access secrets directly, but it can broaden the agent’s behavior by steering it into downstream skills such as `shipping-and-launch` and `ci-cd-and-automation`.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shell commands, scripts, code evaluation, or native executables appear in `SKILL.md`; it is workflow guidance only. |
| Network access | 0 (none) | The file does not download from or send data to any remote host; it only names other local skills. |
| Filesystem reach | 0 (none) | It does not read, write, or delete files itself; the only path reference is `../../references/definition-of-done.md` as a document link. |
| Secrets & credentials | 0 (none) | There is no request to access tokens, keys, passwords, `.env` files, or browser/CLI sessions. |
| Privilege & persistence | 0 (none) | The skill does not request sudo, global installs, services, shell startup edits, or OS/git setting changes. |
| Instruction hijack surface | 0 (none) | The strong wording is normal workflow control (for example, `STOP`, `Do NOT`, `Skills are workflows, not suggestions`), not hidden or external instruction injection. |
| Irreversible actions | 1 (low) | It is a router that directs the agent through many workflows, including `shipping-and-launch` and `ci-cd-and-automation`, but it does not itself push, deploy, post, or delete. |
| Transparency | 0 (none) | The content is plain readable markdown; there are no binaries, blobs, unpinned installs, or runtime-decoded code. |
Before installing
- Read the downstream skills this router references before using them on a live repo.
- Confirm `../../references/definition-of-done.md` matches your project’s actual acceptance bar.
Rated 2026-10-19 by an automated review of 1 file from the skill's repository.
Source
- Repository
- addyosmani/agent-skills (all skills from this repository)
- Path
- skills/using-agent-skills/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- code-review-and-quality — Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human.
- constraint-driven-development — Establishes a project's quality bar as a written contract and stops agents quietly lowering it.
- context-engineering — Optimizes agent context setup.
- deprecation-and-migration — Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another.
- documentation-and-adrs — Records decisions and documentation.
- doubt-driven-development — Subjects every non-trivial decision to a fresh-context adversarial review before it stands.