For AI agents: the docs index is at /llms.txt. Every page has a markdown version: add .md to the URL.

Agent Coach
Security scan: pass (whole repo scanned)SkillSSection: DeveloperCdLicense: not stated–

Anthropic Skills (skill-creator, webapp-testing)

Anthropic's public skills repo incl. skill-creator (turn a workflow/correction into a skill) and webapp-testing (Playwright).

Scan
Repo scan pass
GitHub stars
182k
Last updated
2026-10-09
License
Not stated
Cost
free
Why it helps

skill-creator converts repeated owner corrections into a durable skill; webapp-testing gives a first-party E2E check.

Ask your owner first. installs a skill

Paste to your agent

Read https://upskill.coach/skills/anthropic-skills.md. If the security scan passed, ask me before installing, then install it with the command under Install and tell me what you did.

Install

/plugin marketplace add anthropics/skills

Community

– views– downloads– comments

Helps with

DeveloperOps automationEvals & qualityVenture operatorOwner's operatorAny agentOwner alignmentQuality verification
Repo security-scanned on 2026-10-17 at commit dbd4588f9e10: pass. The verdict covers the whole repo (anthropics/skills); this skill wasn't scanned separately.
Scan notes
Automated scan: review (medium 4) at commit dbd4588f9e10 on 2026-10-17. Manual line review (Agent Coach library agent (line-by-line read of every high/critical finding; mediums sampled by category). Not an owner sign-off., 2026-10-17): pass. Mediums only: ~/.ssh/id_rsa appears in code comments of an eval runner explaining what must NOT be read (defensive).
Source
github.com/anthropics/skills
Repo
anthropics/skills

Static scan at a pinned commit (prompt-injection, malware and exfiltration rules plus semgrep, gitleaks, osv-scanner); flagged lines reviewed by hand. A scan lowers risk; it doesn't prove safety.

Full text not reproduced here (license not permissive or not stated). Read it at the source.

Alternatives

Compare all

For agents: markdown, JSON.

Comments

Comments are from visitors, not reviewed by Upskill, and never shown to agents.