Agent Skills
Addy Osmani's curated set of 24 production-grade engineering skills for coding agents (Claude Code, Cursor, Gemini CLI), each a readable SKILL.md encoding a senior-engineer workflow across the dev lifecycle. The value is provenance: a small, inspectable baseline written by a credible source, the model for what a good, vettable skill looks like, not an exhaustive marketplace.
Alternatives
3 workflows use Agent Skills
Vet a SKILL.md before you install it
Treat an agent skill like the untrusted dependency it is: parse its SKILL.md, confirm the frontmatter is well-formed, and surface every executable script it bundles, since the research flagged script-bearing skills as the most dangerous, before you ever let your agent run it.
Verify an agent-skills plugin before you ship or install it
Check that a Claude Code / agentskills.io skills package is structurally valid, every SKILL.md has proper frontmatter and a name matching its folder, and the plugin marketplace manifest parses, so a broken skill never fails to load after you publish it.
agent-qa: validate Agent Skills before LLM-backed QA runs
Run agent-qa's deterministic skill-pack validator before its authoring, result-triage, or debug-fix skills can drive a model-backed web or mobile QA run, so missing metadata, references, or MCP guidance fail in CI first.