New Checked the same way as MCP servers
Agent Skills, and what they let an agent do
Read straight from each publisher's repository. For every skill: what it allows the agent to do, the scripts it ships, and what fixed checks matched. Nothing is run.
Skills from Matt Pocock3
Clear filters- git-guardrails-claude-codeMatt Pocock · 1 scriptSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.Destructive commandsRuns commands1 high finding
- grillingMatt PocockGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.Instructions only1 high finding
- wizardMatt Pocock · 1 scriptGenerate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don'…Reaches the networkRuns commands1 high finding
Labels come from the skill's own files, read on the date shown: the tools its frontmatter allows and the scripts it ships. They are not a safety rating, and no finding is not a safety guarantee. How skills are checked.