Loading...
Loading...
Found 4,004 Skills
Before ANY destructive, irreversible, or high-impact action, pause and surface a clear checklist of what's about to happen. This includes: file deletions, database changes, production deployments, mass updates, permission changes, or anything that can't easily be undone. Require explicit confirmation before proceeding. Never auto-execute dangerous operations.
Agent skill for release-manager - invoke with $agent-release-manager
Detect accidentally committed secrets, credentials, and sensitive information in code.
Kubernetes container orchestration with Helm, operators, and service mesh. Use for cluster management.
Analyze Windows Registry hives for forensic investigation. Use when investigating malware persistence, user activity, system configuration changes, or evidence of program execution. Supports offline registry analysis from disk images or extracted hives.
Use after completing implementation - create pull request with complete documentation, proper labels, linked issues, and verification summary
Complete spec workflow - generates Run ID, creates isolated worktree, brainstorms requirements, writes lean spec documents that reference constitutions, validates architecture quality, and reports completion
Domain/DNS ops across Cloudflare, DNSimple, Namecheap for Peter. Use for onboarding zones to Cloudflare, flipping nameservers, setting redirects (Page Rules/Rulesets/Workers), updating redirect-worker mappings, and verifying DNS/HTTP. Source of truth: ~/Projects/manager.
Reset the working directory for the next task by ensuring no uncommitted changes exist, then switching to the main branch and pulling latest.
Rummage through code with curious precision, inspecting every corner for security risks and cleaning up what doesn't belong. Use when auditing security, finding secrets, removing dead code, or sanitizing before deployment.
Push commits and create/update pull request
Use when the user wants to verify their understanding of a branch's code changes by being quizzed on runtime behavior, assumptions, failure points, and edge cases instead of just reading diffs