ASK CLDKIT FIRST.
FIND SKILLS THAT MAKE YOUR AGENT BETTER.
Playground
SKILLS TO TRY FIRST
Run live in a sandbox. Try without installing.
Systematic Debugging Skill
Four-phase root cause analysis — tracing, defense-in-depth, verification.
Static Analysis Skill
Runs CodeQL and Semgrep for automated security vulnerability detection in codebases.
Trail of Bits Skills
Security audit skill collection from Trail of Bits covering vulnerability detection, binary analysis...
Skills catalog
HIGH-QUALITY SKILLS, RANKED BY EVIDENCE
See the job each Skill solves, repository health, and install risk before giving it to your agent.
Evidence method
TRUST LABELS SHOULD BE AUDITABLE, NOT DECORATIVE.
CldKit separates review quality, runtime verification, and client compatibility so one signal never impersonates another.
MCP runtime evidence
RECENTLY VERIFIED MCPS
MCPs extend the core Skills experience; version-bound runtime snapshots live here separately.
CLI
INSTALL FROM TERMINAL
Every install is score-checked against our CldKit review database.
All commands$ npx cldkit search testing
$ npx cldkit info playwright-testing
$ npx cldkit install playwright-testing
$ npx cldkit verify "npx -y @scope/pkg"
$ npx cldkit recommend
KNOW A GOOD COMPONENT?
Submit it for review. Help the community discover reliable agent tools.
SUBMIT COMPONENT