Agent Skills Directory for Claude Code & Codex
A browsable index of agent skills from GitHub, with a safety box score and a visual flow for each one. 1052 skills indexed. What is an agent skill? · How safety box scores work · Personal agent prompts
Discover skills
- caveman — Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens".
- add-read-aloud — Use when the user runs /add-read-aloud or wants the app to speak text with Grok text-to-speech: read-aloud button on assistant replies, auto-speak, TTS.
- emails — When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program.
- pr-improver — Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean.
- executing-plans — Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution.
- ui-uitk — Unity UI Toolkit expert for Unity 6.0+. Understands, edits, and generates UXML and USS files with flex-based layouts. Use for requests involving .uxml, .uss.
- job-stories — Create job stories using the 'When [situation], I want to [motivation], so I can [outcome]' format with detailed acceptance criteria.
- teach — Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation.
- skills-search — This skill should be used when users want to search, discover, install, or manage Claude Code skills from the CCPM registry.
- chrome-mcp-troubleshooting — Diagnose and fix Claude in Chrome MCP extension connectivity issues.
- pnpm — Node.js package manager with strict dependency resolution. Use when running pnpm specific commands, configuring workspaces via pnpm-workspace.yaml.
- benchmark-models — Cross-model benchmark for gstack skills. (gstack)
Collections
- agentic-actions-auditor (1)
- audit-context-building (1)
- aws-agents (8)
- aws-agents-for-devsecops (13)
- aws-core (24)
- aws-data-analytics (9)
- building-secure-contracts (11)
- burpsuite-project-parser (1)
- c-review (1)
- caveman (6)
- claude-in-chrome-troubleshooting (1)
- claude-seo (31)
- code-improver (3)
- constant-time-analysis (1)
- culture-index (1)
- cursor (94)
- devcontainer-setup (1)
- differential-review (1)
- dimensional-analysis (1)
- do-app-platform (13)
- dwarf-expert (1)
- entry-point-analyzer (1)
- expo (24)
- expo-experiments (1)
- firebase-apk-scanner (1)
- fp-check (1)
- gh-cli (1)
- github-triage (1)
- goal-prompt (1)
- let-fate-decide (1)
- marketingskills (50)
- modern-cpp (1)
- modern-python (1)
- mutation-testing (1)
- open-sourcing (1)
- post-patch-validation (1)
- property-based-testing (1)
- railway (1)
- review-walkthrough (1)
- rust-review (1)
- second-opinion (1)
- semgrep-rule-creator (1)
- semgrep-rule-variant-creator (1)
- sharp-edges (1)
- spec-to-code-compliance (1)
- static-analysis (3)
- stitch-build (5)
- stitch-design (6)
- stitch-utilities (5)
- supply-chain-risk-auditor (1)
- testing-handbook-skills (15)
- trailmark (14)
- variant-analysis (1)
- vulnerability-triage-brocards (1)
- writing-lean-proofs (1)
- yara-authoring (1)
- zeroize-audit (1)