Collection

Best Skills for Autonomous Agents

Skills curated specifically for autonomous agent workflows — agent-friendly metadata, deterministic scripts.

23 skills · ranked by composite score

Curated

Best Skills for Autonomous Agents

Escape generic AI-generated UIs. Forces a bold, distinctive design direction before any code is written.

ReactTailwindDesign
All surfaces

Structured multi-step development. Brainstorm → spec → plan → build → review → merge — TDD baked in.

TDDMulti-agentPlans
Code

1,000+ SaaS integrations as one skill. OAuth lifecycle, scoped credentials, structured actions.

OAuthSaaSAction-taking
All surfaces
Official

Extract, fill, merge. PDF manipulation with bundled scripts so Claude does not waste tokens generating them.

PDFFormsRead-write
All surfaces

Supabase done right. RLS policies, edge functions, realtime, auth — in idiomatic patterns.

PostgresRLSRealtime
Code

Security audits run by a real security firm. CodeQL + Semgrep + audit workflows.

CodeQLSemgrepAudit
Code

Web scraping, search, and browser automation built to be agent-friendly.

ScrapingSearchWeb
All surfaces

Web search + 36 authoritative data sources. SEC, PubMed, ChEMBL, FRED — agent-grade research.

SearchSECPubMed
All surfaces

Review for reuse, quality, efficiency. Catches over-abstraction and dead code before merge.

ReviewRefactorDRY
Code

Always-current Claude API reference and SDK docs. Bundled with Claude Code.

APISDKDocs
Code

20 SEO + GEO skills in one bundle. Keyword research, audits, rank tracking, AI search optimization.

SEOGEOContent
Code
Community

TDD with red/green/refactor as a concrete TypeScript walkthrough.

TDDTypeScript
Code

Dockerfiles done right. Multi-stage, cache-friendly, distroless, hardened.

DockerContainersSecurity
Code

GitHub Actions workflows with matrix, reusable jobs, OIDC, secrets done right.

GitHub ActionsCI/CDYAML
Code

TypeScript strict mode by default. Discriminated unions, branded types, exhaustive switches.

TypeScriptTypesStrict
Code

Structured PR reviews with severity-tagged findings — bugs, security, perf, style.

ReviewSecurityPR
Code

Terraform expertise on tap. State inspection, module validators, safety-first IaC.

TerraformIaCAWS
Code

Deterministic web control. ref-based clicks/fills, no flaky selectors, parallel sessions.

BrowserAutomationAction-taking
Code
Verified

Real exploits, no false positives. 96.15% exploit success across 50+ vuln types.

PentestExploitationAction-taking
Code

Multi-agent orchestration. Spawn parallel subagents and merge their outputs reliably.

Multi-agentSubagentsParallel
Code