Curated Configs
Curated means we read it, the source is still active, and it is about building software with agents. Start from a starter kit if you want a set that works together. Looking for the long tail? Browse skills.sh.
Workers Best Practices
Cloudflare Workers best practices for production applications
Plan CEO Review
Pressure-test project plans with a founder/CEO mindset, challenging assumptions and finding the 10-star product hiding inside the request.
Brainstorming
Guides agents through collaborative brainstorming to refine ideas into concrete designs and specifications.
Frontend Design
Frontend design and UI/UX development tools
Agents Md
Generate and manage AGENTS.md files
Gh Address Comments
Address review and issue comments on open GitHub PRs via CLI
Ask Questions If Underspecified
Prompt for clarification on ambiguous requirements
Postgres Best Practices
PostgreSQL best practices for Supabase
Composition Patterns
React component composition and reusable patterns
Plan Engineering Review
Review engineering plans like an experienced tech lead, focusing on architecture, data flow, edge cases, and test coverage.
Executing Plans
For when you have a detailed implementation plan and need to execute it methodically.
Mcp Builder
Create MCP servers to integrate external APIs and services
Claude Settings Audit
Audit Claude settings configuration
Gh Fix Ci
Debug and fix failing GitHub Actions PR checks using log inspection
Differential Review
Security-focused diff review with git history analysis
Next Best Practices
Next.js best practices and recommended patterns
QA Testing
Systematic web app testing with full explorations, quick smoke tests, or baseline regression comparisons.
Systematic Debugging
Enforces a structured approach to debugging that prioritizes root cause identification over quick fixes.
Skill Creator
Guide for creating skills that extend Claude's capabilities
Commit
Create commits with best practices
Security Threat Model
Generate repo-specific threat models identifying trust boundaries
Insecure Defaults
Detect insecure default configurations like hardcoded secrets, default credentials, and weak crypto
React Best Practices
React best practices and patterns
Code Review
Catch common PR issues before landing: SQL safety, LLM trust boundaries, race conditions, and more.
Test-Driven Development
Guides development using TDD methodology: write a failing test first, implement just enough code to make it pass, then refactor.
Webapp Testing
Test local web applications using Playwright
Create Pr
Create pull requests
Security Best Practices
Review code for language-specific security vulnerabilities
Modern Python
Modern Python tooling with uv, ruff, ty, and pytest best practices
Web Design Guidelines
Web design guidelines and standards
Ship
Automated release workflow from feature branch to pull request: merge, test, version bump, changelog, and PR creation.
Verification Before Completion
Ensures every claim of completion or success is backed by concrete evidence.
Code Simplifier Agent
An agent prompt that simplifies recently modified code for clarity and maintainability, without changing behavior. Runs after implementation to clean up what was just written.
Code Review
Perform code reviews
Property Based Testing
Property-based testing for multiple languages and smart contracts
Writing Plans
Helps outline implementation details for features and tasks by generating actionable, step-by-step plans.
Feature Development Workflow
A 7-phase workflow for building features with AI agents. Discovery, exploration, clarifying questions, architecture, implementation, review, summary.
Find Bugs
Find and identify bugs in code
Static Analysis
Static analysis toolkit with CodeQL, Semgrep, and SARIF
PR Review with Confidence Scoring
Run multiple specialized review agents in parallel, score every issue 0-100, and only surface the ones that matter. Reduces false positives without missing real bugs.
Iterate Pr
Iterate on pull request feedback
Context Optimization
Apply compaction, masking, and caching strategies
Context Fundamentals
Understand what context is, why it matters, and the anatomy of context in agent systems
Evaluation
Build evaluation frameworks for agent systems
Code Review
Comprehensive PR code review using specialized agents: bug-hunter, security-auditor, code-quality-reviewer, contracts-reviewer, historical-context-reviewer, test-coverage-reviewer
Tool Design
Build tools that agents can use effectively, including architectural reduction patterns
Prompt Engineering
Widely used prompt engineering techniques and patterns, including Anthropic best practices and agent persuasion principles.
Sdd
Spec-driven development workflow that transforms prompts into production-ready implementations through structured planning, architecture design, and LLM-as-a-Judge based quality gates.