Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 696 files from 2 113 authors, of which 68 413 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Diagnose machine learning training failures including loss divergence, mode collapse, gradient issues, architecture problems, and optimization failures. This skill spawns a specialist ML debugging ...
Configure Claude Code sandbox network isolation with trusted domains, custom access policies, and environment variables
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.
Loop 2 of the Three-Loop Integrated Development System. META-SKILL that dynamically compiles Loop 1 plans into agent+skill execution graphs. Queen Coordinator selects optimal agents from 86-agent registry and assigns skills (when available) or custom instructions. 9-step swarm with theater detection and reality validation. Receives plans from research-driven-planning, feeds to cicd-intelligent-recovery. Use for adaptive, theater-free implementation.
Enterprise-grade PowerPoint deck generation system using evidence-based prompting techniques, workflow enforcement, and constraint-based design. Use when creating professional presentations (board decks, reports, analyses) requiring consistent visual quality, accessibility compliance, and integration of complex data from multiple sources. Implements html2pptx workflow with spatial layout optimization, validation gates, and multi-chat architecture for 30+ slide decks.
Comprehensive pre-deployment validation ensuring code is production-ready. Runs complete audit pipeline, performance benchmarks, security scan, documentation check, and generates deployment checklist.
Comprehensive framework for analyzing, creating, and refining prompts for AI systems. Use when creating prompts for Claude, ChatGPT, or other language models, improving existing prompts, or applying evidence-based prompt engineering techniques. Applies structural optimization, self-consistency patterns, and anti-pattern detection to transform prompts into highly effective versions.
Lightning-fast quality check using parallel command execution. Runs theater detection, linting, security scan, and basic tests in parallel for instant feedback on code quality.
Implement ReasoningBank adaptive learning with AgentDB for trajectory tracking, verdict judgment, memory distillation, and pattern recognition to build self-learning agents that improve decision-making through experience.
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
Loop 1 of the Three-Loop Integrated Development System. Research-driven requirements analysis with iterative risk mitigation through 5x pre-mortem cycles using multi-agent consensus. Feeds validated, risk-mitigated plans to parallel-swarm-implementation. Use when starting new features or projects requiring comprehensive planning with <3% failure confidence and evidence-based technology selection.
Configure Claude Code sandbox security with file system and network isolation boundaries
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
Creates Claude Code skills where each skill is tied to a specialist agent optimized with evidence-based prompting techniques. Use this skill when users need to create reusable skills that leverage specialized agents for consistent high-quality performance. The skill ensures that each created skill spawns an appropriately crafted agent that communicates effectively with the parent Claude Code instance using best practices.
Advanced skill creation system for Claude Code that combines deep intent analysis, evidence-based prompting principles, and systematic skill engineering. Use when creating new skills or refining existing skills to ensure they are well-structured, follow best practices, and incorporate sophisticated prompt engineering techniques. This skill transforms skill creation from template filling into a strategic design process.
Creates ergonomic slash commands (/command) that provide fast, unambiguous access to micro-skills, cascades, and agents. Enhanced with auto-discovery, intelligent routing, parameter validation, and command chaining. Generates comprehensive command catalogs for all installed skills with multi-model integration.
Intelligent bug fixing workflow combining root cause analysis, multi-model reasoning, Codex auto-fix, and comprehensive testing. Uses RCA agent, Codex iteration, and validation to systematically fix bugs.
Complete REST API development workflow coordinating backend, database, testing, documentation, and DevOps agents. 2-week timeline with TDD approach.
Comprehensive code review workflow coordinating quality, security, performance, and documentation reviewers. 4-hour timeline for thorough multi-agent review.
Complete product launch workflow coordinating 15+ specialist agents across research, development, marketing, sales, and operations. Uses sequential and parallel orchestration for 10-week launch timeline.
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration
Audits code against CI/CD style rules, quality guidelines, and best practices, then rewrites code to meet standards without breaking functionality. Use this skill after functionality validation to ensure code is not just correct but also maintainable, readable, and production-ready. The skill applies linting rules, enforces naming conventions, improves code organization, and refactors for clarity while preserving all behavioral correctness verified by functionality audits.
Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.
Performs comprehensive audits to detect placeholder code, mock data, TODO markers, and incomplete implementations in codebases. Use this skill when you need to find all instances of "theater" in code such as hardcoded mock responses, stub functions, commented-out production logic, or fake data that needs to be replaced with real implementations. The skill systematically identifies these instances, reads their full context, and completes them with production-quality code.
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
Guide users on when to use Claude Code Web vs CLI and seamlessly teleport sessions between environments
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms
Analyze skill library to identify coverage gaps, redundant overlaps, optimization opportunities, and provide recommendations for skill portfolio improvement
Advanced intent interpretation system using cognitive science principles and probabilistic intent mapping
Code style and conventions audit with auto-fix capabilities for comprehensive style enforcement
Comprehensive security auditing across static analysis, dynamic testing, dependency vulnerabilities, secrets detection, and OWASP compliance
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management. Coordinates cicd-engineer, workflow-automation, tester, and security-auditor agents through mesh topology to create, optimize, and maintain GitHub Actions workflows. Handles workflow generation, performance optimization, security hardening, matrix testing strategies, and workflow debugging. Use when building CI/CD pipelines, optimizing existing workflows, or establishing automation standards.
Bridge web interfaces with CLI workflows for seamless bidirectional integration
| Use when building a production-ready REST API from requirements through deployment. Orchestrates 8-12 specialist agents across 5 phases using Test-Driven Development methodology. Covers planning, architecture, TDD implementation, comprehensive testing, documentation, and blue-green deployment over a 2-week timeline with emphasis on quality and reliability.
Chain agent outputs as inputs in sequential or parallel pipelines for data flow orchestration
Configure Claude Code sandbox security with file system and network isolation boundaries. Ensures safe code execution with proper access controls and resource limits.
Enterprise-grade PowerPoint deck generation using evidence-based prompting, workflow enforcement, constraint-based design
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization
Create ergonomic slash commands for fast access to micro-skills with auto-discovery and parameter validation
Intelligent debugging workflow that systematically identifies symptoms, performs root cause analysis, generates fixes with explanations, validates solutions, and prevents regressions through compre...
Debug ML training issues and optimize performance including loss divergence, overfitting, and slow convergence
Deploy cloud-based AI agent swarms with event-driven workflow automation using Flow Nexus platform. Supports hierarchical, mesh, ring, and star topologies with E2B sandbox distribution.
| Detects non-functional "theater" code that appears complete but doesn't actually work. Use this skill to identify code that looks correct in static analysis but fails during execution, preventing fake implementations from reaching production. Scans for suspicious patterns, validates actual functionality, and reports findings with recommendations.
Specialized ML model development, training, and deployment workflow
Automated comprehensive code documentation generation with API docs, README files, inline comments, and architecture diagrams
Use Claude Code's AskUserQuestion tool to gather comprehensive requirements through structured multi-select questions.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning. Coordinates planner, issue-tracker, and project-board-sync agents to automate issue triage, sprint planning, milestone tracking, and project board updates. Integrates with GitHub Projects v2 API for advanced automation, custom fields, and workflow orchestration. Use when managing development projects, coordinating team workflows, or automating project management tasks.
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration. Coordinates repo-architect, code-analyzer, and coordinator agents across multiple repositories to maintain consistency, propagate changes, manage dependencies, and ensure architectural alignment. Handles monorepo-to-multi-repo migrations, cross-repo refactoring, and synchronized releases. Use when managing microservices, multi-package ecosystems, or coordinating changes across related repositories.
Proactive token budget management tool for assessing usage, analyzing task complexity, generating chunking strategies, and creating execution plans that stay within budget limits
Comprehensive dependency mapping, analysis, and visualization tool for software projects
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement
Comprehensive framework for analyzing, creating, and refining prompts for AI systems using evidence-based techniques
Active diagnostic tool for analyzing prompt quality, detecting anti-patterns, identifying token waste, and providing optimization recommendations
Complex multi-agent swarm orchestration with task decomposition, distributed execution, and result synthesis
Comprehensive performance profiling, bottleneck detection, and optimization system
| Use when launching a new product end-to-end from market research through post-launch monitoring. Orchestrates 15+ specialist agents across 5 phases in a 10-week coordinated workflow including research, development, marketing, sales preparation, launch execution, and ongoing optimization. Employs hierarchical coordination with parallel execution for efficiency and comprehensive coverage.
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management. Coordinates release-manager, cicd-engineer, tester, and docs-writer agents through hierarchical topology to handle semantic versioning, changelog generation, release notes, deployment validation, and post-release monitoring. Supports multiple release strategies (rolling, blue-green, canary) and automated rollback. Use when creating releases, managing deployments, or coordinating version updates.
Comprehensive PR review with multi-agent swarm specialization for security, performance, style, tests, and documentation
Comprehensive GitHub pull request code review using multi-agent swarm with specialized reviewers for security, performance, style, tests, and documentation. Coordinates security-auditor, perf-analyzer, code-analyzer, tester, and reviewer agents through mesh topology for parallel analysis. Provides detailed feedback with auto-fix suggestions and merge readiness assessment. Use when reviewing PRs, conducting code audits, or ensuring code quality standards before merge.
Claude Skills — questions
Answers built from the skills we actually parsed.