Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
reflective-reviewer
Self-reflection specialist that analyzes completed work for quality issues, security vulnerabilities, and improvement opportunities. Performs comprehensive code review covering OWASP Top 10, best practices, testing gaps, performance, and technical debt. Activates after task completion to provide constructive feedback and catch issues early before code review. Activates for self-reflection, code review, quality assessment, security review, OWASP check, best practices review, testing gaps, performance review, technical debt, lessons learned, what went well, what could improve, post-task analysis, code quality, reflection.
majiayu000/claude-skill-registry 163
-
Rust
Rust development patterns, project setup, CLI/TUI applications, error handling, and system integration
majiayu000/claude-skill-registry 163
-
debugging-agent
Self-Improving Agent that monitors all other agent skills, analyzes their logs,
detects issues, and proposes improvements.
AUTO-TRIGGERS:
- Every 30 minutes (scheduled)
- When error rate > 5% (any agent)
- When 3+ recurring errors in 24h (same error type)
- When performance degrades > 2x baseline
majiayu000/claude-skill-registry 163
-
unit-test-workflow
Guided multi-phase workflow for designing and generating comprehensive unit tests
majiayu000/claude-skill-registry 163
-
dapr-integration
Integrate Dapr building blocks for event-driven microservices - Pub/Sub, State Management, Secrets, Service Invocation, and Jobs API. Use when implementing event-driven architecture for Phase 5. (project)
majiayu000/claude-skill-registry 163
-
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
majiayu000/claude-skill-registry 163
-
creating-case-studies
Writes compelling customer success stories with measurable results. Use when the user asks about case studies, success stories, customer stories, client wins, testimonials, or proof of results.
majiayu000/claude-skill-registry 163
-
maven-dependency-management
Use when managing Maven dependencies, resolving dependency conflicts, configuring BOMs, or optimizing dependency trees in Java projects.
majiayu000/claude-skill-registry 163
-
causal-tracing
Causal mediation analysis to identify which model components mediate specific behaviors. Use when investigating how information flows through the network and which neurons or layers are causally responsible for outputs.
majiayu000/claude-skill-registry 163
-
GetStorage Patterns
Local storage with GetStorage for preferences, caching, and offline-first patterns
majiayu000/claude-skill-registry 163
-
service-implementation
Implement Effect services as fine-grained capabilities avoiding monolithic designs
majiayu000/claude-skill-registry 163
-
product-roast
Comprehensive product audit skill combining brutal UX/code roasting with behavioral psychology-informed vision crafting. Use when analyzing apps to find bugs, missed opportunities, and transformative improvements. Generates roast reports, vision documents, prioritized roadmaps, GitHub issues, and implementation specs. Works as a guided workshop with interactive questioning.
majiayu000/claude-skill-registry 163
-
hooks-automation
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration
majiayu000/claude-skill-registry 163
-
innozverse-repo-structure
Navigate and understand the innozverse repository structure, file organization, naming conventions, and module boundaries. Use when creating new files, organizing code, or understanding where to add features.
majiayu000/claude-skill-registry 163
-
two-agent-harness
This skill sets up a complete two-agent development system based on the "Effective Harnesses for Long-Running Agents" research. It creates initializer-agent (for project planning) and coding-agent (for incremental implementation), along with enforcement hooks and progress tracking infrastructure. Use when users ask to "set up two-agent system", "install agent harness", "configure Opus delegation", or want to implement the two-agent architecture pattern.
majiayu000/claude-skill-registry 163
-
umbraco-skill-validator
Validate links and references in SKILL.md files using deterministic scripts
majiayu000/claude-skill-registry 163
-
cox-tooling-excellence
Write Go code in the style of Russ Cox, Go tech lead. Emphasizes tooling, module design, correctness, and backward compatibility. Use when designing packages, modules, or tools that others will depend on.
majiayu000/claude-skill-registry 163
-
feature-status
Count features marked as @failing and write to status JSON file. Used to determine when the autonomous coding loop should end.
majiayu000/claude-skill-registry 163
-
gmail
Read and search Gmail emails. Check inbox, search messages, and view email threads.
majiayu000/claude-skill-registry 163
-
dbt-migration-ms-sql-server
Convert Microsoft SQL Server/Azure Synapse T-SQL DDL to dbt models compatible with Snowflake. This skill should be used when converting views, tables, or stored procedures from SQL Server to dbt code, generating schema.yml files with tests and documentation, or migrating T-SQL to follow dbt best practices.
majiayu000/claude-skill-registry 163
-
implementing-compliance
Implement and maintain compliance with SOC 2, HIPAA, PCI-DSS, and GDPR using unified control mapping, policy-as-code enforcement, and automated evidence collection. Use when building systems requiring regulatory compliance, implementing security controls across multiple frameworks, or automating audit preparation.
majiayu000/claude-skill-registry 163
-
google-workspace
Access Google Workspace services including Gmail, Calendar, Docs, Sheets, Slides, Drive, and Chat. Use for email, scheduling, document creation, and file management.
majiayu000/claude-skill-registry 163
-
updateclaudemd
Use when user says "update CLAUDE.md", "refresh the docs", "sync claude config", "optimize project instructions", "clean up CLAUDE.md", or when documentation is stale, verbose, or out of sync with codebase reality.
majiayu000/claude-skill-registry 163
-
task-to-agent-matcher
Matches tasks to appropriate agents by analyzing task requirements and finding agents with matching capabilities. Use when you need to assign tasks to agents or determine which agent should handle a task. Considers task type, requirements, and agent capabilities.
majiayu000/claude-skill-registry 163