Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
work
Execute work plans efficiently while maintaining quality and shipping complete features. Use when implementing a plan, working through a todo list, or executing a specification. Focuses on finishing features, not perfecting process.
majiayu000/claude-skill-registry 163
-
changeset
Use when writing changesets for releases
majiayu000/claude-skill-registry 163
-
audit
Run comprehensive codebase audit for gaps, deprecated code, TODOs, FIXMEs, architectural anti-patterns, type issues, and code smells. Use when user asks to audit code, find issues, check code quality, or identify architectural problems.
majiayu000/claude-skill-registry 163
-
bloc-advanced-lapc506-flutter-agentic-boil
majiayu000/claude-skill-registry 163
-
layton
Personal AI assistant for attention management. Use when user asks about focus, briefings, tracking items, or needs orientation across integrated skills.
majiayu000/claude-skill-registry 163
-
FinOps AI Expert
Cost optimization for AI workloads - model selection, GPU sizing, commitment strategies, and multi-cloud cost management
majiayu000/claude-skill-registry 163
-
code-quality-auditor
Proactively audits developer work to ensure completeness and production-readiness. This skill should be used when reviewing code changes, validating task completion, or verifying that work meets industry standards—catching incomplete implementations, deferred features, hardcoded values, missing tests, and shortcuts before code goes to production.
majiayu000/claude-skill-registry 163
-
dbt-transformations
ALWAYS USE when working with dbt models, SQL transformations, tests, snapshots, or macros. Use IMMEDIATELY when editing dbt_project.yml, profiles.yml, or creating SQL models. MUST be loaded before any transform-layer work. Enforces dbt owns SQL principle - never parse, validate, or transform SQL in Python.
majiayu000/claude-skill-registry 163
-
rust-engineer
Rust specialist with expertise in async programming, ownership patterns, FFI, and WebAssembly development
majiayu000/claude-skill-registry 163
-
using-system-archaeologist
Use when analyzing existing codebases to generate architecture documentation - coordinates subagent-driven exploration with mandatory workspace structure, validation gates, and pressure-resistant workflows
majiayu000/claude-skill-registry 163
-
videos
majiayu000/claude-skill-registry 163
-
analytics-metrics-kpi
Master metrics definition, KPI tracking, dashboarding, A/B testing, and data-driven decision making. Use data to guide product decisions.
majiayu000/claude-skill-registry 163
-
dag-performance-profiler
Profiles DAG execution performance including latency, token usage, cost, and resource consumption. Identifies bottlenecks and optimization opportunities. Activate on 'performance profile', 'execution metrics', 'latency analysis', 'token usage', 'cost analysis'. NOT for execution tracing (use dag-execution-tracer) or failure analysis (use dag-failure-analyzer).
majiayu000/claude-skill-registry 163
-
web-validation
Comprehensive web page validation with authentication, screenshot capture, mobile testing, and enhanced error detection
majiayu000/claude-skill-registry 163
-
parallel-run
Orchestrate parallel agent execution with git worktrees
majiayu000/claude-skill-registry 163
-
comp-mechanics
Use to assemble rate tables, accelerator logic, and plan governance templates.
majiayu000/claude-skill-registry 163
-
qiskit
IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.
majiayu000/claude-skill-registry 163
-
supabase-patterns
Patterns for Supabase integration in Battery. Use this skill when working with database schemas, row-level security policies, edge functions, or Supabase client usage in Next.js.
majiayu000/claude-skill-registry 163
-
episode-start
Start a new learning episode in the self-learning memory system with proper context. Use this skill when beginning a new task that should be tracked for learning from execution patterns.
majiayu000/claude-skill-registry 163
-
requirements-analyst
Copilot agent that assists with requirements analysis, user story creation, specification definition, and acceptance criteria definition
Trigger terms: requirements, EARS format, user stories, functional requirements, non-functional requirements, SRS, requirement analysis, specification, acceptance criteria, requirement validation
Use when: User requests involve requirements analyst tasks.
majiayu000/claude-skill-registry 163
-
Ethical Hacking Methodology
This skill should be used when the user asks to "learn ethical hacking", "understand penetration testing lifecycle", "perform reconnaissance", "conduct security scanning", "exploit vulnerabilities", or "write penetration test reports". It provides comprehensive ethical hacking methodology and techniques.
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-deployment-logs
View logs for a specific deployment. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
nextjs-deployment-josiahsiegel-claude-plugin-market-2
majiayu000/claude-skill-registry 163
-
apollo-core-workflow-a
Implement Apollo.io lead search and enrichment workflow.
Use when building lead generation features, searching for contacts,
or enriching prospect data from Apollo.
Trigger with phrases like "apollo lead search", "search apollo contacts",
"find leads in apollo", "apollo people search", "enrich contacts apollo".
majiayu000/claude-skill-registry 163