Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
subagent-batching
Patterns for launching and managing parallel subagents efficiently.
majiayu000/claude-skill-registry 163
-
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
majiayu000/claude-skill-registry 163
-
spec-driven-release
Orchestrates production releases through spec-driven deployment workflow with structural anti-skip enforcement. Implements 8 phases covering setup, build, validation, staging, production deployment, post-deployment validation, documentation, and monitoring using the Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias through lean orchestration, fresh-context subagent delegation, and binary CLI gate enforcement. Supports multiple deployment strategies (blue-green, canary, rolling, recreate) and environments (staging, production). Use when deploying QA-approved stories. Always use this skill when the user runs /release.
majiayu000/claude-skill-registry 163
-
rebuttal
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.
majiayu000/claude-skill-registry 163
-
orchardcore-users-roles
Skill for managing users, roles, and permissions in Orchard Core. Covers user registration, role creation, permission definitions, custom user settings, and authentication configuration.
majiayu000/claude-skill-registry 163
-
localsetup-pr-reviewer
Automated GitHub PR code review with diff analysis, lint integration, and structured reports. Use when reviewing pull requests, checking for security issues, error handling gaps, test coverage, or code style problems. Supports Go, Python, and JavaScript/TypeScript. Requires gh CLI authenticated with repo access.
majiayu000/claude-skill-registry 163
-
performing-dll-hijacking
majiayu000/claude-skill-registry 163
-
sveltekit-svelte5-tailwind-skill
Comprehensive integration skill for building sites with SvelteKit 2, Svelte 5, and Tailwind CSS v4
majiayu000/claude-skill-registry 163
-
canine-medicine
Canine-specific clinical medicine covering breed predispositions, common disease presentations, normal physiologic parameters, and species-specific diagnostic and treatment approaches for dogs.
majiayu000/claude-skill-registry 163
-
github-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration
majiayu000/claude-skill-registry 163
-
pdf
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
majiayu000/claude-skill-registry 163
-
game-audio
Game audio principles. Sound design, music integration, adaptive audio systems.
majiayu000/claude-skill-registry 163
-
cost-optimization
Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
majiayu000/claude-skill-registry 163
-
postmortem
Brutally honest incident postmortem. Reconstructs what happened from git, deploys, and logs — not from memory. Questions the process that allowed this to ship, not just the code that broke. No blame, all accountability.
majiayu000/claude-skill-registry 163
-
AgentDB Learning Plugins
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
majiayu000/claude-skill-registry 163
-
MCP Integration
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
majiayu000/claude-skill-registry 163
-
error-handling
Implement consistent error handling across the application. Use when adding try-catch blocks, error boundaries, or custom error classes.
majiayu000/claude-skill-registry 163
-
python-project-structure
Python project organization, module architecture, and public API design. Use when setting up new projects, organizing modules, defining public interfaces with __all__, or planning directory layouts.
majiayu000/claude-skill-registry 163
-
malware-analysis
majiayu000/claude-skill-registry 163
-
vitals-and-labs
Generate vital signs using FHIR Vital Signs profile and lab panels (CBC, BMP, CMP, lipid, HbA1c, urinalysis, COVID) with LOINC codes, reference ranges, and interpretation. Use when user mentions vitals, labs, observations, blood pressure, heart rate, HbA1c, glucose, CBC, lab results, or test results.
majiayu000/claude-skill-registry 163
-
supabase
Query a Supabase/PostgreSQL database with safety guardrails.
majiayu000/claude-skill-registry 163
-
red-team-tools
This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate su...
majiayu000/claude-skill-registry 163
-
clarity-gate
Pre-ingestion verification for epistemic quality in RAG systems with 9-point verification and Two-Round HITL workflow
majiayu000/claude-skill-registry 163
-
agentic-jumpstart-dependency-management
Dependency management guidelines for Jarvy - crate selection criteria, feature flag best practices, version management, security auditing with cargo-audit and cargo-deny.
majiayu000/claude-skill-registry 163