Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
session-resume
Resume previous work from archived session with full context restoration
majiayu000/claude-skill-registry 163
-
schedule-validator
Validate generated schedules for ACGME compliance, coverage gaps, and operational viability. Use when verifying schedule integrity before deployment or investigating schedule issues.
majiayu000/claude-skill-registry 163
-
react_perf_perfection
A "No-Compromise" React performance checklist enforcing strict re-render discipline and bundle auditing.
majiayu000/claude-skill-registry 163
-
agentuity-cli-project-create
Create a new project. Use for project management operations
majiayu000/claude-skill-registry 163
-
pencil-to-code
Export .pen design to React/Tailwind code. Does ONE thing well.
Input: .pen frame ID or file path
Output: React component code + Tailwind config
Use when: design-exploration or user needs implementation code
from a finalized Pencil design.
majiayu000/claude-skill-registry 163
-
mutate
Change persistent state with checkpoint and rollback support. Use when modifying files, updating databases, changing configuration, or any operation that permanently alters state.
majiayu000/claude-skill-registry 163
-
coding-standard-cpp
Enforce C++ coding standards including camelCase or snake_case variables, PascalCase classes, and consistent file naming.
majiayu000/claude-skill-registry 163
-
media-processing
Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration) and ImageMagick (image manipulation, format conversion, batch processing, effects, composition). Use when converting media formats, encoding videos with specific codecs (H.264, H.265, VP9), resizing/cropping images, extracting audio from video, applying filters and effects, optimizing file sizes, creating streaming manifests (HLS/DASH), generating thumbnails, batch processing images, creating composite images, or implementing media processing pipelines. Supports 100+ formats, hardware acceleration (NVENC, QSV), and complex filtergraphs.
majiayu000/claude-skill-registry 163
-
74-mid-session-save-150
[74] CLOSE. Quick checkpoint during active work when context is running low. Use multiple times per development cycle to preserve progress and lessons. Lighter than close-session — no full handoff needed. Triggers on 'save progress', 'checkpoint', 'context low', or automatically when nearing token limits.
majiayu000/claude-skill-registry 163
-
model-first-reasoning
Apply Model-First Reasoning (MFR) to code generation tasks. Use when the user requests "model-first", "MFR", "formal modeling before coding", "model then implement", or when tasks involve complex logic, state machines, constraint systems, or any implementation requiring formal correctness guarantees. Enforces strict separation between modeling and implementation phases.
majiayu000/claude-skill-registry 163
-
working-with-documents
Creates and edits Office documents: Word (.docx), PDF, and PowerPoint (.pptx).
Use when working with document creation, PDF manipulation, presentation generation,
tracked changes, or converting between formats.
majiayu000/claude-skill-registry 163
-
sqlmodel-task-models
This skill should be used when defining a robust, type-safe, and async-compatible database schema for the Todo application using SQLModel, ensuring compatibility with Better Auth and optimized for PostgreSQL.
majiayu000/claude-skill-registry 163
-
rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
majiayu000/claude-skill-registry 163
-
using-system-architect
Use when you have architecture documentation from system-archaeologist and need critical assessment, refactoring recommendations, or improvement prioritization - routes to appropriate architect specialist skills
majiayu000/claude-skill-registry 163
-
duckdb-ies
Layer 4: IES Interactome Analytics with GF(3) Momentum Tracking
majiayu000/claude-skill-registry 163
-
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
majiayu000/claude-skill-registry 163
-
analyzing-system-throughput
This skill enables Claude to analyze and optimize system throughput. It is triggered when the user requests throughput analysis, performance improvements, or bottleneck identification. The skill uses the `throughput-analyzer` plugin to assess request throughput, data throughput, concurrency limits, queue processing, and resource saturation. Use this skill when the user mentions "analyze throughput", "optimize performance", "identify bottlenecks", or asks about system capacity. It helps determine limiting factors and evaluate scaling strategies.
majiayu000/claude-skill-registry 163
-
ai-ad-fe-gen
majiayu000/claude-skill-registry 163
-
state-tanstack
State management patterns using Tanstack Query for server state and Zustand for client state. This skill should be used when setting up data fetching, implementing mutations, managing UI state, or organizing stores in React applications.
majiayu000/claude-skill-registry 163
-
fixing
Fix bugs, errors, test failures, CI/CD issues with intelligent routing. Use when reporting bugs, type errors, log errors, UI issues, code problems. Auto-classifies complexity and activates relevant skills.
majiayu000/claude-skill-registry 163
-
tiktok-workflow-e2e
End-to-end orchestration of TikTok content creation. Single entry point for batch processing multiple products from scraping to production-ready scripts.
majiayu000/claude-skill-registry 163
-
Skillsmith
Discover, install, compare, and manage Claude Code skills. Use when searching for skills, evaluating quality, understanding trust tiers, checking quotas, or creating custom skills. Triggers: 'find skill', 'search skills', 'install skill', 'trust tier', 'create skill', 'skill quality', 'skill quota'.
majiayu000/claude-skill-registry 163
-
ha-error-checking
Debug and validate Home Assistant dashboards, configurations, and entity usage via WebSocket API. Use when troubleshooting dashboard errors, validating entity IDs, checking HACS card installations, or investigating lovelace/frontend issues. Covers system logs, configuration validation, entity verification, and common error patterns.
majiayu000/claude-skill-registry 163
-
struct-interface
Reviews Go interfaces and struct design for proper abstraction, embedding, and composition patterns. Use when designing APIs, reviewing interface definitions, or seeing type hierarchies.
majiayu000/claude-skill-registry 163