Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
loop-review-skill-until-fixed-point
Iterate /review-skill on a target until fixed point. Runs review passes until all reviewers return NO ISSUES.
majiayu000/claude-skill-registry 163
-
capi-test-naming-verifier
This skill should be used when the user asks to "verify C API test naming", "check test naming convention", "validate test names", "C API test naming compliance", "test naming verification", "ensure test naming consistency", "audit test names", "review test naming", or mentions verifying that C API unit test names follow the standardized naming convention methodNameTestScenario.
majiayu000/claude-skill-registry 163
-
self / sop_extraction
General SOP for extracting and structuring processes or checklists from conversation evidence.
majiayu000/claude-skill-registry 163
-
cycle-plan
Plan Linear cycles using velocity analytics. Suggests scope based on historical capacity, identifies dependency risks, balances workload.
majiayu000/claude-skill-registry 163
-
case-study-doc
Format a client result into a shareable case study document. Structure follows Client Background → The Challenge → What We Did → The Results → Key Takeaways. 500-800 words. Professional, results-focused, quotable. Use when user needs a "case study", "client success story", "results document", or "portfolio piece".
majiayu000/claude-skill-registry 163
-
tavily-search
使用Tavily API进行网络搜索，获取实时信息、回答问题或研究主题
majiayu000/claude-skill-registry 163
-
sim-run
Run deterministic simulation tests with progressive difficulty levels (sunny/stormy/radioactive) inspired by TigerBeetle VOPR — orchestrates seed management, workload selection, and invariant verification
majiayu000/claude-skill-registry 163
-
intelliprint-automation
Automate Intelliprint tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
vibecoder-guide
VibeCoder（非技術ユーザー）を自然言語開発でガイド。Use when user asks what to do next, how to use the system, needs help, or is stuck. Do NOT load for: technical-user work, direct implementation requests, or reviews.
majiayu000/claude-skill-registry 163
-
system-design-decision-engine
Motor de decisão para System Design. Use quando a pessoa usuária pedir para desenhar, decidir, revisar ou defender uma arquitetura. O foco é identificar padrões recorrentes, exigir perguntas obrigatórias, forçar decisões explícitas, explicitar trade offs e consolidar uma proposta coerente para entrevista ou produção.
majiayu000/claude-skill-registry 163
-
condition-based-waiting
Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses
majiayu000/claude-skill-registry 163
-
auto-review-loop
Autonomous multi-round research review loop. Repeatedly reviews using Claude Code via claude-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
majiayu000/claude-skill-registry 163
-
valid-skill
A valid skill for testing purposes.
majiayu000/claude-skill-registry 163
-
password-reset-poisoning
Exploit password reset vulnerabilities during authorized penetration testing.
majiayu000/claude-skill-registry 163
-
zero-trust
Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.
majiayu000/claude-skill-registry 163
-
vexa
Send bots to Zoom, Google Meet, and Microsoft Teams meetings. Get live transcripts, recordings, and reports. Self-hosted or cloud — no external API needed.
majiayu000/claude-skill-registry 163
-
ln-783-container-launcher
Builds and launches Docker containers with health verification. Use when validating that containerized services start correctly.
majiayu000/claude-skill-registry 163
-
authenticate-wallet
Sign in to the wallet. Use when you or the user want to log in, sign in, connect, or set up the wallet, or when any wallet operation fails with authentication or "not signed in" errors. This skill is a prerequisite before sending, trading, or funding.
majiayu000/claude-skill-registry 163
-
making-feedback-loopable
Scaffolds build/test/lint/runtime checks so agents get structured, self-locating feedback with file paths, line numbers, and error codes. Use when setting up a repo for AI-assisted development, when an agent is failing to debug due to weak diagnostics, or when asked to make a codebase more LLM-friendly.
majiayu000/claude-skill-registry 163
-
alphafold-database
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.
majiayu000/claude-skill-registry 163
-
Wireshark Network Traffic Analysis
This skill should be used when the user asks to "analyze network traffic with Wireshark", "capture packets for troubleshooting", "filter PCAP files", "follow TCP/UDP streams", "detect network anomalies", "investigate suspicious traffic", or "perform protocol analysis". It provides comprehensive techniques for network packet capture, filtering, and analysis using Wireshark.
majiayu000/claude-skill-registry 163
-
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
majiayu000/claude-skill-registry 163
-
implement-worktree-no-merge
Implement a plan in an isolated git worktree without merging, testing, or cleaning up. For MCP orchestration use — the orchestrator handles testing and merging separately.
majiayu000/claude-skill-registry 163
-
pytorch-lightning
Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
majiayu000/claude-skill-registry 163