Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
reve-ai
Generate, edit, and remix images using the Reve AI API. Use when creating images from text prompts, editing existing images with instructions, or combining/remixing multiple reference images. Requires REVE_API_KEY or REVE_AI_API_KEY environment variable.
majiayu000/claude-skill-registry 163
-
early-stopping-callback
Early Stopping Callback - Auto-activating skill for ML Training.
Triggers on: early stopping callback, early stopping callback
Part of the ML Training skill category.
majiayu000/claude-skill-registry 163
-
Windows Privilege Escalation
This skill should be used when the user asks to "escalate privileges on Windows," "find Windows privesc vectors," "enumerate Windows for privilege escalation," "exploit Windows misconfigurations," or "perform post-exploitation privilege escalation." It provides comprehensive guidance for discovering and exploiting privilege escalation vulnerabilities in Windows environments.
majiayu000/claude-skill-registry 163
-
agent-md-generator
交互式生成 GitHub Copilot agents.md 文件的工作流。当用户请求创建代理、构建自定义 Copilot 代理、生成 agents.md 或需要帮助配置 GitHub Copilot 自定义代理时使用。触发短语包括"创建代理"、"生成 agent.md"、"做一个文档代理"、"生成测试代理"等涉及 GitHub Copilot 代理配置的请求。
majiayu000/claude-skill-registry 163
-
dev-test-hammerspoon
This skill should be used when the user asks to "debug macOS app", "test native app", "automate macOS workflow", "test native macOS application", or needs desktop automation for testing macOS applications with Hammerspoon. Use for application launch/control, window management, keyboard/mouse simulation, and visual verification.
majiayu000/claude-skill-registry 163
-
prism-node-api
Complete API specification for PRISM.node K1 Light Lab editor, including node system architecture, type definitions, color space transforms, WebSocket TLV protocol, and engine configuration for 320-LED addressable light patterns.
majiayu000/claude-skill-registry 163
-
playwright-responsive-screenshots
Captures screenshots at multiple viewport breakpoints for responsive design validation and
documentation. Use when you need to test responsive layouts, validate mobile/tablet/desktop
views, document design system breakpoints, or create visual regression test baselines.
Triggers on "test responsive design", "screenshot at breakpoints", "capture mobile and
desktop views", "responsive design testing", or "multi-device screenshots". Works with
Playwright MCP tools (browser_navigate, browser_resize, browser_take_screenshot).
majiayu000/claude-skill-registry 163
-
auth-wechat-miniprogram
Complete guide for WeChat Mini Program authentication with CloudBase - native login, user identity, and cloud function integration.
majiayu000/claude-skill-registry 163
-
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
majiayu000/claude-skill-registry 163
-
registry-component-patterns
Register components in registry.json for shadcn/ui add command. Apply when adding new 8-bit components to the component library.
majiayu000/claude-skill-registry 163
-
agenta
LLM prompt management and evaluation platform. Version prompts, run A/B tests, evaluate with metrics, and deploy with confidence using Agenta's self-hosted solution.
majiayu000/claude-skill-registry 163
-
docs-seeker
Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy
majiayu000/claude-skill-registry 163
-
gtm-pricing
B2B go-to-market strategy, pricing models, ICP development, positioning, and competitive intelligence. Use when planning GTM strategy, setting pricing, defining ICP, or evaluating opportunities.
majiayu000/claude-skill-registry 163
-
review-maintainability
Audit code for DRY violations, dead code, complexity, and consistency issues.
majiayu000/claude-skill-registry 163
-
loki-mode
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
majiayu000/claude-skill-registry 163
-
distributed-llm-pretraining-torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
majiayu000/claude-skill-registry 163
-
strategic-insight-prospecting
Replace generic sales pitches with data-driven research reports that analyze a prospect's internal performance against competitors. Use this when targeting high-level executives (C-suite/VP) or attempting to break into "ungettable" enterprise accounts during budget freezes or market downturns.
majiayu000/claude-skill-registry 163
-
vibecoder-guide
Guides VibeCoder (non-technical users) through natural language development. 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
-
task-breakdown
FIRST STEP - Assess task complexity (0-20 score) and output orchestration level (0-3). Use for ANY non-trivial task BEFORE execution. Scores across scope, time, agents, dependencies, documentation. Level 0 (0-2 direct), Level 1 (3-7 single agent), Level 2 (8-14 multi-agent), Level 3 (15-20 epic). Outputs recommendation then exits. NOT for execution or agent selection (use agent-selector after).
majiayu000/claude-skill-registry 163
-
taiyo-style-sales-letter
太陽スタイル完全準拠のセールスレター作成。176パターン・80項目チェックリスト・taiyo-analyzer連携による品質保証付き。
majiayu000/claude-skill-registry 163
-
Knack Goal Tracker
Tracks HTI's performance against both grant and business development goals in real-time. Provides early warning system for goal attainment risks an...
majiayu000/claude-skill-registry 163
-
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
majiayu000/claude-skill-registry 163
-
32-analyze-verify-150
[32] ANALYZE. Ensure every critical claim has verifiable evidence with confidence levels. Each fact must have source + confidence percentage. If confidence <85%, enter Loop150 to find more sources. Use for critical decisions, factual claims, legal/compliance work, or any situation where unverified claims are dangerous.
majiayu000/claude-skill-registry 163
-
speckit-specify
Create or update a feature specification from a natural language feature description.
majiayu000/claude-skill-registry 163