Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
ams
ams-OSRAM MPN encoding patterns, suffix decoding, and handler guidance. Use when working with ams sensor products, optical components, or AMSHandler.
majiayu000/claude-skill-registry 163
-
checkpoint-protocol
Human interaction protocol with automation-first rule. Defines checkpoint types and when to use them.
majiayu000/claude-skill-registry 163
-
user-profile-reader
Read user profile from workspace and calculate content relevance.
Use to personalize output based on user interests.
majiayu000/claude-skill-registry 163
-
skill-author
Guide for creating new Claude Code skills following best practices. Use when the user asks to create a new skill, agent capability, or wants to extend Claude's autonomous functionality.
majiayu000/claude-skill-registry 163
-
Root Cause Tracing
Systematically trace bugs backward through call stack to find original trigger
majiayu000/claude-skill-registry 163
-
differentiation-schemes
Select and apply numerical differentiation schemes for PDE/ODE discretization. Use when choosing finite difference/volume/spectral schemes, building stencils, handling boundaries, estimating truncation error, or analyzing dispersion and dissipation.
majiayu000/claude-skill-registry 163
-
testability-scoring
AI-powered testability assessment using 10 principles of intrinsic testability with Playwright and optional Vibium integration. Evaluates web applications against Observability, Controllability, Algorithmic Simplicity, Transparency, Stability, Explainability, Unbugginess, Smallness, Decomposability, and Similarity. Use when assessing software testability, evaluating test readiness, identifying testability improvements, or generating testability reports.
majiayu000/claude-skill-registry 163
-
configuring-zed
Provides guidance for configuring and customizing the Zed editor. Use when modifying Zed settings, keybindings, themes, or extensions.
majiayu000/claude-skill-registry 163
-
textual
Expert guidance for building TUI (Text User Interface) applications with the Textual framework. Invoke when user asks about Textual development, TUI apps, widgets, screens, CSS styling, reactive programming, or testing Textual applications.
majiayu000/claude-skill-registry 163
-
bifurcation
Hopf bifurcation detection for dynamical system state transitions with GF(3) phase portraits
majiayu000/claude-skill-registry 163
-
claude-md-maintainer
Validate/update/create CLAUDE.md memory files with progressive disclosure and context-optimized structure
majiayu000/claude-skill-registry 163
-
api-endpoint-generator
Generates CRUD REST API endpoints with request validation, TypeScript types, consistent response formats, error handling, and documentation. Includes route handlers, validation schemas (Zod/Joi), typed responses, and usage examples. Use when building "REST API", "CRUD endpoints", "API routes", or "backend endpoints".
majiayu000/claude-skill-registry 163
-
bun-test-lifecycle
majiayu000/claude-skill-registry 163
-
marp-authoring
Use when you need Marp/Marpit Markdown authoring rules, directives, layouts, or theme guidance and want the minimal reading path for slide writing.
majiayu000/claude-skill-registry 163
-
Daily Reporter
Generate comprehensive daily status reports after solving AoC puzzles. Documents success/failure, challenges faced, retry attempts, execution time, and insights for workflow tuning. Use after completing each day's puzzle to provide developer feedback on automation effectiveness.
majiayu000/claude-skill-registry 163
-
starwards-debugging
Systematic debugging for Starwards - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) with Colyseus state inspection, Tweakpane debugging, multiplayer sync issues, and monorepo-specific troubleshooting
majiayu000/claude-skill-registry 163
-
swift-lang
Swift language mastery skill covering advanced language features beyond UI.
Use when working with macros, concurrency (async/await, actors), networking,
Swift Testing, generics, memory optimization, or result builders. Not for SwiftUI patterns - see swift-ui.
majiayu000/claude-skill-registry 163
-
market-sizing-analysis
This skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate market opportunity", "what's the total addressable market", or requests market sizing analysis for a startup or business opportunity.
majiayu000/claude-skill-registry 163
-
agent-tooling-engineer
Expert tooling engineer specializing in developer tool creation, CLI development, and productivity enhancement. Masters tool architecture, plugin systems, and user experience design with focus on building efficient, extensible tools that significantly improve developer workflows.
majiayu000/claude-skill-registry 163
-
localization-testing
Internationalization (i18n) and localization (l10n) testing for global products including translations, locale formats, RTL languages, and cultural appropriateness. Use when launching in new markets or building multi-language products.
majiayu000/claude-skill-registry 163
-
profile-code
Measure execution time and memory usage of code. Use when analyzing performance characteristics.
majiayu000/claude-skill-registry 163
-
Org-roam Note Management
Helps users create, manage, and link org-roam notes using emacsclient to connect to a running Emacs daemon.
**ALWAYS USE THIS SKILL** when user mentions "roam note" or "org-roam", references file paths containing `/roam/` or `/org-roam/`, or wants to create/search/link notes in their roam directory.
Use this skill for: creating roam notes, searching notes, adding backlinks, querying org-roam database, managing Zettelkasten-style knowledge systems.
**NEVER use Read/Write/Edit tools directly on roam notes** - they bypass database sync and break org-roam functionality.
majiayu000/claude-skill-registry 163
-
create-haskell-bazel-target
Create a target for haskell application.
majiayu000/claude-skill-registry 163
-
clear-cove-task-design
Combine CLEAR (Concise, Logical, Explicit, Adaptive, Reflective) and CoVe (Chain of Verification) to write and lint agent task files that will be executed by worker agents. Use when orchestration or planning agents are producing task plans, task prompts, or TASK.md style instructions that must be unambiguous, verifiable, and resistant to hallucination.
majiayu000/claude-skill-registry 163