Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
architectural-forensics
Master protocol for deconstructing agent frameworks to inform derivative system architecture. Use when (1) analyzing an agent framework's codebase comprehensively, (2) comparing multiple frameworks to select best practices, (3) designing a new agent system based on prior art, (4) documenting architectural decisions with evidence, or (5) conducting technical due diligence on AI agent implementations. This skill orchestrates sub-skills for data substrate, execution engine, cognitive architecture, and synthesis phases.
majiayu000/claude-skill-registry 163
-
remove-comments
Clean obvious and redundant comments from code
majiayu000/claude-skill-registry 163
-
ts-strict-guardian
Enforce strict TypeScript guidelines and safety
majiayu000/claude-skill-registry 163
-
copyright-docs
Generate software copyright design specification documents compliant with China Copyright Protection Center (CPCC) standards. Creates complete design documents with Mermaid diagrams based on source code analysis. Use for software copyright registration, generating design specification, creating CPCC-compliant documents, or documenting software for intellectual property protection. Triggers on "软件著作权", "设计说明书", "版权登记", "CPCC", "软著申请".
majiayu000/claude-skill-registry 163
-
windows-3-1-web-designer
Modern web applications with authentic Windows 3.1 aesthetic. Solid navy title bars, Program Manager navigation, beveled borders, single window controls. Extrapolates Win31 to AI chatbots (Cue Card paradigm), mobile UIs (pocket computing). Activate on 'windows 3.1', 'win31', 'program manager', 'retro desktop', '90s aesthetic', 'beveled'. NOT for Windows 95 (use windows-95-web-designer - has gradients, Start menu), vaporwave/synthwave, macOS, flat design.
majiayu000/claude-skill-registry 163
-
faker
Use when writing Vague (.vague) files that need realistic test data using faker generators for names, emails, addresses, dates, and more
majiayu000/claude-skill-registry 163
-
sequential-thinking
Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.
majiayu000/claude-skill-registry 163
-
aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
majiayu000/claude-skill-registry 163
-
fixing-bugs
Use when encountering a bug - complete workflow from discovery through debugging, bd issue, test-driven fix, verification, and closure
majiayu000/claude-skill-registry 163
-
site-architecture
Technical SEO - robots.txt, sitemap, meta tags, Core Web Vitals
majiayu000/claude-skill-registry 163
-
tax-strategy-optimizer
Pre-tax vs Roth analysis, charitable giving optimization, capital gains timing, deduction maximization. Not a substitute for CPA.
majiayu000/claude-skill-registry 163
-
nextjs-data-fetching-and-caching
Use this skill whenever the user wants to design, refactor, or optimize data fetching and caching in a Next.js (App Router) + TypeScript project, including server components, route handlers, server actions, cache modes, revalidation, and selective client-side fetching.
majiayu000/claude-skill-registry 163
-
linear-cost-tuning
Optimize Linear API usage and manage costs effectively.
Use when reducing API calls, managing rate limits efficiently,
or optimizing integration costs.
Trigger with phrases like "linear cost", "reduce linear API calls",
"linear efficiency", "linear API usage", "optimize linear costs".
majiayu000/claude-skill-registry 163
-
fastapi-auth-patterns
Implement and validate FastAPI authentication strategies including JWT tokens, OAuth2 password flows, OAuth2 scopes for permissions, and Supabase integration. Use when implementing authentication, securing endpoints, handling user login/signup, managing permissions, integrating OAuth providers, or when user mentions JWT, OAuth2, Supabase auth, protected routes, access control, role-based permissions, or authentication errors.
majiayu000/claude-skill-registry 163
-
plotly-chart-generator
Generate plotly chart generator operations. Auto-activating skill for Visual Content.
Triggers on: plotly chart generator, plotly chart generator
Part of the Visual Content skill category. Use when working with plotly chart generator functionality. Trigger with phrases like "plotly chart generator", "plotly generator", "plotly".
majiayu000/claude-skill-registry 163
-
toast
Toast notifications with Sonner for user feedback. Use for success/error messages, async operation feedback, and temporary notifications. Always use when using Sonner.
majiayu000/claude-skill-registry 163
-
aceternity-ui-configuration
majiayu000/claude-skill-registry 163
-
Bankr Agent - Token Deployment
This skill should be used when the user asks to "deploy token", "create token", "launch token", "Clanker", "claim fees", "token metadata", "update token", "mint new token", or any token deployment operation. Provides guidance on deploying ERC20 tokens via Clanker.
majiayu000/claude-skill-registry 163
-
cloudkit-debugging
CloudKit sync and sharing debugging specialist. Use when encountering CloudKit sync issues, schema problems, sharing bugs, or CKRecord errors.
majiayu000/claude-skill-registry 163
-
mongoose-patterns
Mongoose/MongoDB patterns for schema design, queries, indexes, aggregations. Use when working with MongoDB through Mongoose.
majiayu000/claude-skill-registry 163
-
swiftui-view-refactor
Refactor and review SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view’s layout/ordering, handle view models safely (non-optional when possible), or standardize how dependencies and @Observable state are initialized and passed.
majiayu000/claude-skill-registry 163
-
address-sanitizer
AddressSanitizer detects memory errors during fuzzing. Use when fuzzing C/C++ code to find buffer overflows and use-after-free bugs.
majiayu000/claude-skill-registry 163
-
evidence-judge
Validate claims against sources and score confidence; use when asked to verify research output accuracy.
majiayu000/claude-skill-registry 163
-
ln-642-layer-boundary-auditor
L3 Worker. Audits architectural layer boundaries, detects violations (code in wrong layers), checks pattern coverage. Invoked by ln-640 once per audit.
majiayu000/claude-skill-registry 163