Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
depth-search
Deep multi-source research combining academic MCPs (arxiv, semantic-scholar, paper-search, deepwiki), Exa semantic search, and local ~/.topos knowledge base. Use for comprehensive research requiring multiple sources. NEVER fall back to web_search - ask user for help instead.
majiayu000/claude-skill-registry 163
-
plutonium-portal
Plutonium portals - web interfaces with authentication, entity scoping, and routes
majiayu000/claude-skill-registry 163
-
spawn-markdown-writer
비정형 마크다운 작성을 markdown-writer-agent에 위임
majiayu000/claude-skill-registry 163
-
code-guru
Senior principal engineer for Raamattu Nyt codebase. Use when:
(1) Implementing features with architectural implications (Cinema Reader, search UX, audio)
(2) Refactoring prototypes into production-grade components
(3) Reviewing PRs for architecture, UX, and cinema constraints
(4) Designing typed APIs that age well
(5) Deciding what NOT to build yet
(6) Challenging abstractions or spotting future maintenance issues
Triggers: "code review", "architecture decision", "should this be", "is this portable", "design review", "principal review", "future-proof"
majiayu000/claude-skill-registry 163
-
analytics-tracking
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.
majiayu000/claude-skill-registry 163
-
linux-services
Systemd service management and log access
majiayu000/claude-skill-registry 163
-
bio-crispr-screens-base-editing-analysis
Analyzes base editing and prime editing outcomes including editing efficiency, bystander edits, and indel frequencies. Use when quantifying CRISPR base editor results, comparing ABE vs CBE efficiency, or assessing prime editing fidelity.
majiayu000/claude-skill-registry 163
-
monitoring-cpu-usage
This skill enables Claude to monitor and analyze CPU usage patterns within applications. It helps identify CPU hotspots, analyze algorithmic complexity, and detect blocking operations. Use this skill when the user asks to "monitor CPU usage", "optimize CPU performance", "analyze CPU load", or "find CPU bottlenecks". It assists in identifying inefficient loops, regex performance issues, and provides optimization recommendations. This skill is designed for improving application performance by addressing CPU-intensive operations.
majiayu000/claude-skill-registry 163
-
next-best-practices
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
majiayu000/claude-skill-registry 163
-
knowledge
Query knowledge artifacts across all locations. Triggers: "find learnings", "search patterns", "query knowledge", "what do we know about", "where is the plan".
majiayu000/claude-skill-registry 163
-
labor-rate
Calculate construction labor rates with overhead, benefits, and productivity factors. Regional rate databases and crew composition.
majiayu000/claude-skill-registry 163
-
data-processor
Process and validate data inputs
majiayu000/claude-skill-registry 163
-
authoring-stitch-prompts
Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts. Use when creating, refining, or validating design directives for Google Stitch. Follows Stitch best practices with short, directive prompts focused on screens, structure, and visual hierarchy.
majiayu000/claude-skill-registry 163
-
creating-libraries
This skill should be used when the user asks to "create a library", "scaffold a new lib", "add a local library", "create a namespace module", "set up _.ts and __.ts", or needs to create a new TypeScript library following the _.ts/__.ts namespace pattern. Handles both simple (single file) and complex (barrel) library structures.
majiayu000/claude-skill-registry 163
-
Orchestration Planner
Plan multi-step workflows using capability graph and Codex-powered goal decomposition with HTN-style hierarchical task planning.
majiayu000/claude-skill-registry 163
-
runway
Create with AI video tools on Runway - generate videos, edit with AI, and use creative ML models
majiayu000/claude-skill-registry 163
-
Newman Testing
Newman/Postman collection testing patterns for API testing with environment variables, test assertions, and reporting. Use when building API tests, running Newman collections, testing REST APIs, validating HTTP responses, creating Postman collections, configuring API test environments, generating test reports, or when user mentions Newman, Postman, API testing, collection runner, integration tests, API validation, test automation, or CI/CD API testing.
majiayu000/claude-skill-registry 163
-
querying-gemini
Queries Gemini 3 Flash for high-speed code analysis, generation, and complex coding questions. Provides P0-P3 prioritized analysis reports, architecture audits, and code generation with configurable thinking levels (minimal/low/medium/high). 1M context, 64K output. Pro-level intelligence at Flash pricing.
majiayu000/claude-skill-registry 163
-
md-split
Splits a Markdown file by H2 headings into numbered documents and generates an index file.
majiayu000/claude-skill-registry 163
-
session-managing
自动触发的会话生命周期管理 - INHERIT (继承知识) + DEPOSIT (沉淀精华)
majiayu000/claude-skill-registry 163
-
oop-encapsulation
Use when applying encapsulation and information hiding principles in object-oriented design. Use when controlling access to object state and behavior.
majiayu000/claude-skill-registry 163
-
quality-verify-integration
Verifies components are integrated into the system, not just created. Detects orphaned code (exists but never imported). Use BEFORE marking features complete, moving ADRs to completed/, or claiming integration work done. Enforces Creation-Connection-Verification (CCV) principle.
majiayu000/claude-skill-registry 163
-
github-analysis
Analyze GitHub commits, generate PR reviews, calculate contributor leaderboards, and assess code quality. Use when analyzing git commits, reviewing code, generating GitHub activity reports, or tracking developer contributions.
majiayu000/claude-skill-registry 163
-
export
PDF/PPTX 내보내기가 필요할 때
majiayu000/claude-skill-registry 163