Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
template-skill
Replace with description of the skill and when Claude should use it.
majiayu000/claude-skill-registry 163
-
performance-advisor
Reference guide for MongoDB performance patterns: index strategies (ESR rule, compound, partial, TTL), explain plan interpretation, and performance checklists. Use as background knowledge when advising on indexing or performance. For hands-on optimization of a specific slow query, trigger the query-advisor agent instead.
majiayu000/claude-skill-registry 163
-
Skill Builder
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
majiayu000/claude-skill-registry 163
-
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
majiayu000/claude-skill-registry 163
-
citation-agent
Retrieves verified citations from RAG DB only. Never invents citations. Returns citations with hashes.
majiayu000/claude-skill-registry 163
-
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".
majiayu000/claude-skill-registry 163
-
monitorando-entregas
Consulta status de entregas, datas de embarque/faturamento, canhotos e devolucoes.
USAR QUANDO (NFs JA FATURADAS):
- Status: "NF 12345 foi entregue?", "status da entrega do Atacadao"
- Datas de embarque: "que dia saiu?", "que dia embarcou?", "quando expediu?"
- Datas de faturamento: "quando faturou?", "data da NF"
- Datas de entrega: "quando chegou?", "foi entregue quando?"
- Canhoto: "tem canhoto da NF?", "canhotos pendentes"
- Devolucoes: "houve devolucao?", "NFs devolvidas"
- Pendencias: "entregas pendentes", "NFs no CD", "entregas com problema"
NAO USAR QUANDO (ANTES de faturar):
- Pedidos em carteira/separacao → usar **gerindo-expedicao**
- Estoque, disponibilidade → usar **gerindo-expedicao**
- Criar separacao → usar **gerindo-expedicao**
- Rastrear NF no Odoo → usar **rastreando-odoo**
majiayu000/claude-skill-registry 163
-
architecture-review
Architecture evaluation criteria and technology standards for the homelab.
Preloaded into the designer agent to ground design decisions in established
patterns and principles.
Use when: (1) Evaluating a proposed technology addition, (2) Reviewing architecture decisions,
(3) Assessing stack fit for a new component, (4) Comparing implementation approaches.
Triggers: "architecture review", "evaluate technology", "stack fit", "should we use",
"technology comparison", "design review", "architecture decision"
majiayu000/claude-skill-registry 163
-
git-essentials
Essential Git commands and workflows for version control, branching, and collaboration.
majiayu000/claude-skill-registry 163
-
local-prospect-audit
Quick pre-sales assessment of a local business prospect. Determines GO / SOFT GO / NO-GO before investing time in a client. Use when user says "oceń tego klienta", "czy warto go brać", "zrób pre-sales audit", "sprawdz konkurencje dla X", "czy łatwo go wypromować", or shares a business name/URL asking if it's worth pursuing. Costs max $0.10 in DataForSEO credits.
majiayu000/claude-skill-registry 163
-
deep-index
코드베이스 인덱싱 및 구조 분석. 프로젝트를 스캔하여 모듈별 요약, 의존성 그래프, 진입점 맵을 생성하고 project context를 풍부하게 합니다. Use when onboarding to a new codebase or when project structure needs documentation.
majiayu000/claude-skill-registry 163
-
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
majiayu000/claude-skill-registry 163
-
convex-schema-validator
Defining and validating database schemas with proper typing, index configuration, optional fields, unions, and migration strategies for schema changes
majiayu000/claude-skill-registry 163
-
gkg
Semantic code analysis with GitLab Knowledge Graph. Use for go-to-definition, find-usages, impact analysis, architecture visualization. Supports Ruby, Java, Kotlin, Python, TypeScript/JavaScript.
majiayu000/claude-skill-registry 163
-
testing
Root: testing pyramid unit/integration/e2e, TDD/BDD, coverage strategy, naming conventions
majiayu000/claude-skill-registry 163
-
getting-started
Interactive post-onboarding tour with adaptive pathways based on available data
majiayu000/claude-skill-registry 163
-
sync-notion
majiayu000/claude-skill-registry 163
-
bmad-code-review
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code"
majiayu000/claude-skill-registry 163
-
nnews-guide
Guides how to integrate the NNews NuGet package for consuming the NNews CMS API in a .NET 8 project. Use when the user wants to consume articles, categories, tags, images, or AI-powered content generation from the NNews API.
majiayu000/claude-skill-registry 163
-
tcm-constitution-analyzer
分析中医体质数据、识别体质类型、评估体质特征,并提供个性化养生建议。支持与营养、运动、睡眠等健康数据的关联分析。
majiayu000/claude-skill-registry 163
-
society-of-mind
Intelligence emerges from many simple agents (Minsky)
majiayu000/claude-skill-registry 163
-
debugging
Systematic debugging strategies and error analysis patterns. Auto-triggers when investigating bugs, analyzing stack traces, or troubleshooting issues.
majiayu000/claude-skill-registry 163
-
album-art-director
Creates visual concepts for album artwork and generates AI art prompts. Use during planning for concept discussion, or after all tracks are Final for actual artwork generation.
majiayu000/claude-skill-registry 163
-
solana-vulnerability-scanner
Scans Solana programs for 6 critical vulnerabilities including arbitrary CPI, improper PDA validation, missing signer/ownership checks, and sysvar spoofing. Use when auditing Solana/Anchor programs. (project, gitignored)
majiayu000/claude-skill-registry 163