Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
kotlin-android-reviewer
WHEN: Android Kotlin code review, Jetpack Compose patterns, Coroutines/Flow checks, ViewModel structure analysis
WHAT: Compose best practices + Coroutines patterns + State management + Memory leak detection + Performance optimization
WHEN NOT: KMP shared code → kotlin-multiplatform-reviewer, Backend → kotlin-spring-reviewer
majiayu000/claude-skill-registry 163
-
Single Purpose Variables
Use each variable for exactly one purpose - no hybrid coupling or hidden meanings
majiayu000/claude-skill-registry 163
-
laravel-tdd
Test-Driven Development specifically for Laravel applications using Pest PHP. Use when implementing any Laravel feature or bugfix - write the test first, watch it fail, write minimal code to pass.
majiayu000/claude-skill-registry 163
-
git-pr-workflow
Complete GitHub workflow from commit to PR including conventional commits, branch management, pre-push quality checks, PR creation with gh CLI, and wiki synchronization. Use when creating commits, ...
majiayu000/claude-skill-registry 163
-
pdf-text-extractor
Download PDFs (when available) and extract plain text to support full-text evidence, writing `papers/fulltext_index.jsonl` and `papers/fulltext/*.txt`.
**Trigger**: PDF download, fulltext, extract text, papers/pdfs, 全文抽取, 下载PDF.
**Use when**: `queries.md` 设置 `evidence_mode: fulltext`（或你明确需要全文证据）并希望为 paper notes/claims 提供更强 evidence。
**Skip if**: `evidence_mode: abstract`（默认）；或你不希望进行下载/抽取（成本/权限/时间）。
**Network**: fulltext 下载通常需要网络（除非你手工提供 PDF 缓存在 `papers/pdfs/`）。
**Guardrail**: 缓存下载到 `papers/pdfs/`；默认不覆盖已有抽取文本（除非显式要求重抽）。
majiayu000/claude-skill-registry 163
-
code-review-checklist
Code review criteria covering security, performance, quality standards, and issue prioritization for thorough code analysis.
majiayu000/claude-skill-registry 163
-
pine-debugger
Adds debugging capabilities and troubleshoots Pine Script issues in TradingView's opaque environment. Use when scripts have errors, unexpected behavior, need debugging tools added, or require troubleshooting. Triggers on "debug", "fix", "error", "not working", "wrong values", or troubleshooting requests.
majiayu000/claude-skill-registry 163
-
refine-plan
Refines an existing implementation plan through discussion with the user. Takes a GitHub issue number. Use when the user wants to refine a plan, discuss a plan, change a plan, or says "refine plan X" or "let's discuss the plan for issue
majiayu000/claude-skill-registry 163
-
agents-manager
Branch skill for building and improving agents. Use when creating new agents, adapting marketplace agents, validating agent structure, writing system prompts, or improving existing agents. Triggers: 'create agent', 'improve agent', 'validate agent', 'fix agent', 'agent frontmatter', 'system prompt', 'adapt agent', 'customize agent', 'agent examples', 'agent tools'.
majiayu000/claude-skill-registry 163
-
kubectl-localmesh-operations
kubectl-localmesh固有の運用操作（起動、/etc/hosts管理、サービスアクセス、依存関係チェック）を提供します
majiayu000/claude-skill-registry 163
-
graphql-codegen
Generate TypeScript types and React hooks from GraphQL schemas
majiayu000/claude-skill-registry 163
-
sf-imagen
AI-powered visual content generation for Salesforce development. Generates ERD diagrams, LWC mockups, architecture visuals using Nano Banana Pro. Also provides Gemini as a parallel sub-agent for code review and research.
majiayu000/claude-skill-registry 163
-
resource-scout
Search and discover Claude Code skills and MCP servers from marketplaces, GitHub repositories, and registries. Use when (1) user asks to find skills for a specific task, (2) looking for MCP servers to connect external tools, (3) user mentions "find skill", "search MCP", "discover tools", or "what skills exist for X", (4) before creating a custom skill to check if one already exists.
majiayu000/claude-skill-registry 163
-
initializer
Initialize long-running agent projects with environment setup, feature list generation, and progress tracking. Use when starting a new implementation project or setting up an existing codebase for Claude-assisted development. Creates init.sh (dev server script), claude-progress.txt (work log), and docs/features.json (feature list with status tracking).
majiayu000/claude-skill-registry 163
-
agent-architect
Create and refine OpenCode agents via guided Q&A. Use proactively for agent creation, performance improvement, or configuration design.
Examples:
- user: "Create an agent for code reviews" → ask about scope, permissions, tools, model preferences, generate AGENTS.md frontmatter
- user: "My agent ignores context" → analyze description clarity, allowed-tools, permissions, suggest improvements
- user: "Add a database expert agent" → gather requirements, set convex-database-expert in subagent_type, configure permissions
- user: "Make my agent faster" → suggest smaller models, reduce allowed-tools, tighten permissions
majiayu000/claude-skill-registry 163
-
research-questions
Formulate research questions using FINER criteria (Feasible, Interesting, Novel, Ethical, Relevant). Use when: (1) Starting new research projects, (2) Refining study scope, (3) Grant proposal development, (4) Ensuring research question quality.
majiayu000/claude-skill-registry 163
-
byethrow
Reference the byethrow documentation to understand and use the Result type library for error handling in JavaScript/TypeScript. Access detailed API references, practical usage examples, and best practice guides.
majiayu000/claude-skill-registry 163
-
student-success-scorecard
Metrics framework for monitoring engagement, progression, and completion.
majiayu000/claude-skill-registry 163
-
reviewing
Get second opinions from external models (Codex, Gemini) for adversarial review, tie-breaking, and multi-model consensus. Use when validating critical decisions or when stuck.
majiayu000/claude-skill-registry 163
-
multi-system-sso-authentication
Implement enterprise Single Sign-On (SSO) authentication supporting multiple identity providers with JWT RS256 tokens, backwards verification, session management, and cross-system permission mapping. Use this skill when building authentication systems that integrate with multiple enterprise SSO providers or when implementing secure token validation with session verification.
majiayu000/claude-skill-registry 163
-
pathml
Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.
majiayu000/claude-skill-registry 163
-
gh-repo-bootstrap
Create a new GitHub repository with the gh CLI and bootstrap a local project in ~/projects with git init, README, remote setup, and initial push. Use when the user asks to create a repo (public/private) in their account, set up the local folder, add the upstream remote, and push the first commit.
majiayu000/claude-skill-registry 163
-
generate-image
Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that isn't a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.
majiayu000/claude-skill-registry 163
-
review-changes-java
Systematic code review workflow to evaluate changes against Java and Spring standards. Use when reviewing Pull Requests, commits, or diffs. Ensures robustness, maintainability, and adherence to best practices.
majiayu000/claude-skill-registry 163