Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
systematic-testing
Use when writing tests, debugging failures, or investigating bugs - provides TDD guidance, test generation patterns, systematic debugging framework. Activates when user says "write tests", "this test fails", "debug this", mentions "TDD", "test coverage", or encounters errors/bugs.
majiayu000/claude-skill-registry 163
-
help-text-formatter
Generate formatted help text with examples, descriptions, sections, and consistent styling for CLI applications.
majiayu000/claude-skill-registry 163
-
cursor-rules
This skill should be used when creating or editing Cursor rules files (.mdc format) in the .cursor/rules directory. Provides guidance on rule types, frontmatter configuration, effective rule writing patterns, and best practices for structuring AI instructions for Cursor IDE.
majiayu000/claude-skill-registry 163
-
AOC Orchestrator
Main coordinator for the automated Advent of Code workflow. Orchestrates puzzle fetching, TDD solving, and submission for daily AoC challenges. Use when running the full automated solving pipeline or when user requests to solve an AoC day.
majiayu000/claude-skill-registry 163
-
cfn-expert-update
Update CFN system expert agent with relevant git commits and project changes
majiayu000/claude-skill-registry 163
-
copilot-handoff
Create Copilot-optimized task specifications for handoff between Claude and GitHub Copilot. Use when planning implementation tasks that Copilot will complete. Optimizes comment format, provides rich context, includes checklists and examples.
majiayu000/claude-skill-registry 163
-
android-qa-verification
This skill is used to verify Android features against acceptance criteria, catch regressions and define tests that reflect real device behaviour.
majiayu000/claude-skill-registry 163
-
troubleshooting-devbox
Use when SSH connection fails, host key mismatch, NixOS issues, or verifying devbox is properly configured
majiayu000/claude-skill-registry 163
-
windsurf-cicd-github-actions
Generate and maintain GitHub Actions with Cascade assistance. Activate when users mention
"github actions", "ci/cd pipeline", "workflow automation", "continuous integration",
or "deployment pipeline". Handles CI/CD configuration with AI assistance. Use when working with windsurf cicd github actions functionality. Trigger with phrases like "windsurf cicd github actions", "windsurf actions", "windsurf".
majiayu000/claude-skill-registry 163
-
workflow-analyzer
作業フローや手順を分析し、自動化可能な要素を特定する。ワークフロー分析時、自動化検討時、業務プロセス改善時、またはユーザーが作業フロー分析、自動化要素、業務手順、プロセス最適化に言及した際に使用する。
majiayu000/claude-skill-registry 163
-
claude-code-commands
Create slash commands for Claude Code with $ARGUMENTS handling, agent invocation patterns, and template best practices. Reference for building user-triggered workflow shortcuts.
majiayu000/claude-skill-registry 163
-
nextjs-frontend-testing
Use this skill whenever the user wants to set up, improve, or run frontend tests (unit, component, and E2E) for a Next.js (App Router) + TypeScript + Tailwind + shadcn/ui project using Vitest/Jest, React Testing Library, and Playwright.
majiayu000/claude-skill-registry 163
-
swift-localization
Best practices for internationalizing Swift/SwiftUI applications using LocalizedStringResource, String Catalogs (.xcstrings), and type-safe localization patterns. Use when implementing multi-language support, adding new UI strings, or refactoring hardcoded text in Swift apps.
majiayu000/claude-skill-registry 163
-
repo-prepare-release
Prepare releases by analyzing changelogs, determining version bumps, and updating package.json and changelog files.
majiayu000/claude-skill-registry 163
-
bash-tools
Proper usage of Bash and file operation tools. Use this skill when executing shell commands, writing files, or when tempted to use echo/cat/heredoc to pipe content to files. Prevents permission circumvention patterns like piping multiline content through echo instead of using Write tool. Covers Bash tool, Write tool, Edit tool, and Read tool best practices.
majiayu000/claude-skill-registry 163
-
ghostty-config
Guidance for editing Ghostty terminal configuration files. You must use this skill when creating or modifying Ghostty config files.
majiayu000/claude-skill-registry 163
-
mistral-core-workflow-b
Execute Mistral AI secondary workflows: Embeddings and Function Calling.
Use when implementing semantic search, RAG applications,
or tool-augmented LLM interactions.
Trigger with phrases like "mistral embeddings", "mistral function calling",
"mistral tools", "mistral RAG", "mistral semantic search".
majiayu000/claude-skill-registry 163
-
compound-engineering
Compound Engineering workflow for AI-assisted development. Use when planning features, executing work, reviewing code, or codifying learnings. Follows the Plan → Work → Review → Compound loop where each unit of engineering makes subsequent work easier. Triggers on: plan this feature, implement this, review this code, compound learnings, create implementation plan, systematic development.
majiayu000/claude-skill-registry 163
-
i18n-curator
majiayu000/claude-skill-registry 163
-
kamino
Complete guide for Kamino Finance - Solana's leading DeFi protocol for lending, borrowing, liquidity management, and leverage trading. Covers klend-sdk (lending), kliquidity-sdk (automated liquidity strategies), scope-sdk (oracle aggregator), multiply/leverage operations, vaults, and obligation orders.
majiayu000/claude-skill-registry 163
-
local-finetune
local-finetune
majiayu000/claude-skill-registry 163
-
Global Coding Style
TypeScript and Remotion-specific coding style conventions for naming, formatting, and organization. Use this when writing any TypeScript code, creating new files, naming variables/functions/types, or structuring imports. Enforces frame-based timing and path alias usage.
majiayu000/claude-skill-registry 163
-
kantra-analyze
Utilize Kantra, a CLI that unifies analysis and transformation capabilities of Konveyor, to analyze the source code of an application for violations.
majiayu000/claude-skill-registry 163
-
analyzing-tdigest-metrics
Analyze percentile metrics (tdigest type) using OPAL for latency analysis and SLO tracking. Use when calculating p50, p95, p99 from pre-aggregated duration or latency metrics. Covers the critical double-combine pattern with align + m_tdigest() + tdigest_combine + aggregate. For simple metrics (counts, averages), see aggregating-gauge-metrics skill.
majiayu000/claude-skill-registry 163