Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
policy-engine-builder
Guide for creating Gemini CLI policy engine TOML rules. Covers rule syntax, priority tiers, conditions, and MCP wildcards. Use when restricting Gemini tools, creating security policies, controlling MCP server permissions, or setting up approval workflows.
majiayu000/claude-skill-registry 163
-
japanese-grammar-master
Comprehensive Japanese grammar expert covering particles, verb conjugations, sentence patterns, and the nuances between spoken and written Japanese
majiayu000/claude-skill-registry 163
-
cpp14-code-review
AUTOSAR C++14およびCERT C++コーディング規約に準拠したC++14コードレビュー。安全性重視のC++システムのコードレビュー、セキュリティ監査、品質評価、静的解析ツール設定を行う際に使用。
majiayu000/claude-skill-registry 163
-
blog-resume
Resume work on blog posts - both in-progress drafts and published posts needing updates. Restores context when returning to continue work.
Trigger phrases: "resume", "continue", "work on", "update post", "continue working", "resume post", "continue post"
majiayu000/claude-skill-registry 163
-
commit-work
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
majiayu000/claude-skill-registry 163
-
acceptance-criteria-authoring
Write clear, testable acceptance criteria in Given-When-Then format following INVEST principles and BDD best practices.
majiayu000/claude-skill-registry 163
-
go-mod-helper
Go module system, dependency management, and project configuration assistance.
majiayu000/claude-skill-registry 163
-
code-delta
Visualize proposed code changes in a structured ASCII format with file tree, impact summary, syntax-highlighted diff, and rationale. Use this skill when proposing refactors, simplifications, or any code modifications.
majiayu000/claude-skill-registry 163
-
secure-workflow-guide
Guide you through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integration), generates visual security diagrams, helps document security properties for fuzzing/verification, and reviews manual security areas. (project, gitignored)
majiayu000/claude-skill-registry 163
-
feature-dhofheinz-open-plugins
Implement production-ready features across database, backend, and frontend layers with incremental phased approach
majiayu000/claude-skill-registry 163
-
template-mason-brick
Guide for creating, updating, or removing Mason bricks with corresponding tests and CI workflow (project)
majiayu000/claude-skill-registry 163
-
openrouter-trending-models
Fetch trending programming models from OpenRouter rankings. Use when selecting models for multi-model review, updating model recommendations, or researching current AI coding trends. Provides model IDs, context windows, pricing, and usage statistics from the most recent week.
majiayu000/claude-skill-registry 163
-
prettier-config
Prettier configuration validation and templates for package.json "prettier" field in MetaSaver monorepos. Includes 4 required standards (prettier field in package.json with string reference only, no separate prettierrc files, prettier in devDependencies, required npm scripts format and format:check). Use when creating or auditing Prettier configs to ensure consistent code formatting via shared library.
majiayu000/claude-skill-registry 163
-
track-and-field
Track & Field affiliate tracking context
majiayu000/claude-skill-registry 163
-
bmad-story-planning
Breaks epics into developer stories.
majiayu000/claude-skill-registry 163
-
eld-ground-pr-review
PCE (Process-Context Engine) を活用したPRレビュースキル。Compile→Execute→Captureのフローでレビューを行い、知見を蓄積する。
LDE(Law-Driven Engineering)との統合により、Law遵守・Grounding検証も実行。
トリガー条件:
- 「PRをレビューして」
- 「PR #123 を確認して」
- 「変更内容をチェックして」
- gh pr view の結果を見た後
- 「Law観点でレビューして」
majiayu000/claude-skill-registry 163
-
Nodes Programmatic Patterns
Build n8n nodes using programmatic style with full control over execution, data handling, and API calls. Use this skill when implementing execute() methods, creating helper functions for API requests, handling pagination with cursor-based logic, implementing loadOptions for dynamic dropdowns, processing binary data, building webhook or polling triggers, or handling complex data transformations. Apply when building trigger nodes, GraphQL integrations, non-HTTP protocols, or any scenario requiring custom execution logic.
majiayu000/claude-skill-registry 163
-
opencode-skill-generator
Generate OpenCode configuration components and skills. Use this skill when you need to create or update OpenCode agents, commands, MCP servers, plugins, tools, or full agent skills following the official opencode.json schema. Supports generating supagents, commands, mcp configs, frontmatter, plugins, and tool mappings.
majiayu000/claude-skill-registry 163
-
forensics:investigate
Guided workflow for reverse engineering black-box systems. Use when a user wants to decode a defunct API, replicate a competitor's feature, understand unfamiliar code, or crack a data format.
majiayu000/claude-skill-registry 163
-
windsurf-cascade-context
Manage Cascade context window and memory for complex projects. Activate when users mention
"cascade context", "ai memory", "context management", "large codebase navigation",
or "multi-session development". Handles context optimization and persistence. Use when working with windsurf cascade context functionality. Trigger with phrases like "windsurf cascade context", "windsurf context", "windsurf".
majiayu000/claude-skill-registry 163
-
meeting-intelligence
Prepare for meetings by gathering context and creating comprehensive agendas
majiayu000/claude-skill-registry 163
-
run-uat
Run User Acceptance Testing by creating a PR with rendered markdown on GitHub or Azure DevOps. Use when validating markdown rendering in real platforms.
majiayu000/claude-skill-registry 163
-
cargo-fuzz
cargo-fuzz is the de facto fuzzing tool for Rust projects using Cargo. Use for fuzzing Rust code with libFuzzer backend.
majiayu000/claude-skill-registry 163
-
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry 163