ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
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
-
redis-cache
Implement or debug Redis caching strategies using the centralized Upstash Redis client. Use when adding cache layers, debugging cache issues, or optimizing cache invalidation.
majiayu000/claude-skill-registry 163
-
baseline-restorer
Use when multiple fix attempts fail and you need to systematically restore to a working baseline and reimplement instead of fixing broken code.
majiayu000/claude-skill-registry 163
-
overnight-development
Automates software development overnight using git hooks to enforce test-driven Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
majiayu000/claude-skill-registry 163
-
ai-code-cleanup
Remove AI-generated code slop from branches. Use after AI-assisted coding sessions to clean up defensive bloat, unnecessary comments, type casts, and style inconsistencies. Focuses on identifying and removing AI artifacts that degrade code quality.
majiayu000/claude-skill-registry 163
-
ddd-validator
Validate DDD architecture compliance including layer separation, dependency rules, and patterns. Use when validating context before commit, checking new features, reviewing refactored code, or ensuring layer isolation (e.g., "Validate User context", "Check Product domain layer").
majiayu000/claude-skill-registry 163
-
sss-blog
SSS Blogプロジェクトの運用スキル。ブログ記事作成、短編小説作成、サムネイル追加、プロジェクト構造の理解、デプロイ作業を支援します。記事追加、コンテンツ作成、Git操作、プロジェクトについての質問に対応します。
majiayu000/claude-skill-registry 163
-
smartspec
AI-Ready requirements specification generator that transforms vague ideas into professional specification documents deliverable to AI development tools (BMAD Story Format and GitHub Spec-Kit Format) through intelligent guided conversations. Use this when users need to create requirement specifications, product requirements documents (PRD), user stories, or AI-ready development documentation.
majiayu000/claude-skill-registry 163
-
agent-repair
A two-phase repair skill that analyzes errors and suggests fixes before executing repairs. Phase one: user describes error, agent analyzes and proposes solution. Phase two: upon approval, executes the repair action.
majiayu000/claude-skill-registry 163
-
skills-registry-organization
Pattern for organizing Skills Registry as a shared submodule across projects
majiayu000/claude-skill-registry 163
-
refactoring-catalog
Identifies code smells and applies refactoring techniques from Martin Fowler's catalog. Use when improving code structure, reducing complexity, or eliminating smells without changing behavior.
majiayu000/claude-skill-registry 163
-
GDScript Validate
Validate GDScript changes by refreshing Godot cache and checking diagnostics. Use after creating or editing GDScript files.
majiayu000/claude-skill-registry 163
-
brainstorm-acceptance-test
Gather examples for the acceptance test; use when we are about to start development of a new feature
majiayu000/claude-skill-registry 163
-
aico-pm-user-story-writing
Transform requirements into well-structured User Stories using "As a [user], I want [goal], So that [benefit]" format with Given/When/Then acceptance criteria.
Use this skill when:
- User asks to "write user story", "create story", "add story"
- User mentions "user story", "backlog item", "story"
- Running /pm.plan and need to break PRD into implementable stories
- Creating backlog items for development team
- Need to formalize a requirement into standard story format
- Converting feature request into actionable story with acceptance criteria
Output: ALWAYS write story files to docs/reference/pm/stories/{story-name}.md
majiayu000/claude-skill-registry 163
-
birdmate
APM project for birdmate
majiayu000/claude-skill-registry 163
-
tacosdedatos-editor
Use this skill to perform comprehensive editorial reviews of tacosdedatos content. Provides developmental editing (structure, flow, argument strength, pacing) and voice authenticity editing (ensuring content sounds like tacosdedatos, not generic AI). Use when reviewing drafts, giving feedback on submissions, or evaluating content before publication. Distinct from the writer skill (creates content) and copy-editor agent (grammar/mechanics polish).
majiayu000/claude-skill-registry 163
-
svelte-game-writer
End-to-end planning, building, and testing of small-scale browser games in SvelteKit + TypeScript running in Docker, including scaffolding, game loop, input, UI, tests, and Docker dev/release setups. Use when a user asks to create or modify a SvelteKit game project, prototype a simple single-player game, or add tests. When requirements are unclear, ask clarifying questions and offer to choose defaults automatically if the user prefers. This skill uses SvelteKit+TS in Docker only (debug hot-reload + nginx release); do not switch stacks unless the user explicitly asks to change scope. Not for multiplayer, servers, or backend services.
majiayu000/claude-skill-registry 163
-
repo-docs-wiki
Generate and maintain DeepWiki-style documentation for code repositories. Use when the user asks to generate docs for a repo, create full documentation, build a wiki for a codebase, create DeepWiki-style docs, sync docs with code, update documentation, refresh the wiki, or bring docs up to date. Creates structured markdown docs (ARCHITECTURE, INTERFACES, DEVELOPER_GUIDE, INDEX, concepts, module READMEs) without modifying source code.
majiayu000/claude-skill-registry 163
-
asciinema-streaming-backup
Real-time asciinema recording backup to GitHub orphan branch with idle-based chunking and brotli archival. TRIGGERS - streaming backup, recording backup, asciinema backup, continuous recording, session backup, orphan branch recording, zstd streaming, chunked recording, real-time backup, github recording storage.
majiayu000/claude-skill-registry 163
-
branch-pusher
Push branches to remote repository with safety checks and force-with-lease support
majiayu000/claude-skill-registry 163
-
evidence-draft
Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance.
**Trigger**: evidence draft, evidence pack, claim candidates, concrete comparisons, evidence snippets, provenance, 证据草稿, 证据包, 可引用事实.
**Use when**: `outline/subsection_briefs.jsonl` exists and you want evidence-first section drafting where every paragraph can be backed by traceable citations/snippets.
**Skip if**: `outline/evidence_drafts.jsonl` already exists and is refined (no placeholders; >=4 comparisons per subsection; `blocking_missing` empty).
**Network**: none (richer evidence improves with abstracts/fulltext).
**Guardrail**: NO PROSE; do not invent facts; only use citation keys that exist in `citations/ref.bib`.
majiayu000/claude-skill-registry 163
-
ado-multi-project
Expert at organizing specs and splitting tasks across multiple Azure DevOps projects. Handles project-per-team, area-path-based, and team-based architectures. Intelligently maps increments and specs to correct projects based on content analysis. Activates for multi-project Azure DevOps setups, task splitting, spec organization, team allocation, cross-project coordination.
majiayu000/claude-skill-registry 163
-
opencode-cli
This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode ollama", "opencode local models", "opencode deepseek", "opencode kimi", "opencode mistral", "fallback cli tool", or "headless llm cli". Covers command syntax, provider configuration, Vertex AI setup, MCP servers, local models, cloud providers, and subprocess integration patterns.
majiayu000/claude-skill-registry 163
-
n8n-mcp-orchestrator
Expert MCP (Model Context Protocol) orchestration with n8n workflow automation. Master bidirectional MCP integration, expose n8n workflows as AI agent tools, consume MCP servers in workflows, build agentic systems, orchestrate multi-agent workflows, and create production-ready AI-powered automation pipelines with Claude Code integration.
majiayu000/claude-skill-registry 163