ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
context-persistence
Waypoint plans methodology and session survival patterns for Claude Code. Use when working on long-running features, need to resume after context reset, want to document task progress, or need to survive session interruptions. Covers three-file structure (plan/context/tasks), SESSION PROGRESS tracking, quick resume instructions, update frequency, and context handoff patterns.
majiayu000/claude-skill-registry 163
-
Task Breakdown Specialist
Break large tasks into ADHD-friendly micro-tasks that minimize activation energy and maximize momentum. Use when feeling overwhelmed, can't start a task, or need to make progress visible. Optimized for ADHD developers with 15-minute task chunking and dopamine-driven ordering.
majiayu000/claude-skill-registry 163
-
learning-habit-formation
habit-formation for enhanced learning effectiveness and personal development.
majiayu000/claude-skill-registry 163
-
root
Manage and guide Hikaze-Model-Manager-2 Codex project work via the .codex governance system. Use when the user says "root skill" or asks to start development based on the root skill, or when asked to set up or operate .codex constitution/workflows/guidelines/jobs, manage jobs/phases/tasks with Markdown checklists, or migrate project prompts from conductor/ into .codex/.
majiayu000/claude-skill-registry 163
-
server-actions-and-routes
Next.js App Router における Server Actions と Route Handlers の使い分け、セキュリティ、および実装規約。
majiayu000/claude-skill-registry 163
-
sip-protocol-fundamentals
Use when working with SIP messages, methods, call flows, and protocol fundamentals for VoIP applications.
majiayu000/claude-skill-registry 163
-
looper-live-test
Run a live Looper-Go smoke test by creating a temporary project (PROJECT.md + to-do.json), executing looper for one iteration, observing output, and reporting results. Use when verifying looper-go behavior or demonstrating a live run.
majiayu000/claude-skill-registry 163
-
architecture-synthesis
Generate a reference architecture specification from analyzed frameworks. Use when (1) designing a new agent framework based on prior art, (2) defining core primitives (Message, State, Tool types), (3) specifying interface protocols, (4) creating execution loop pseudocode, or (5) producing architecture diagrams and implementation roadmaps.
majiayu000/claude-skill-registry 163
-
paper-question
論文のプレーンテキストを読み込み、ユーザーの質問に研究のプロとして分かりやすく回答するスキル。ユーザーが「この論文について質問」「論文の内容を教えて」「この研究の目的は？」などと指示した時に使用。Claude自身が直接回答する。
majiayu000/claude-skill-registry 163
-
account-executive
Эксперт по B2B продажам. Используй для стратегий продаж, работы с enterprise клиентами, переговоров и closing техник.
majiayu000/claude-skill-registry 163
-
typescript-async-patterns
Use when typeScript async patterns including Promises, async/await, and async iterators with proper typing. Use when writing asynchronous TypeScript code.
majiayu000/claude-skill-registry 163
-
monitoring-apis
Build real-time API monitoring dashboards with metrics, alerts, and health checks.
Use when tracking API health and performance metrics.
Trigger with phrases like "monitor the API", "add API metrics", or "setup API monitoring".
majiayu000/claude-skill-registry 163
-
twitter-poster
Posts business news, reports, and insights to Twitter/X with intelligent formatting, thread support, and media attachments
majiayu000/claude-skill-registry 163
-
add-resource
Add new learning resources (books, articles, courses, papers) to the appropriate resources.md file. Use when user mentions adding, saving, or tracking learning materials.
majiayu000/claude-skill-registry 163
-
crdt
Loro CRDT state management with loro-mirror. Use when working on files in src/lib/crdt/.
majiayu000/claude-skill-registry 163
-
codemap
Analyze codebase structure, dependencies, and changes. Use when user asks about project structure, where code is located, how files connect, what changed, or before starting any coding task. Provides instant architectural context.
majiayu000/claude-skill-registry 163
-
synthese-multi-llm
Synthèse co-fabriquée par un conseil de 3 LLMs (Claude, Gemini, Codex). Ce skill devrait être utilisé quand l'utilisateur demande une synthèse robuste, traçable et vérifiée. Il orchestre trois modèles avec des rôles experts distincts (Extracteur, Critique, Architecte) pour produire une synthèse fidèle au texte source, avec contrôle des glissements sémantiques et trail d'audit complet.
majiayu000/claude-skill-registry 163
-
install-mkdocs-template
This skill creates a complete MkDocs Material project structure for intelligent textbooks. It sets up a Conda virtual environment named 'mkdocs', installs all dependencies, generates mkdocs.yml with all Material theme options, custom CSS for branding, the social_override plugin for custom social media cards, builds the site, and deploys to GitHub Pages. Use this skill when starting a new intelligent textbook project.
majiayu000/claude-skill-registry 163
-
gemini
Gemini CLI for one-shot Q&A, summaries, and generation.
majiayu000/claude-skill-registry 163
-
oss
This skill should be used when the user asks to "create a pull request", "create PR", "open PR", "create an issue", "file an issue", "create a GitHub issue", "create a Claude Code issue", "report a bug in Claude Code", "create a Codex issue", "report a bug in Codex CLI", "create a discussion", "start a GitHub discussion", or mentions OSS contribution workflows.
majiayu000/claude-skill-registry 163
-
implementing-code-splitting
Teaches code splitting with lazy() and Suspense in React 19 for reducing initial bundle size. Use when implementing lazy loading, route-based splitting, or optimizing performance.
majiayu000/claude-skill-registry 163
-
llm-basics
LLM architecture, tokenization, transformers, and inference optimization. Use for understanding and working with language models.
majiayu000/claude-skill-registry 163
-
quality-validation
Systematic validation methodology for ResearchPacks and Implementation Plans. Provides scoring rubrics and quality gates to ensure outputs meet standards before proceeding to next phase. Prevents garbage-in-garbage-out scenarios.
majiayu000/claude-skill-registry 163
-
code-review-preferences
Use when reviewing code, PRs, or discussing code quality standards. Applies team coding standards and review methodology.
majiayu000/claude-skill-registry 163