ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
swarm
N coordinated agents on shared task list with SQLite-based atomic claiming
majiayu000/claude-skill-registry 163
-
architecture-validate-srp
Detect Single Responsibility Principle (SRP) violations using multi-dimensional analysis.
Use when reviewing code for "SRP", "single responsibility", "god class", "doing too much",
"too many dependencies", before commits, during refactoring, or as quality gate.
Analyzes Python, JavaScript, TypeScript files with AST-based detection, metrics (TCC, ATFD, WMC),
and project-specific patterns. Provides actionable fix guidance with refactoring estimates.
majiayu000/claude-skill-registry 163
-
er-diagram-and-data-modeling
[STUB - Not implemented] Entity-relationship diagrams and data modeling for database schema design. PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]
majiayu000/claude-skill-registry 163
-
propose-feature-design
Create or update feature technical design document with architecture and implementation guidance
majiayu000/claude-skill-registry 163
-
flesh-out
flesh out our plan by filling in gaps and clearly building out the specfification
majiayu000/claude-skill-registry 163
-
chaos-compounding
Iteration 2 of Multiplicity Cascade - Amplifies jank recursively through iterations
majiayu000/claude-skill-registry 163
-
pre-push-quality-checks
PR作成・git push前に必ず使用。bun install → fix → format → type → lint を順番に実行。
majiayu000/claude-skill-registry 163
-
liveview-patterns
Phoenix LiveView UI and real-time feature patterns
majiayu000/claude-skill-registry 163
-
railstart-preset-builder
Guide for creating railstart preset configuration files. Use when building new presets, customizing Rails 8 app generation, creating team-specific configurations, or defining opinionated Rails stacks. Covers YAML structure, ID-based merging, post-action configuration, and testing presets for the railstart gem.
majiayu000/claude-skill-registry 163
-
wp-gutenberg-blocks
Use when developing WordPress (Gutenberg) blocks: block.json metadata, register_block_type, attributes/serialization, supports, dynamic rendering (render.php), deprecations/migrations, InnerBlocks, viewScript/viewScriptModule, and @wordpress/scripts build workflows.
majiayu000/claude-skill-registry 163
-
evaluation-harness
Builds repeatable evaluation systems with golden datasets, scoring rubrics, pass/fail thresholds, and regression reports. Use for "LLM evaluation", "testing AI systems", "quality assurance", or "model benchmarking".
majiayu000/claude-skill-registry 163
-
tzurot-tooling
Use when adding CLI commands, dev scripts, or tooling utilities. Covers the ops CLI structure, where scripts belong, and standardized commands for linting/testing.
majiayu000/claude-skill-registry 163
-
oe-llm-provider-toggle
Switch OpenEvent-AI between OpenAI, Gemini, hybrid, or stub LLM modes via environment variables or the /api/config/llm-provider admin endpoints. Use when Codex/Claude needs to verify or change AGENT_MODE, INTENT/ENTITY/VERBALIZER providers, or OE_LLM_PROFILE settings.
majiayu000/claude-skill-registry 163
-
cloudflare-hyperdrive
Connect Workers to PostgreSQL/MySQL with Hyperdrive's global pooling and caching. Use when: connecting to existing databases, setting up connection pools, using node-postgres/mysql2, integrating Drizzle/Prisma, or troubleshooting pool acquisition failures, TLS errors, or nodejs_compat missing. Prevents 11 documented errors.
majiayu000/claude-skill-registry 163
-
memex-search
Search, filter, and retrieve Claude/Codex history indexed by the memex CLI. Use when the user wants to index history, run lexical/semantic/hybrid search, fetch full transcripts, or produce LLM-friendly JSON output for RAG.
majiayu000/claude-skill-registry 163
-
bio-workflows-hic-pipeline
End-to-end Hi-C analysis workflow from contact pairs to compartments, TADs, and loops. Covers cooler matrices, cooltools analysis, and visualization. Use when processing Hi-C data to compartments and TADs.
majiayu000/claude-skill-registry 163
-
hypothesis
Use Hypothesis for property-based testing to automatically generate comprehensive test cases, find edge cases, and write more robust tests with minimal example shrinking. Includes Polars parametric testing integration.
majiayu000/claude-skill-registry 163
-
task-wrapup
Comprehensive work session wrap-up orchestrator that generates summaries, sends notifications across multiple channels (email, SMS, Slack), logs work time, and updates project documentation
majiayu000/claude-skill-registry 163
-
agent-o-rama
Layer 4: Learning and Pattern Extraction for Cognitive Surrogate Systems
majiayu000/claude-skill-registry 163
-
codex-qa
Use OpenAI Codex CLI to answer questions about code, analyze files, or perform read-only codebase exploration. Invoke this skill when the user asks to use Codex, wants a second opinion from another AI agent, or wants to compare Claude's answer with Codex's response.
majiayu000/claude-skill-registry 163
-
task-classifier
Classify task complexity (1-10) to route to optimal model. Use when starting any non-trivial task to determine resources and approach. Triggers include: 'classify', 'complexity', 'what model', 'how complex'.
majiayu000/claude-skill-registry 163
-
base44-sdk
Use for writing JavaScript/TypeScript code with the Base44 SDK in EXISTING projects. Triggers: user wants to implement features, build functionality, or write code using Base44; code uses '@base44/sdk' imports; user mentions SDK methods like base44.entities, base44.auth, base44.agents, base44.functions, base44.integrations; user says 'add a feature', 'implement', 'build component', 'write code for'. NOT for: creating new projects, CLI commands (npx base44 create/deploy/login), or directories without base44/config.jsonc - use base44-cli instead.
majiayu000/claude-skill-registry 163
-
setup-claude-md
Create comprehensive CLAUDE.md files with tech stack, standard commands, repository structure, and boundaries to optimize repositories for AI-assisted development
majiayu000/claude-skill-registry 163
-
agentdb-reinforcement-learning-training
AgentDB Reinforcement Learning Training operates on 3 fundamental principles:
majiayu000/claude-skill-registry 163