ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
script-executor
Executes shell scripts in a safe environment.
majiayu000/claude-skill-registry 163
-
typescript-expert-2025
Expert TypeScript development patterns and tooling for December 2025. Use when (1) Setting up modern TypeScript projects with Bun, Node 22+, or Deno, (2) Configuring tsconfig, ESM/CJS dual publishing, or build tooling, (3) Implementing advanced type patterns like satisfies, as const, template literals, mapped types, (4) Choosing between Biome, Oxlint, or ESLint for linting, (5) Optimizing TypeScript performance, or any expert-level TypeScript architecture questions.
majiayu000/claude-skill-registry 163
-
module-exports
Module export patterns including factory functions and public API design
majiayu000/claude-skill-registry 163
-
chrome-extension-wxt
Build Chrome extensions using WXT framework with TypeScript, React, Vue, or Svelte. Use when creating browser extensions, developing cross-browser add-ons, or working with Chrome Web Store projects. Triggers on phrases like "chrome extension", "browser extension", "WXT framework", "manifest v3", or file patterns like wxt.config.ts.
majiayu000/claude-skill-registry 163
-
production-validator
AI video pipeline validator for Veo 3 feasibility, 8-second scene chunking, and shot continuity.
USE WHEN: Validating screenplays for AI video generation, chunking scenes into 8-second segments, generating continuation prompts, scoring feasibility risk, or adding editing metadata.
PIPELINE POSITION: screenwriter → **production-validator** → imagine/arch-v
INPUT: XML from screenwriter skill (scene tags with duration, action, key_visuals) OUTPUT: Enhanced XML with validation, chunks, continuity tags, and Veo 3 prompts
KEY FUNCTIONS: - Veo 3 feasibility validation with risk scoring (LOW/MEDIUM/HIGH/CRITICAL) - 8-second scene chunking with continuation prompts - Shot continuity tagging for editors - Technical optimization for AI-friendly alternatives
majiayu000/claude-skill-registry 163
-
zig-system-calls
Guides using bun.sys for system calls and file I/O in Zig. Use when implementing file operations instead of std.fs or std.posix.
majiayu000/claude-skill-registry 163
-
manage-markdown-docs
Standardize markdown document creation and updates with proper headers and footers. Use when creating OR updating any markdown file that is NOT a subagent, command, or skill definition. Ensures consistent metadata, classification, and change tracking.
majiayu000/claude-skill-registry 163
-
web-quality-audit
Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".
majiayu000/claude-skill-registry 163
-
slime-lisp
SLIME integration for Common Lisp development
majiayu000/claude-skill-registry 163
-
hammer-quality-check
Runs comprehensive code quality checks for SDL3 HammerEngine including compilation warnings, static analysis (cppcheck, clang-tidy), coding standards validation, threading safety verification, and architecture compliance. Use before commits, pull requests, or when the user wants to verify code meets project quality standards.
majiayu000/claude-skill-registry 163
-
cronologia
Guardián de la cronología SyV - valida coherencia temporal, previene contradicciones, mantiene perspectiva 2178
majiayu000/claude-skill-registry 163
-
graphic-design-expert
Comprehensive design engine for UI/UX, Print, and Social Media. Includes automated image resizing tools, contrast calculators, and 2026 strategic frameworks.
majiayu000/claude-skill-registry 163
-
memory-safety-patterns
Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.
majiayu000/claude-skill-registry 163
-
agentic-eval
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when:
- Implementing self-critique and reflection loops
- Building evaluator-optimizer pipelines for quality-critical generation
- Creating test-driven code refinement workflows
- Designing rubric-based or LLM-as-judge evaluation systems
- Adding iterative improvement to agent outputs (code, reports, analysis)
- Measuring and improving agent response quality
majiayu000/claude-skill-registry 163
-
managing-sc-packages
List, install, or uninstall Synaptic Canvas packages. Use with the `/sc-manage` command.
majiayu000/claude-skill-registry 163
-
pihole-dns-setup
Configures Pi-hole local DNS records to enable local network resolution of *.temet.ai
domains. Use when you need to set up DNS, add local DNS entries, configure Pi-hole DNS,
troubleshoot DNS resolution, or make services resolve locally. Triggers on "setup DNS",
"configure Pi-hole DNS", "add DNS record", "DNS not resolving", "local DNS setup", or
"why can't I access [service].temet.ai locally". Works with Pi-hole container, domains.toml,
docker-compose.yml, and manage-domains.sh.
majiayu000/claude-skill-registry 163
-
contributor-analyzer
Analyzes engineering contributors for annual reviews, progress tracking, and production ownership. Reads every commit diff (not sampling), calculates accuracy rates, assesses engineering maturity through qualitative judgment, and generates promotion-ready performance reviews. Works with any git repository using local git for commit analysis and gh CLI for GitHub PR/review metadata.
majiayu000/claude-skill-registry 163
-
plan-code-workflow
Plan/Code workflow for moderate to complex tasks. Defines when to use Plan vs Code mode. Applied automatically for non-trivial implementations.
majiayu000/claude-skill-registry 163
-
evergreen
Principles for creating evergreen notes - atomic, lasting insights that compound over time. Use when discussing note quality, what makes a good evergreen note, or the "only what was explored" principle. Tool-agnostic concepts that apply regardless of note-taking app.
majiayu000/claude-skill-registry 163
-
anvil
Heavy-duty "No-Vibes" debugging and hardening orchestrator. Use this for complex, stubborn bugs where `review-code` has failed, or for "Red Teaming" (hardening) a codebase. Runs multiple agents in parallel (Thunderdome) using git worktree isolation.
majiayu000/claude-skill-registry 163
-
lightfriend-add-frontend-page
Step-by-step guide for adding new pages to the Yew frontend
majiayu000/claude-skill-registry 163
-
gsap-greensock
Use when implementing Disney's 12 animation principles with GSAP (GreenSock Animation Platform)
majiayu000/claude-skill-registry 163
-
neo
Give your OpenClaw the power of the Matrix. Download expertise directly into your AI's mind. 119 modules. 15 categories. Instant mastery.
"I know kung fu."
Physicists. Negotiators. VCs. Psychologists. Surgeons. Game theorists. The library keeps growing — or build your own.
Free your mind.
majiayu000/claude-skill-registry 163
-
database-expert-advisor
Database design, optimization, and operations expert
majiayu000/claude-skill-registry 163