Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
create-qa-task
Use to create QA task documents. Generates test specifications and validation requirements for QA team.
majiayu000/claude-skill-registry 163
-
observability-design
Monitoring strategies, distributed tracing, SLI/SLO design, and alerting patterns. Use when designing monitoring infrastructure, defining service level objectives, implementing distributed tracing, creating alert rules, building dashboards, or establishing incident response procedures. Covers the three pillars of observability and production readiness.
majiayu000/claude-skill-registry 163
-
ops-claude
Claude Code maintenance and diagnostics. Check inotify limits, clean caches, diagnose startup failures, and manage skills directories across projects.
majiayu000/claude-skill-registry 163
-
openwebf-host-caching-httpcachemode
Configure and debug WebF runtime caching in Flutter using HttpCacheMode (stale content, offline-first, cache busting, clearing caches with WebF.clearAllCaches). Use when the user mentions HttpCacheMode, WebF.clearAllCaches, offline-first, stale remote bundles, or cache adapter behavior.
majiayu000/claude-skill-registry 163
-
db-designer
Generate database schema from feature descriptions. User doesn't see SQL.
Use when: features require data persistence.
Triggers: internal use only.
majiayu000/claude-skill-registry 163
-
oxfmt-oxlint
OXFMT-OXLINT documentation assistant
majiayu000/claude-skill-registry 163
-
HyperIndex Development
This skill should be used when the user asks to "create an indexer", "build a hyperindex", "index blockchain events", "write event handlers", "configure config.yaml", "define schema.graphql", "use envio", "set up hyperindex", "index smart contract events", "create graphql schema for blockchain data", or mentions Envio, HyperIndex, blockchain indexing, or event handler development.
majiayu000/claude-skill-registry 163
-
setup-typescript-project
majiayu000/claude-skill-registry 163
-
article-creation
新規ブログ記事の作成。「記事を書きたい」「新しい記事を作成」「ブログ投稿」などのリクエスト時に使用。
majiayu000/claude-skill-registry 163
-
understanding-saleor-domain
Explains Saleor e-commerce domain and Configurator business rules. Covers entity identification (slug vs name), deployment pipeline stages, and configuration schema. Triggers on: entity types, deployment pipeline, config schema, slug identification, categories, products, channels, YAML configuration.
majiayu000/claude-skill-registry 163
-
log-validator
Validates logs against type-specific schemas checking frontmatter, structure, and required fields
majiayu000/claude-skill-registry 163
-
file-archiver
创建和解压ZIP、TAR和GZIP压缩包,支持密码保护。
majiayu000/claude-skill-registry 163
-
deepwork_rules
Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code review triggers.
majiayu000/claude-skill-registry 163
-
datadog-cli
Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.
majiayu000/claude-skill-registry 163
-
comp-scout-persist
[DEPRECATED] Persistence logic has been merged into comp-scout-scrape. This skill remains for reference only.
majiayu000/claude-skill-registry 163
-
better-skill-builder
Build SKILL.md files for Claude Code, Codex, Amp, OpenCode. Production examples and patterns for skill structure, scripts, distribution, and making CLI tools AI-native.
majiayu000/claude-skill-registry 163
-
sec-context-depth
Comprehensive AI code security review using 27 sec-context anti-patterns. Use for code review when security vulnerabilities are suspected, especially for AI-generated code.
majiayu000/claude-skill-registry 163
-
Enforcing pnpm
Ensure pnpm is used exclusively for package management, blocking npm/yarn commands. Use when running package scripts, installing dependencies, or when user mentions package manager/依存関係/パッケージ.
majiayu000/claude-skill-registry 163
-
researching-web-sources
Strategic web research using WebSearch and WebFetch - finds accurate, relevant information with multiple search angles, prioritizes authoritative sources, synthesizes findings with proper attribution.
majiayu000/claude-skill-registry 163
-
human-extractor
GPU-accelerated pipeline for detecting, tracking, and classifying humans in dashcam footage. This skill should be used when users need to extract human presence from videos, analyze dashcam footage for people detection, perform investigative analysis of human subjects in recordings, or classify individuals with optional head covering detection.
majiayu000/claude-skill-registry 163
-
loop-vectorizer
Convert Python loops to vectorized PyTorch tensor operations for performance. This skill should be used when optimizing computational bottlenecks in PyTorch code during Phase 4 performance optimization.
majiayu000/claude-skill-registry 163
-
war-room-ops
Use when running launch command centers, standups, and escalation workflows.
majiayu000/claude-skill-registry 163
-
train-test-splitter
Train Test Splitter - Auto-activating skill for ML Training.
Triggers on: train test splitter, train test splitter
Part of the ML Training skill category.
majiayu000/claude-skill-registry 163
-
cognitive-surrogate
Layer 6 Barton Cognitive Surrogate - build, train, validate psychological models with >90% fidelity
majiayu000/claude-skill-registry 163