Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
lebesgue-measure
Problem-solving strategies for lebesgue measure in measure theory
majiayu000/claude-skill-registry 163
-
managing-timelines
Help users set and hit realistic deadlines. Use when someone is planning project timelines, struggling to hit deadlines, dealing with timeline pressure from stakeholders, or trying to improve estimation accuracy.
majiayu000/claude-skill-registry 163
-
thinking-thought-experiment
Test ideas through hypothetical scenarios when empirical testing is impractical. Use for architecture evaluation, edge case analysis, ethics considerations, and strategy development.
majiayu000/claude-skill-registry 163
-
context7
Fetch up-to-date library documentation using Context7 API. Use this skill when the user asks for docs, examples, or help with a specific library/framework (e.g., "look up React docs", "context7 nextjs routing", "fetch docs for fastapi").
majiayu000/claude-skill-registry 163
-
skill-compliance-auditor
Validates that the generated skill adheres to the Antigravity Folder Structure and Blueprint requirements.
majiayu000/claude-skill-registry 163
-
validate-space
Validate project space structure, boilerplate docs, and consistency with ideas/
majiayu000/claude-skill-registry 163
-
tlaplus-from-source
Generate a high-level TLA+ model from source code (C, C++, Rust, etc.). Analyzes code to understand its purpose, creates abstractions, writes TLA+ specification, and proposes invariants and properties. Use when the user wants to model source code in TLA+, create a formal specification from implementation, or verify concurrent/distributed algorithms.
majiayu000/claude-skill-registry 163
-
reviewing-skills
Claude Codeスキルを公式ベストプラクティスに基づいてレビューします。SKILL.mdファイルのレビュー、スキル品質のチェック、スキル構造の検証、改善提案が必要な場合に使用します。「このスキルをレビューして」「スキル品質をチェック」「SKILL.mdを検証」「このスキルを改善」などのリクエストで起動します。
majiayu000/claude-skill-registry 163
-
koan-entity-first
Entity<T> patterns, GUID v7 auto-generation, static methods vs manual repositories
majiayu000/claude-skill-registry 163
-
humanizer-ko
Detects and corrects Korean AI writing patterns to transform text into natural human writing. Based on scientific linguistic research (KatFishNet paper with 94.88% AUC accuracy). Analyzes 19 patterns including comma overuse, spacing rigidity, POS diversity, AI vocabulary overuse, and structural monotony. Use when humanizing Korean text from ChatGPT/Claude/Gemini or removing AI traces from Korean LLM output.
majiayu000/claude-skill-registry 163
-
ordercli
Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).
majiayu000/claude-skill-registry 163
-
create-standard-component
표준 RNBT 컴포넌트를 생성합니다. 페이지가 GlobalDataPublisher로 데이터를 제어합니다.
majiayu000/claude-skill-registry 163
-
creating-apm-dashboards
This skill enables Claude to create Application Performance Monitoring (APM) dashboards. It is triggered when the user requests the creation of a new APM dashboard, monitoring dashboard, or a dashboard for application performance. The skill helps define key metrics and visualizations for monitoring application health, performance, and user experience across multiple platforms like Grafana and Datadog. Use this skill when the user needs assistance setting up a new monitoring solution or expanding an existing one. The plugin supports the creation of dashboards focusing on golden signals, request metrics, resource utilization, database metrics, cache metrics, business metrics, and error tracking.
majiayu000/claude-skill-registry 163
-
minimax-mcp-usage
Optimal patterns for MiniMax MCP tools (web_search + understand_image)
majiayu000/claude-skill-registry 163
-
Pokemon Card Analyst
Use when analyzing individual Pokemon cards, comparing card stats, evaluating attacks/abilities, or researching card rarity.
**Activates when user mentions:**
- Card names (e.g., "Pikachu ex", "Mewtwo ex")
- Card comparisons ("compare X vs Y")
- Card stats ("HP", "damage", "attacks")
- Rarity inquiries ("rarest cards", "Secret Rare")
- Strategic value ("is this card good", "tier ranking")
**Provides:** Detailed card analysis with type effectiveness, strategic value, meta positioning, and synergy recommendations. References comprehensive card database (2077 cards) and tier lists from research documentation.
**Key benefit:** Instant access to complete card statistics, competitive viability scores, and strategic recommendations from expert meta analysis.
majiayu000/claude-skill-registry 163
-
ln-630-test-auditor
Test suite audit coordinator (L2). Delegates to 5 workers (Business Logic, E2E, Value, Coverage, Isolation). Aggregates results, creates Linear task in Epic 0.
majiayu000/claude-skill-registry 163
-
speak-webhooks-events
Implement Speak webhook signature validation and event handling for language learning.
Use when setting up webhook endpoints, implementing signature verification,
or handling Speak event notifications for lessons and progress.
Trigger with phrases like "speak webhook", "speak events",
"speak webhook signature", "handle speak events", "speak notifications".
majiayu000/claude-skill-registry 163
-
convert-golang-rust
Convert Go code to idiomatic Rust. Use when migrating Go projects to Rust, translating Go patterns to idiomatic Rust, or refactoring Go codebases. Extends meta-convert-dev with Go-to-Rust specific patterns.
majiayu000/claude-skill-registry 163
-
deployment-gcp-canary-setup
Set up progressive canary deployments on GCP Cloud Run with traffic splitting, monitoring alerts, and automated rollback.
majiayu000/claude-skill-registry 163
-
freight-optimization
When the user wants to optimize freight transportation, reduce shipping costs, or improve carrier selection. Also use when the user mentions "freight management," "carrier optimization," "mode selection," "LTL/TL optimization," "freight consolidation," "load planning," or "transportation procurement." For local delivery routes, see route-optimization. For last-mile, see last-mile-delivery.
majiayu000/claude-skill-registry 163
-
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
majiayu000/claude-skill-registry 163
-
browser
Minimal Chrome DevTools Protocol tools for browser automation and scraping. Use when you need to start Chrome, navigate pages, execute JavaScript, take screenshots, or interactively pick DOM elements.
majiayu000/claude-skill-registry 163
-
headless-component-architecture
Design components that provide logic and accessibility without prescribing UI styling.
majiayu000/claude-skill-registry 163
-
map-codebase
Analyze codebase with parallel Explore agents to produce .planning/codebase/ documents. Use for brownfield project onboarding, refreshing codebase understanding after significant changes, before major refactoring, when onboarding to unfamiliar codebases, or when asked to understand codebase or analyze project structure. Creates structured documentation of stack, architecture, structure, conventions, testing, integrations, and concerns.
majiayu000/claude-skill-registry 163