Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
pytdc
Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.
majiayu000/claude-skill-registry 163
-
transforming-string-methods
Write type-safe transformations with Zod including string methods, custom transforms, codecs, and pipelines
majiayu000/claude-skill-registry 163
-
agent-onboarding
Comprehensive framework for effective gptme agent onboarding that builds user trust, communicates capabilities clearly, and establishes productive working relationships from the first interaction.
majiayu000/claude-skill-registry 163
-
tailwind
Tailwind CSS v4 performance optimization and best practices guidelines (formerly tailwindcss-v4-style). This skill should be used when writing, reviewing, or refactoring Tailwind CSS v4 code to ensure optimal build performance, minimal CSS output, and correct usage of v4 features. Triggers on tasks involving Tailwind configuration, @theme directive, utility classes, responsive design, dark mode, container queries, or CSS generation optimization.
majiayu000/claude-skill-registry 163
-
red-phase
Write failing tests before implementation (RED phase of TDD). Creates test file with test functions that fail because code doesn't exist yet. Use when starting TDD workflow or adding tests for new functionality.
majiayu000/claude-skill-registry 163
-
Code Helper
Assist with code review, refactoring, and explanations. Use when analyzing or improving code.
majiayu000/claude-skill-registry 163
-
github-repo-skill
Guide for creating new GitHub repos and best practice for existing GitHub repos, applicable to both code and non-code projects
majiayu000/claude-skill-registry 163
-
model-usage
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
majiayu000/claude-skill-registry 163
-
verbump
Bump the Blackpepper version, review full git diffs (including unrelated changes), craft a Conventional Commit message, and push the current branch. Use when the user asks to "verbump", "bump version", "increment version", "release", or explicitly requests version bump + commit + push for this repo.
majiayu000/claude-skill-registry 163
-
strict-review-agent
Performs strict code review with comprehensive validation
majiayu000/claude-skill-registry 163
-
typescript-react-reviewer
Expert code reviewer for TypeScript + React 19 applications. Use when reviewing React code, identifying anti-patterns, evaluating state management, or assessing code maintainability. Triggers: code review requests, PR reviews, React architecture evaluation, identifying code smells, TypeScript type safety checks, useEffect abuse detection, state management review.
majiayu000/claude-skill-registry 163
-
ghe-requirements
This skill should be used when creating, updating, linking, or versioning requirements for GitHub Elements threads. Use when user mentions requirements, specs, REQ files, or when starting feature development. Provides the requirements folder structure, versioning system, and SERENA backup protocols.
majiayu000/claude-skill-registry 163
-
reviewing-site-structures
analyze-websiteスキルで作成したワイヤーフレームとサイトマップを入力として、サイト全体の構造分析・問題点の特定・改善提案を行います。情報アーキテクチャ、ユーザーフロー、コンテンツギャップの観点から包括的にレビューします。
majiayu000/claude-skill-registry 163
-
code-hardcode-audit
Detects hardcoded values, magic numbers, duplicate constants, and leaked secrets using Ruff, Semgrep, jscpd, and gitleaks. Use when auditing for hardcodes, magic numbers, PLR2004, constant detection, secret scanning, or before release.
majiayu000/claude-skill-registry 163
-
qa-refactoring
Systematic refactoring patterns, code smell detection, technical debt management, automated code quality gates, and legacy code modernization strategies for maintainable codebases.
majiayu000/claude-skill-registry 163
-
Plugin Installation
Use when the user wants to install, update, or set up a Claude Code plugin
majiayu000/claude-skill-registry 163
-
source-map-setup
Configure source maps for readable stack traces. Use when setting up error tracking, debugging production issues, or configuring build tools.
majiayu000/claude-skill-registry 163
-
react-native-deployment
Master deployment - EAS Build, Fastlane, App Store, Play Store, and OTA updates
majiayu000/claude-skill-registry 163
-
learning-dashboard-builder
dashboard-builder for measuring learning effectiveness and business impact.
majiayu000/claude-skill-registry 163
-
pdf
Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.
majiayu000/claude-skill-registry 163
-
scanning-git-for-tils
Scans GitHub commit history for commits that might make good TIL blog posts. Queries all your repos across all orgs via GitHub API. Tracks assessed commits in Notion to avoid duplicates across machines. Use when user asks for TIL ideas from their recent work.
majiayu000/claude-skill-registry 163
-
Geo-Risk Assessment
Assess country and jurisdiction risk levels for compliance purposes
majiayu000/claude-skill-registry 163
-
forensic-analyst
Use this skill when users need to conduct digital forensics investigations, perform timeline reconstruction, analyze memory dumps, examine artifacts, or build comprehensive forensic reports using LimaCharlie's forensic capabilities.
majiayu000/claude-skill-registry 163
-
bear-notes
Create, search, and manage Bear notes via grizzly CLI.
majiayu000/claude-skill-registry 163