Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
nano-pdf
This skill uses nano-pdf to edit PDF pages via natural language commands. It adds a CLI wrapper that lets Claude modify PDFs by specifying page numbers and edit instructions. The skill is specifically designed for quick text adjustments in existing PDF documents.
cloudflare-queues
Build async message queues with Cloudflare Queues for background processing. Use when: handling async tasks, batch processing, implementing retries, configuring dead letter queues, managing consumer concurrency, or troubleshooting queue timeout, batch retry, message loss, or throughput exceeded. Prevents 13 documented errors including multi-dev limitations, remote binding conflicts, and DLQ issues.
hook-development
Provides detailed guidance for implementing Claude Code plugin hooks with clear examples of prompt-based and command hooks. Includes practical testing scripts and covers all major hook events like PreToolUse, PostToolUse, and Stop. The documentation distinguishes between plugin and settings formats, helping avoid configuration errors.
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
notion
Notion API for creating and managing pages, databases, and blocks.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
code-reviewer
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
claude-opus-4-5-migration
Automates migration from older Claude models (Sonnet 4.0/4.5, Opus 4.1) to Opus 4.5 by updating model strings across multiple platforms and suggesting prompt adjustments for known behavioral differences. Handles API calls, removes unsupported beta headers, and provides platform-specific model identifiers.
feishu-user-md
飞书端读取USER.md任务清单。当用户说"查看任务"、"我的任务"时触发，实时解析并返回格式化的分类任务列表，让用户快速了解当前所有可用任务和技能。
brutal-honesty-review
A highly structured and innovative skill for delivering unfiltered technical feedback with clear modes, calibration levels, and actionable frameworks for code review, quality assessment, and BS detection.
debug-cuda-crash
Tutorial for debugging CUDA crashes using API logging
image-enhancer
This skill processes images and screenshots to improve resolution, sharpness, and clarity. It handles batch operations, preserves originals, and provides specific use cases for documentation, social media, and presentations. The tool is straightforward with clear examples for common enhancement tasks.
open-source-contributions
Create maintainer-friendly pull requests with clean code and professional communication. Prevents 16 common mistakes that cause PR rejection. Use when: contributing to open source, submitting PRs, or troubleshooting PR rejection, CI failures, or personal artifacts in commits.
search-interceptor
This skill intercepts bulk file read operations before execution and suggests using Claude Memory semantic search instead. It provides clear triggers for when to intervene, decision matrices, and practical examples to reduce token waste during code exploration.
discover-database
A gateway skill that automatically loads relevant database expertise when Claude detects SQL, NoSQL, or schema design work. It provides structured access to 8 core database skills covering PostgreSQL, MongoDB, Redis, connection pooling, ORM patterns, and database selection decisions. The skill uses progressive loading to minimize token usage while offering comprehensive coverage.
session-logs
This skill provides jq-based shell commands to search and analyze Claude conversation history stored in JSONL files. It helps users find past discussions, calculate costs, and extract specific message types from session logs located in ~/.clawdbot directories.
ruzzy
Ruzzy is a coverage-guided Ruby fuzzer by Trail of Bits. Use for fuzzing pure Ruby code and Ruby C extensions.
code-maturity-assessor
Systematic code maturity assessment using Trail of Bits' 9-category framework. Analyzes codebase for arithmetic safety, auditing practices, access controls, complexity, decentralization, documentation, MEV risks, low-level code, and testing. Produces professional scorecard with evidence-based ratings and actionable recommendations. (project, gitignored)
moai-foundation-claude
Provides the official reference documentation and templates for building Claude Code extensions. Covers skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns. Essential for developers extending Claude's capabilities.
ffmpeg-keyframe-extraction
Extract key frames (I-frames) from video files using FFmpeg command line tool. Use this skill when the user needs to pull out keyframes, thumbnails, or important frames from MP4, MKV, AVI, or other video formats for analysis, previews, or processing.
hooks-automation
Provides automated hooks for Claude Code operations including pre/post task execution, agent coordination, code formatting, and session persistence. Integrates with MCP tools for swarm management and maintains memory across development sessions. Includes Git commit validation and pattern learning from successful operations.
tdd-london-chicago
This skill guides developers through London (mock-based) and Chicago (state-based) TDD approaches with clear decision rules. It provides concrete examples, common pitfalls, and agent coordination patterns for test generation and refactoring. The quick reference card helps teams choose the right testing style based on code type.
n8n-trigger-testing-strategies
Provides concrete testing strategies for n8n workflow triggers including webhook payload validation, HTTP method testing, authentication checks, and cron schedule verification. Includes TypeScript code examples for common testing scenarios.
test-writer
Generate comprehensive Vitest tests for code examples in JavaScript concept documentation pages, following project conventions and referencing source lines