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.
Seedance 视频生成
使用 Bytedance Seedance 模型生成视频。支持文生视频（带音频）、图生视频、参考图生视频。当用户想要生成视频、使用图片生成视频、保持人物一致性、或提到 seedance 时使用此 skill。
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
stock-watchlist
Query real-time stock prices, basic quote fields, and manage a Markdown watchlist for A-share, Hong Kong, and US stocks. Use when users ask in Chinese or by ticker/code to search stocks, inspect current price and quote basics, or maintain a watchlist stored in a Markdown file.
ocr
Extract text from images using Tesseract OCR
nanobanana
Generate and edit images using Google Gemini 3 Pro Image (Nano Banana Pro). Supports text-to-image, image editing, various aspect ratios, and high-resolution output (2K/4K).
biorxiv-database
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
image-enhancer
This skill improves image quality by upscaling resolution, sharpening details, and reducing compression artifacts. It's designed specifically for screenshots and digital images used in documentation, blog posts, and social media. The tool preserves original files and supports batch processing of multiple images at once.
audit-claude-md
This tool audits CLAUDE.md files to enforce best practices like line limits, clear language, and required sections. It provides specific refactoring advice and quality scoring. Useful for teams maintaining multiple CLAUDE.md files.
storage-zk
This skill provides clear guidance for using the `wiki` CLI wrapper around zk note-taking tools. It explains when to use `wiki` vs direct `zk` commands, offers practical workflow examples, and covers export formats. The documentation helps avoid common pitfalls like incorrect path handling.
Hook Development
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
create-agent-skills
This skill teaches developers how to create Claude Skills using a structured router pattern. It provides clear guidance on organizing SKILL.md files, separating workflows from references, and using XML tags instead of markdown headings. The skill emphasizes progressive disclosure to keep prompts manageable.
epic-sprints
This skill breaks down epic workflows into parallelizable sprints with dependency analysis. It generates sprint plans with execution layers, locks API contracts for parallel work, and creates task assignments. The tool focuses on optimizing workflow by identifying which sprints can run simultaneously while respecting dependencies.
agent-coordination
Provides structured guidance for assigning tasks to specialized agents, managing blockers, and coordinating multi-agent workflows. Includes clear escalation protocols, pre-implementation gates, and evidence attachment templates for Linear tickets.
workflow-orchestrator
A comprehensive workflow orchestration expert with extensive coverage of process patterns, state management, and error handling, designed for complex business process automation with strong practical value.
knowledge-synthesizer
A specialized agent for extracting insights from multi-agent interactions. It analyzes workflows, identifies patterns, and builds a knowledge graph to suggest improvements. It integrates with vector and graph databases to store and retrieve learnings.
using-git-worktrees
A skill for creating isolated git worktrees with systematic directory selection and safety checks. Automatically detects project type, runs setup commands, verifies tests pass, and ensures worktree directories are properly gitignored to prevent accidental commits.
using-git-worktrees
A well-structured skill for creating isolated Git worktrees with smart directory selection, safety verification, and automated project setup for parallel feature development.
claude-code-agents
Provides a reference framework for creating Claude Code agents with YAML frontmatter configuration. Defines agent structure, tool permissions, model selection, and includes hook system for pre/post-processing. Offers templates for different agent types like analyzers, implementers, and orchestrators.
ethicist-analyst
This skill analyzes ethical dilemmas and decisions using established moral frameworks like deontology and consequentialism, providing structured reasoning for technology, policy, and professional conduct issues.
fact-check
Verify technical accuracy of JavaScript concept pages by checking code examples, MDN/ECMAScript compliance, and external resources to prevent misinformation
zapier-workflows
This skill bridges Zapier's MCP tools with webhook-triggered Zaps, providing persistent memory for workflow preferences. It solves the gap between one-off actions and multi-step automations by storing trigger phrases, webhook URLs, and tool patterns in editable reference files. Users can trigger complex Zaps via curl commands and maintain consistent tool usage across sessions.
parallel-workflows
This skill identifies independent tasks in Claude Code and runs them concurrently using the Task tool. It provides clear patterns for parallel analysis, testing, and component development, with practical examples and performance metrics showing 55-67% speed improvements.
implementation-phase
Executes implementation tasks using Test-Driven Development, prevents code duplication through anti-duplication checks, and maintains quality through continuous testing. Use when implementing features from tasks.md, during the /implement phase, or when the user requests TDD-based implementation. (project)
session-boundary
This skill manages Claude's context window boundaries for long-running autopilot workflows. It automatically detects when context is about to be compacted, generates handoff documents, restores state after context restoration, and tracks session metrics. It integrates with Spec Flow workflows through hooks and command-line tools.