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.
doc-splitter
A sophisticated skill for intelligently splitting massive documentation sites into manageable sub-skills with router-based navigation, featuring excellent structure and mitigation strategies.
impl
A Claude Skill focused on implementing features and writing code with built-in quality guardrails. It emphasizes purpose-driven implementation over stub code, integrates LSP tools for code navigation, and includes TDD recommendations. The skill prevents common anti-patterns like hardcoding test values and provides self-check questions before implementation.
flow-tdd
Enforces strict TDD discipline within the flow-dev workflow. It mandates writing failing tests before any production code, provides clear protocols for the TDD cycle, and integrates error logging with attention refresh protocols to prevent regression. The skill includes rationalization prevention tables and concrete examples.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
browsing-with-playwright
This skill provides a wrapper around the official Playwright MCP server for browser automation. It includes helper scripts for server lifecycle management, a Python client for tool invocation, and detailed workflows for common tasks like form submission and data extraction. The documentation clearly explains when to use it versus static content tools.
skills-proficiency-mapper
A Claude skill that maps educational skills to CEFR/Bloom's/DigComp proficiency levels with validation. It prevents skill fragmentation across curriculum chapters by checking for naming consistency, progression coherence, and prerequisite satisfaction. Useful for curriculum designers creating structured learning paths.
format-todo-list
Converts todo items into TodoWrite-compatible format by adding activeForm fields based on content. Handles status validation and provides clear error messages for invalid inputs. Useful for orchestrators needing consistent todo formatting.
fabric
This skill intelligently selects from 242+ Fabric CLI patterns for text processing tasks like threat modeling, summarization, and analysis. It maps user intent to specific patterns and provides clear execution commands with examples for different input sources.
shell-scripting
Provides concrete guidance for writing reliable bash scripts with defensive programming patterns. Covers when to use shell vs other languages, mandatory safety practices, common pitfalls, and practical templates. Emphasizes ShellCheck compliance, proper error handling, and simplicity over complexity.
ispc-lit-tests
Provides specific guidelines for writing lit tests for the ISPC compiler, focusing on regression testing, code generation verification, and diagnostic checking. Includes practical examples for portable patterns, target-specific tests, and intermediate IR inspection.
skill-developer
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
voice-blend
A sophisticated voice blending tool that enables weighted combination of multiple writing style profiles with clear algorithms for tone, vocabulary, and structure interpolation.
skill-enhancer
This skill automatically improves SKILL.md files by extracting examples from reference documentation, adding quick references and FAQs. It provides multiple enhancement modes including local Claude Code, API-based, and manual templates with backup and validation workflows.
devflow-file-standards
Defines file naming, directory structure, and YAML frontmatter conventions for a multi-agent development workflow. It standardizes IDs, paths, and status tracking across 13 agents, ensuring consistency without duplicating agent-specific content rules. The skill acts as a central reference for format standards.
devflow-constitution-quick-ref
Provides a quick reference guide to the CC-DevFlow Constitution v2.0.0, summarizing all 10 articles and Phase -1 gates with key rules, enforcement mechanisms, and scenario-based lookups. Links to the full constitution document rather than duplicating content, following the 'no duplication' principle.
prompting
Provides concrete guidelines for writing effective prompts and managing context for AI agents. Focuses on clarity, signal-to-noise optimization, and just-in-time information loading based on Anthropic's best practices.
code-changelog
Automatically logs AI-generated code changes to markdown files in a 'reviews' folder and serves them via a simple Python HTTP server with an auto-updating HTML viewer. Provides real-time documentation of incremental development steps.
caching-strategy
Cache expensive operations to avoid redundant work across workflow phases. Caches project docs (15min TTL), npm info (60min), grep results (30min), token counts (until file modified), web searches (15min). Auto-triggers when detecting repeated reads of same files or repeated API calls. Saves 20-40% execution time.
help-center-design
Provides structured templates and modern best practices for designing AI-first help centers and knowledge bases. Includes decision matrices, platform comparisons, implementation checklists, and metrics for 2025-2026 self-service systems.
xhs-writing-coach
Coach and generate Xiaohongshu (小红书/RedNote/XHS) note writing. Use when the user wants help writing XHS notes (标题/正文/标签/评论引导/封面文案), improving engagement, or turning raw points into a publish-ready note. Includes: viral 5-paragraph storytelling template, CES-style engagement optimization, title/tag formulas, and AI内容合规标注提醒. Triggers: 小红书怎么写, 小红书笔记, xhs note, rednote writing, 爆款笔记, 标题公式, 标签怎么选.
extract-version
Parses semantic version strings from various formats including text snippets, validates against semver 2.0.0 spec, and returns structured version components. Handles prefixes, prerelease tags, build metadata, and extraction from mixed text content with clear error messages.
generate-report-header
Creates standardized markdown headers for agent-generated reports with metadata fields like report type, version, status, and timestamp. Maps status codes to emojis, handles optional fields, and provides consistent formatting for bug reports, security audits, and dependency updates.
distributed-tracing
This skill provides concrete instructions for implementing distributed tracing with Jaeger and Tempo. It includes deployment guides for Kubernetes and Docker, instrumentation examples for Python, Node.js, and Go, and practical troubleshooting advice. The content covers sampling strategies, context propagation, and trace analysis queries.
writing-skills
Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dependencies, and rust-documentation skills.