output-customization
Central authority for Claude Code output styles. Covers built-in output styles (Default, Explanatory, Learning), custom output styles, output style frontmatter (name, description, keep-coding-instructions), /ou...
按技能名称、说明或 GitHub 作者匹配的结果。
Central authority for Claude Code output styles. Covers built-in output styles (Default, Explanatory, Learning), custom output styles, output style frontmatter (name, description, keep-coding-instructions), /ou...
Central authority for Claude Code configuration and settings. Covers settings.json files (user, project, enterprise), available settings, permission settings, sandbox settings, settings precedence, plugin confi...
Designing and implementing robust command-line interfaces using OCaml's cmdliner library, following Daniel Bünzli's design principles. Use when Claude needs to: (1) Design a new CLI or subcommand layout, (2) Im...
OCaml fuzz testing with Crowbar for protocol implementations. Use when Claude needs to: (1) Write fuzz tests for parsers and encoders, (2) Test roundtrip invariants (parse(encode(x)) = x), (3) Verify boundary c...
JSON type-safe encoding and decoding using Daniel Bünzli's jsont library. Use when Claude needs to: (1) Define typed JSON codecs for OCaml record types, (2) Parse JSON strings to OCaml values, (3) Serialize OCa...
OCaml 5 algebraic effects design patterns. Use when Claude needs to: (1) Design APIs that interact with effect-based schedulers, (2) Decide between effects vs exceptions, (3) Integrate libraries with Eio or aff...
OCaml memtrace profiling for allocation hotspot analysis. Use when Claude needs to: (1) Add memtrace instrumentation to OCaml executables, (2) Run targeted benchmarks with tracing enabled, (3) Identify allocati...
Eio concurrency patterns for OCaml applications. Use when Claude needs to: (1) Write concurrent OCaml code with Eio, (2) Handle network operations with cohttp-eio, (3) Manage resource lifecycles with switches,...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
This skill helps launch and configure the Chrome DevTools MCP server, giving Claude visual access to a live browser for debugging and automation. Use when the user asks to set up browser debugging, launch Chrom...
Provides master-level guidance for creating exceptional Claude Code skills using combined best practices from official plugin-dev toolkit, community patterns, and latest API. Use when creating skills, designing...
This skill should be used when creating hooks, automating workflows, or when "PreToolUse", "PostToolUse", "hooks.json", "event handler", or "create hook" are mentioned.
This skill should be used when configuring Claude, setting up MCP servers, or when "settings.json", "claude_desktop_config", "MCP server", or "Claude config" are mentioned.
This skill should be used when creating agents, writing agent frontmatter, configuring subagents, or when "create agent", "agent.md", "subagent", or "Task tool" are mentioned.
This skill should be used when creating slash commands, writing command files, or when "/command", ".claude/commands", "$ARGUMENTS", or "create command" are mentioned.
This skill should be used when creating plugins, publishing to marketplaces, or when "plugin.json", "marketplace", "create plugin", or "distribute plugin" are mentioned.
This skill should be used when creating rule files, organizing conventions, or when ".claude/rules/", "FORMATTING.md", "create rule", or "project conventions" are mentioned.
Enforces Conventional Commits format, validates message quality (72 char subject, 80 char body), and BLOCKS Claude Code pollution (co-author/generated-by markers). Use when committing, creating commits, git com...
Creates new Claude Code Skills following best practices from migration patterns. Use when creating new Skills, converting slash commands to Skills, scaffolding Skill structure, or when user mentions "create ski...
Run multi-LLM council for adversarial debate and cross-validation. Orchestrates Claude, GPT-4, and Gemini for production-grade implementation, code review, architecture design, research, and security analysis.
Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, musi...
Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Claude, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion, Imagen, Flux)...
Use when live coding music with SuperCollider via ClaudeCollider MCP server.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。