karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
Flowy lists 1235 skills in the Skill Authoring category for Claude Code, across 85 plugins. A skill is a folder of instructions an agent loads while you work. Every one here shows what is inside before you install, who wrote it, and whether it is Auto-invoked, meaning a FLOW.md router fires it as you prompt.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent…
Set up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), or distill colleague,…
Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream'…
Trigger: preparing branches or PRs for Gentleman-Programming/gentle-ai. Apply this repository's issue-first contribution policy.
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
基于结构映射理论,为场景或两个对象的差异寻找精妙类比与关系隐喻,保留关键关系、解释增量与迁移边界。USE WHEN 用户说「找个类比」「打个比方」「有什么精妙的隐喻」「用类比讲清两者区别」「换个场景理解」或调用 ljg-analogy。NOT FOR…
盲区扫描——读昨天你与 AI 的全部对话,照出暴露的思维盲区(不是不懂的知识,是让某类真相一直看不见的思维习惯),再从微信读书挑一本书的一章精准补上,落成一篇完整分析笔记。Use when user says '扫盲区', '盲区', '照盲区',…
Explain a whole book to readers without specialist knowledge: what it follows, how its main threads connect, where it ends, and…
Manage the user's shared agent-skill library via skills-manager-cli — install, update, remove, deploy or undeploy skills per…
Distill an ex-partner into an AI Skill. Import WeChat history, photos, social media posts, generate Relationship Memory +…
Reading coach: guides users through books systematically with knowledge compilation, mastery testing, spaced repetition, and…
Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes…
Personalized 1-on-1 AI tutor using Bloom's 2-Sigma mastery learning. Guides users through any topic with Socratic questioning,…
Monitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology worth preserving to…
基于当前项目/代码生成 Draw.io 图表,支持技术栈图、系统架构图、数据结构图、E-R 图四种类型。输出符合 Draw.io 语法的 .drawio 文件(mxGraph XML),可直接导入 Draw.io…
基于当前项目/代码生成各类文档,支持论文章节、项目梳理、重点问题、简历项目描述四种类型。当用户提到生成论文章节、项目梳理、技术难点、简历项目描述时使用。要给新同事看的上手文档(新人文档、架构文档、代码导读、onboarding)用 project-docs。
开发流程五步法。支持需求理解、方案设计、代码实现、代码审查、Bug 修复。当用户提到「需求分析」「方案设计」「代码实现」「代码审查」「理解需求」「技术设计」「开始写代码」「Review」「检查代码」「bug」「报错」「崩溃」「异常」「出错了」时使用。
Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts. Use for migration/release/package,…
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits…
Create API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for…
Generate architecture documentation using C4 model Mermaid diagrams. Use when asked to create architecture diagrams, document…
Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive…
Design a process, idea or body of knowledge into an ICM (Interpretable Context Methodology) workspace, where folder structure is…
Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring…
Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners,…
Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom…
Provides Typer templates, handles registration, and ensures consistency. ALWAYS use this skill when adding or modifying CLI…
Generate pytest tests for Typer CLI commands. Includes fixtures (temp_storage, sample_data), CliRunner patterns, confirmation…
Create learning paths for programming tools, and define what information should be researched to create learning guides. Use when…
Defines practical standards for implementation-focused coding agents. Use when creating or editing code, especially when…
Designs clear, testable prompts for agent workflows. Use when creating new prompts, refining weak prompts, or establishing…
Provides a structured verification workflow for code and prompt outputs. Use when asked to validate correctness, catch…
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when…
React useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data…
Apply rigorous coding standards. Use when writing, implementing, or reviewing code.
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and…
Create or update Codex hooks for global or project scope by asking for scope and hook type when ambiguous, then writing the hook…
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web…
This skill should be used when the user asks to "organize the project rules", "clean up scattered documentation", "把规则迁移到 skills…
CRITICAL: Use for writing and editing agent-spec .spec/.spec.md files. Triggers on: write spec, create spec, edit spec, new spec,…
CRITICAL: Use for estimating work effort from agent-spec Task Contracts. Triggers on: estimate, estimation, how long, work…
Use when converting PRD or issue prose into KLL requirements, running the intent compiler plan, or reverse-interviewing a human…
以"程序员鱼皮"的身份、口吻、思维方式回答问题。鱼皮是前腾讯全栈工程师、全网200万+粉丝的AI+编程知识博主、科技公司鱼鸢网络CEO、编程导航创始人。…
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full…
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix →…
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use…
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
Use this skill when the user says 'AI search', 'AI visibility', 'ChatGPT ranking', 'Perplexity optimization', 'GEO', 'generative…
Use this skill when the user says 'audit API', 'check API security', 'API routes security', 'endpoint audit', 'check my routes',…
Use this skill when the user says 'design API', 'API endpoints', 'REST API', 'API designer', 'route structure', 'API…
Reviews a code change for correctness, security, maintainability, architecture, performance, and verification gaps, or performs a…
Audits an entity model field by field: what should exist, what exists now, where each value belongs (column, config, computed…
Challenges an overly conservative, incremental, or compatibility-led proposal with a bold target model, a concrete…
GitHub repository access in containerized environments using REST API and credential detection. Use when git clone fails, or when…
Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe…
Make a short animated film by writing the drawing code yourself: every frame a pure function of time, rendered headlessly to MP4.…
Research, create, improve, migrate, evaluate, package, install-check, govern, and safely publish qiaomu-flavored agent skills…
Design and analyze A/B tests, calculate statistical significance, and determine sample sizes for conversion optimization and…
Implement Role-Based Access Control (RBAC), permissions management, and authorization policies. Use when building secure access…
Implement WCAG 2.1/2.2 accessibility standards, screen reader compatibility, keyboard navigation, and a11y testing. Use when…
Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and…
Test a consequential technical assumption with a small, falsifiable experiment before committing to an approach. Use when a plan…
Surface the user's unknown unknowns before work starts. Use when the user is entering an unfamiliar codebase area, an unfamiliar…
Opinionated guide for building production TypeScript applications with Effect v4. Use when implementing Effect workflows,…
Tạo AI Skill mới từ ý tưởng hoặc quy trình công việc. Kết hợp phỏng vấn thông minh, pattern detection, và quantitative evaluation…
Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, revise,…
Monitors context window health during large, long-running, multi-session, or explicitly context-sensitive work. Uses bounded…
Control-plane workflow for coordinating multi-agent, multi-session project work from a single Codex, GitHub Copilot, or agent-app…
Generate or update an Agent Skill that teaches consumers one npm or local package the user maintains, including framework modules…
Generate or update an Agent Skill from the observed workflows, boundaries, and conventions of one software project.
Review an Agent Skill for valid structure, clear triggers, usable instructions, current evidence, and risky or unclear actions.
Create, edit, debug, and orchestrate Claude Code agents and Task-tool workflows. Use when writing agent files, configuring tools…
Run adaptive APEX implementation with scoped delegation, durable checkpoints, risk-based tests and review, and proof-backed…
Generate a vibrant dimensional iOS and Android app icon, then post-process it for store specs. Use for creating, regenerating, or…
Write or revise a habit-hooks coaching prompt. Use when a linter / knip / jscpd rule fires and the agent's default fix is wrong…
Spawn a reviewer sub-agent to assess a change set against habit-hooks's coding principles. Use AFTER habit-hooks reports clean —…
Cut a new release of the habit-hooks packages. Use when asked to release, publish, or bump the version. Reviews what lands,…
Create lane for fskill-creator; normalizes user briefs into create_context for the main skill to generate functional skills.
Create, maintain, or migrate functional skills; supports creating from a requirement brief and migrating an existing legacy skill…
Migrate lane for fskill-creator; analyzes a legacy skill directory into behavior map, function split proposal, and source…
Manage Discord channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve…
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when…
This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render…
Determine the best Anthropic architecture for your project by analyzing requirements and recommending the optimal combination of…
Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices for Claude…
Design iOS apps following Apple's Human Interface Guidelines. Generate native components, validate designs, and ensure…
1,139 more in Skill Authoring. See them all →