Agent Skill that writes honest, structured READMEs — classifies your project type, audience & distribution model instead │ │ │ of filling templates. Works with Claude Code, Cursor, Codex, Gemini CLI and more AI agents.
**English** | [中文](./README-ZH.md) <div align="center"> # README Crafter **An Agent Skill that writes honest, well-structured READMEs tailored to each project's type, audience, and distribution model.** [](./LICENSE) [](https://agentskills.io) [](#scanner) [](#agent-portability) </div> --- Most README generators scan a repo and fill a template. The result reads like a form, not a front page. README Crafter takes a different approach: it classifies the project along four independent axes — project type, distribution posture, audience, and presentation temperament — then generates a README shaped for that specific combination. It refuses to invent install commands, fabricate code examples, or claim features that don't exist in the source. ## Install ### One-liner (recommended) Auto-detects your installed agents (Claude Code, Cursor, Codex, Cursor CLI, and 40+ others) and installs the skill to all of them: ```bash npx skills add linhai0872/readme-crafter-skill ``` Add `--global` to install at user level, or omit for project level. Add `--all` to skip prompts. ### Ask your agent to install it Copy the prompt below and paste it into any AI coding agent — it will handle the rest: ```text Install the readme-crafter-skill for me: clone https://github.com/linhai0872/readme-crafter-skill.git into my skills directory and symlink it so this agent can use it. Verify SKILL.md is accessible after setup. ``` ### Manual install <details> <summary>Clone + symlink</summary> ```bash git clone https://github.com/linhai0872/readme-crafter-skill.git ``` Then symlink into your agent's skill di
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.