agentsclimarketplace

Readme generator

Skill serejaris/personal-corp-skills/skills/readme-generator

Use when creating or rewriting README.md for projects. Triggers on "write README", "create README", "update README". Creates human-focused documentation with proper structure.From its SKILL.md

Install
npx -y skills add serejaris/personal-corp-skills --skill readme-generator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • runs commandsInstructs the agent to run 1 command, including `mcp__exa__web_search_exa: "best practices README.md {year} {project_type}"`.

SKILL.md

4.7 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

README Generator

Generate human-focused README files following current best practices.

Core principle: README is for humans, not agents. Research → Analyze → Write.

Model recommendation: Use Task tool with model: haiku for README generation — faster and cheaper for documentation tasks.

When to Use

  • Creating README for new project
  • Rewriting outdated README
  • User asks "write/create/update README"

Process

digraph readme_flow {
    rankdir=TB;
    "1. Research best practices via Exa" [shape=box];
    "2. Analyze project structure" [shape=box];
    "3. Identify project type" [shape=diamond];
    "4. Write README with appropriate sections" [shape=box];
    "5. Commit and push if requested" [shape=box];

    "1. Research best practices via Exa" -> "2. Analyze project structure";
    "2. Analyze project structure" -> "3. Identify project type";
    "3. Identify project type" -> "4. Write README with appropriate sections";
    "4. Write README with appropriate sections" -> "5. Commit and push if requested";
}

Step 1: Research

Always search first for current README best practices:

mcp__exa__web_search_exa: "best practices README.md {year} {project_type}"

Look for:

  • Current trends in README structure
  • Examples from similar projects
  • What sections are essential vs optional

Step 2: Analyze Project

Read these files to understand the project:

  • CLAUDE.md or existing docs
  • package.json / pyproject.toml / Cargo.toml
  • Main entry points
  • Test files (understand features)

Step 3: Identify Project Type

TypeKey Sections
CLI ToolUsage examples, Options table, Installation
Library/SDKAPI overview, Quick start, Examples
Web AppFeatures, Quick start, Architecture diagram
Full-stackArchitecture, Quick start both parts, Tech stack
AI/MLModel info, Requirements (GPU), Examples

Step 4: README Structure

Essential (all projects):

# Project Name

**One-line value proposition.**

Brief description (2-3 sentences max).

## What It Does / Features
- Bullet points of capabilities
- Focus on VALUE not implementation

## Quick Start
Minimal steps to get running (< 5 commands)

## Requirements
- Runtime versions
- System requirements
- Disk space if significant

## Usage
Examples for common cases

## Tech Stack (if non-trivial)
Table format preferred

## License

Optional by project type:

SectionWhen to Include
Architecture diagramWeb apps, full-stack, complex systems
Project StructureOpen source, contribution expected
API ReferenceLibraries, SDKs (or link to docs)
Related SkillsIf Claude Code skills exist
CLI Options tableCLI tools
ConfigurationApps with config files
Known LimitationsIf significant gotchas exist

Writing Style

DO:

  • Start with value, not implementation
  • Use active voice
  • Keep sentences short
  • Include runnable examples
  • Write for humans scanning quickly

DON'T:

  • Include API reference for internal use
  • Write walls of text
  • Use jargon without explanation
  • Include every possible option

Related Skills Section

If project has Claude Code skills, add:

## Related Skills

| Skill | Trigger | What it does |
|-------|---------|--------------|
| `skill-name` | "trigger phrase" | Brief description |

Quick Reference

Project has...Include
Web UIScreenshot or architecture
CLIOptions table, examples
APIEndpoint summary (not full docs)
AI/MLModel, hardware requirements
Claude skillsRelated Skills table
Complex archMermaid diagram

Common Mistakes

MistakeFix
API docs dumpLink to separate file or remove
No quick startAdd "clone → run" in < 5 steps
Wall of textUse bullets, tables, code blocks
Missing requirementsAlways list runtime + system reqs
Generic descriptionStart with specific value prop

Example Structure (Full-stack App)

# Project Name

**Value proposition in one line.**

Brief description.

## Features
- Feature 1
- Feature 2

## Quick Start
\`\`\`bash
./start.sh
\`\`\`

## Requirements
- OS/hardware
- Runtime versions

## Tech Stack
| Layer | Stack |
|-------|-------|

## Architecture
\`\`\`mermaid
flowchart...
\`\`\`

## Project Structure
\`\`\`
project/
├── ...
\`\`\`

## Related Skills
| Skill | Trigger | Description |

## Development
How to test, build

## License

What ships with it: 3 files

460.0 KB alongside SKILL.md

assets/

Gives 0 of the 12 instructions most readme changelog skills give in ~1.1k tokens

Counted across 446 of the 460 authors here whose files we hold, read 2026-09-06

  • Follow Keep a Changelog formatin 24 of 446
  • Collect commits since the last git tagin 15 of 446, across 13 files
  • Omit empty sectionsin 14 of 446
  • Put breaking changes first with migration stepsin 14 of 446
  • Include migration guidance for breaking changesin 11 of 446, across 10 files
  • Categorize commits by conventional commit prefixin 11 of 446
  • Mark breaking changes prominentlyin 10 of 446
  • Prepend the new entry to CHANGELOG.mdin 9 of 446
  • Highlight breaking changes with migration notesin 8 of 446, across 7 files
  • Classify changes into Keep a Changelog categoriesin 8 of 446, across 7 files
  • Group related commits into single entriesin 8 of 446
  • Write the changelog from commitsin 8 of 446

Said here and by no other author read

  • Search current README best practices first
  • Start with value, not implementation
  • List runtime and system requirements
  • Use bullets, tables, and code blocks
  • Commit and push if requested

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.