simple-readme
Skill1 starsChanged 43 days agoMITView on GitHub
Create or update a project README in a developer-focused layout: Requirements, Quick Setup, and Structure. Use when the user asks to write, create, update, or refresh a README, or mentions simple-readme.
- Reads credentials
In this repository15 other files it gives its agents.
- simple-cantoneseSkill
- simple-checkSkill
- simple-chineseSkill
- simple-cloudflareSkill
- simple-code-reviewSkill
- simple-commitSkill
- simple-debugSkill
- simple-full-refactorSkill
- simple-launchSkill
- simple-orchestratorSkill
- simple-refactorSkill
- simple-releaseSkill
- simple-restructureSkill
- simple-supabaseSkill
- simple-text-cleanupSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Write a practical, scannable README for developers cloning the repo, not a marketing page.
- Distinctive: line 19
Every README has these three, in this order, with a short intro before them:
- Distinctive: line 49
No placeholder text left
- Distinctive: line 62
Keep accurate URLs, license, warnings, and integration notes.
- Distinctive: line 64
If it is a public marketing page (badges, screenshots, disclaimers), ask whether to convert to dev style or only refresh the setup parts.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Simple README
Write a practical, scannable README for developers cloning the repo, not a marketing page. Direct and neutral, short paragraphs, bullets and tables over walls of text. No emojis unless the project already uses them.
Required sections
Every README has these three, in this order, with a short intro before them:
- Requirements: runtime, services, and external dependencies
- Quick Setup: install, env, run (dev and prod when applicable)
- Structure: ASCII folder tree with short comments on key paths
Everything else is optional. Add an optional section only when it helps someone run, deploy, or integrate the project. Skip it if there is nothing substantive to say.
See template.md for the skeleton.
Workflow
- Mode: no README means write from scratch. If one exists, update in place, keep accurate content, and align it to this format. If the user gives a section list, follow it and still include the three required sections.
Gather facts. Read the repo before writing and never invent ports, env vars, or commands.
Source Extract package.json,pyproject.toml,requirements.txtScripts, runtime version, framework .env.exampleEnv var names, defaults, required or optional docker-compose.yml,DockerfileDocker steps SQL setup files, migrations Database step Entry files, src/layoutStructure tree Existing README Unique content worth keeping - Optional sections. Ask the user which to include when several could apply, such as Scripts, Deployment, Security, Logging, Integration, Routes. Skip the question if the request already says. Include these without asking when the file exists:
.env.example(env table),docker-compose.yml(Docker step), SQL setup file (Database step). - Draft from the template, then verify:
- Requirements list real dependencies only
- Commands match the project's scripts
- Env table matches
.env.example - Structure tree matches the actual folders
- No placeholder text left
Section notes
- Intro: 1 to 3 sentences on what it does, the stack, and key external services or sibling repos.
- Requirements: bullets, with optional integrations marked optional.
- Quick Setup: numbered
###steps. Use exact commands, and note non-default ports and build-time env vars. - Env table: columns Variable, Required, Description.
- Structure: repo root name, comment important paths inline, do not list every file. Add a small table for folder conventions if the layout is not obvious.
- Optional sections go before Structure.
Updating an existing README
- Keep accurate URLs, license, warnings, and integration notes.
- Replace outdated commands and env vars using the repo as the source of truth.
- If it is a public marketing page (badges, screenshots, disclaimers), ask whether to convert to dev style or only refresh the setup parts.
Avoid
- Generic filler like "a modern, scalable solution"
- Commands that are not in the project
- Full API docs, link to them instead
- Optional sections with one vague sentence
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

