How do I install the Readme skill?

Run npx skillmds add alunduil/readme in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Readme safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Readme?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Readme free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Readme?

alunduil (@alunduil) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Readme by alunduil — Agent Skill

Name: Readme
Rating: 4.2 (5 reviews)
Author: alunduil

Readme

Audit, write, or revise README.md. Use when creating a README, editing one, or noticing smells (missing badges, no install steps, unclear purpose, no engagement guidance). Applies ddbeck's checklist and a shields.io badge principle.

alunduil 3b48d5f 2.6 KB Updated Aug 19, 2026 1 repo stars

File contents

README

Reference: https://github.com/ddbeck/readme-checklist/blob/main/checklist.md

Checklist (condensed)

Identify — project name as first heading; repo/homepage URL near top; owner/author named.

Evaluate — describe why (what it achieves), not what (what it's made of). Active voice, second person. License named (open source) or authorized users named (closed source).

Use — prerequisites before install; install + basic usage, tested.

Engage — pointer to deeper docs (CONTRIBUTING, LICENSE, CHANGELOG, etc.) when they exist; where to get help (or explicit "no support"); how to contribute (or explicit "not accepting").

Final — TOC for 10+ screens; split into files past that.

Badges (shields.io)

Each badge earns its place: real-time, decision-relevant info not already visible on the rendered page (e.g. on github.com).

Usually qualifies:

License — img.shields.io/github/license/<owner>/<repo> — survives off-GitHub renders.
Code coverage when codecov/coveralls is wired up.
Tool/config presence (pre-commit, Renovate, Dependabot) when used.
Single-target platform/runtime when exactly one is supported.

Usually doesn't:

CI status — GitHub shows it on commits; multi-workflow makes "build" ambiguous. Promote only when one named workflow is the gate.
Last commit — already on the GitHub page.
Release version — already on the sidebar; promote when README is rendered off-GitHub (npm, mirrors).
Dependency counters — noisy/stale. "Renovate enabled" / "Dependabot enabled" is the usable substitute.

Test: would removing this badge lose information the reader couldn't get from the page above?

Procedure

Read the README. Name the actual audience.
Ethos first — for each existing section, name the reader need it serves (identify / evaluate / use / engage). Sections serving no need are noise; flag them to cut, even if the checklist nominally has a slot. "What it's made of" tours, internal implementation notes, and speculative future plans usually fall here.
Gaps — walk the checklist to find reader needs not yet covered. The checklist is a prompt for missing needs, not a license for existing sections.
Walk the badges against the principle; flag any that don't earn their place.
Surface findings before editing. Apply only after scope is agreed.

---name: readmedescription: Audit, write, or revise README.md. Use when creating a README, editing one, or noticing smells (missing badges, no install steps, unclear purpose, no engagement guidance). Applies ddbeck's checklist and a shields.io badge principle.---# READMEReference: <https://github.com/ddbeck/readme-checklist/blob/main/checklist.md>## Checklist (condensed)**Identify** — project name as first heading; repo/homepage URL near top; owner/author named.**Evaluate** — describe *why* (what it achieves), not *what* (what it's made of). Active voice, second person. License named (open source) or authorized users named (closed source).**Use** — prerequisites before install; install + basic usage, tested.**Engage** — pointer to deeper docs (CONTRIBUTING, LICENSE, CHANGELOG, etc.) when they exist; where to get help (or explicit "no support"); how to contribute (or explicit "not accepting").**Final** — TOC for 10+ screens; split into files past that.## Badges (shields.io)Each badge earns its place: real-time, decision-relevant info not already visible on the rendered page (e.g. on github.com).Usually qualifies:- License — `img.shields.io/github/license/<owner>/<repo>` — survives off-GitHub renders.- Code coverage when codecov/coveralls is wired up.- Tool/config presence (pre-commit, Renovate, Dependabot) when used.- Single-target platform/runtime when exactly one is supported.Usually doesn't:- CI status — GitHub shows it on commits; multi-workflow makes "build" ambiguous. Promote only when one named workflow is the gate.- Last commit — already on the GitHub page.- Release version — already on the sidebar; promote when README is rendered off-GitHub (npm, mirrors).- Dependency counters — noisy/stale. "Renovate enabled" / "Dependabot enabled" is the usable substitute.Test: would removing this badge lose information the reader couldn't get from the page above?## Procedure1. Read the README. Name the actual audience.2. **Ethos first** — for each existing section, name the reader need it serves (identify / evaluate / use / engage). Sections serving no need are noise; flag them to cut, even if the checklist nominally has a slot. "What it's made of" tours, internal implementation notes, and speculative future plans usually fall here.3. **Gaps** — walk the checklist to find reader needs *not yet* covered. The checklist is a prompt for missing needs, not a license for existing sections.4. Walk the badges against the principle; flag any that don't earn their place.5. Surface findings before editing. Apply only after scope is agreed.

Frequently asked questions