- Home
- Skills
- Technical Documentation
- readme-validator
More screenshots
Works with the AI Agents you already use
Readme Validator
Catch broken links, missing sections, and formatting disasters before your README goes public.
Free
readme-validator
Example session with this skill installed
"Validate the README for my open-source CLI tool"
- Read your context and instructions
- Compiled the readme-validator
"README Validation Report — Score: 72/100
Critical Issues (2):
- Line 45:
http://example.com/docsreturns 404 — Installation docs are unreachable - Line 1: No License section found — legal risk for reuse
Warnings (3):
- Line 78: Travis CI badge uses deprecated
.orgdomain - Line 5: No Contributing section for an open-source project
- Line 92: Screenshot from March 2023 — project has had 4 major releases since
Info (4):
- Line 23: Code block missing language tag
- Line 12: Mixed bullet styles (
-and*) - Line 105: No table of contents for a 280-line README
- Line 67: Inconsistent heading capitalization
Total links checked: 24 | Broken: 2 | Sections present: 6 of 9"
Connects securely to your tools. The creator never sees your data.
About this skill
The Problem
Your README has a badge linking to a Travis CI that shut down two years ago, a screenshot from 2023 that no longer matches the UI, and no Installation section — so new contributors can't figure out how to get started. You didn't notice because you wrote it once and never revisited. Now it's the first thing the world sees.
What You Get
- Broken link detection — every Markdown link, HTML anchor, and fragment reference is validated against actual file existence and URL resolution
- Section completeness audit — checks for Project Title, Description, Installation, Usage, Configuration, Contributing, License, Changelog, and Acknowledgments based on project type
- Badge validation — verifies badge images load from trusted CDNs, checks syntax correctness, and flags expired or 404'd badge URLs
- Image quality scan — flags screenshots older than 12 months on active projects, empty alt text, and external image hosts prone to link rot
- Formatting consistency check — heading hierarchy, code block language tags, table alignment, and mixed bullet styles across the entire document
- Severity-scored report — produces a 0-100 quality score with Critical/Warning/Info findings in a structured table format
Why This Beats Prompting It Yourself
You can ask "check my README" once, but you won't ask it before every push. This skill applies a systematic checklist that catches the 12+ categories of README rot that accumulate invisibly over months. A human reviewer reads for meaning; this validator reads for structural integrity — the things that make the difference between a project that looks maintained and one that looks abandoned.
Example Session
You: "Validate the README for my open-source CLI tool"
Agent: "README Validation Report — Score: 72/100
Critical Issues (2):
- Line 45:
http://example.com/docsreturns 404 — Installation docs are unreachable - Line 1: No License section found — legal risk for reuse
Warnings (3):
- Line 78: Travis CI badge uses deprecated
.orgdomain - Line 5: No Contributing section for an open-source project
- Line 92: Screenshot from March 2023 — project has had 4 major releases since
Info (4):
- Line 23: Code block missing language tag
- Line 12: Mixed bullet styles (
-and*) - Line 105: No table of contents for a 280-line README
- Line 67: Inconsistent heading capitalization
Total links checked: 24 | Broken: 2 | Sections present: 6 of 9"
Use Cases
- Pre-publish audit before pushing a new repo or open-source project
- Documentation sprint cleanup across an organization's repositories
- CI/CD integration to catch README rot before it reaches the main branch
- Onboarding a new project by establishing a documentation quality baseline
- Preparing repos for submission to awesome-lists or curated directories
Known Limitations
This skill is read-only and does not modify files. Link liveness (HTTP status codes) requires external network verification beyond the structural checks. Handles Markdown (.md) files up to 500KB; ReStructuredText and AsciiDoc are out of scope.
This skill is read-only and does not modify files. Link liveness (HTTP status codes) requires external network verification beyond the structural checks. Handles Markdown (.md) files up to 500KB; ReStructuredText and AsciiDoc are out of scope.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
5 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 5 months ago
- Free with an Agensi account
Requires