Skip to content
Agentmart
Submit a tool

rag-chunking-audit

Audits whether website content has clear, bounded, retrieval-friendly structural units for AI retrieval and answer generation.

Skill by Ishu250412

IndexedApache-2.0
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ishu250412-rag-chunking-audit

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Audits whether website content has clear, bounded, retrieval-friendly structural units for AI retrieval and answer generation.

Use cases: ml, security, writing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/rag-chunking-audit

What's inside

Skill name
rag-chunking-audit
Description
Audits whether website content has clear, bounded, retrieval-friendly structural units for AI retrieval and answer generation.
License
Apache-2.0
Instructions
16 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (3)

  • SKILL.md
  • chunking_rules.md · references/
  • audit_chunkability.py · scripts/

SKILL.md (first lines)

# RAG Chunkability Audit Skill

This skill evaluates content structure that can be observed directly from crawled pages. It does not perform retrieval, embeddings, or vector search.

## Checks
- `RAG-01`: Clear primary heading structure.
- `RAG-02`: Logical heading hierarchy.
- `RAG-03`: Descriptive section headings.
- `RAG-04`: Oversized text blocks.
- `RAG-05`: Section boundaries on long pages.
- `RAG-06`: Structural aids such as lists/tables on dense informational pages.

## Detection
Checks are deterministic structural heuristics. Findings must not be presented as proof of actual RAG retrieval performance.

From Ishu250412/Brand--ai-readiness-audit, Apache-2.0.

More from Ishu250412/Brand--ai-readiness-audit

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 19, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/Ishu250412/Brand--ai-readiness-audit
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Ishu250412

Cite this page

rag-chunking-audit skill. Agent Mart. https://agentmart.dev/skills/ishu250412-rag-chunking-audit (last updated 2026-10-24)