Skip to content
TrustedSkillsbeta
Back to all skills

Docs Review

Checked
metabase·vlatest·writing

Quickly identifies potential issues like inconsistencies, errors, and missing information in uploaded documents.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add metabase/metabase --skill docs-review -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

metabase

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned metabase/metabase at 674c8b8dc6.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
674c8b8dc6
Manifest
.claude/skills/docs-review/SKILL.md
Scanned
1 file, 160 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

The docs-review skill enables AI agents to systematically analyze documentation, identifying gaps, inconsistencies, and areas for improvement. It helps ensure technical writing remains accurate, clear, and aligned with the latest product updates or codebase changes.

When to use it

  • Before publishing new release notes to verify factual accuracy against recent commits.
  • During onboarding phases to audit existing guides for clarity and completeness.
  • When updating legacy documentation to match current API endpoints or feature sets.
  • To generate a prioritized list of missing examples or edge cases in user manuals.

Key capabilities

  • Automated scanning of text for logical inconsistencies and factual errors.
  • Identification of outdated references compared to the latest system state.
  • Assessment of tone, clarity, and structural organization within documents.
  • Extraction of specific sections requiring human review or revision.

Example prompts

  • "Review the 'Getting Started' guide and list any steps that contradict the current installation instructions."
  • "Analyze the API documentation for missing error code explanations and suggest where to add them."
  • "Identify sentences in the user manual that are ambiguous or lack sufficient context for new users."

Tips & gotchas

This skill is most effective when paired with a live codebase or version-controlled documentation repository to validate claims. Ensure the AI agent has read access to both the documents being reviewed and the source material it should compare against.