Skip to content
TrustedSkillsbeta
Back to all skills

Sherlock Review

Checked
proffesor-for-testing·vlatest·other·MIT

Analyzes text data to identify inconsistencies, biases, and potential errors like Sherlock Holmes investigates a case.

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 proffesor-for-testing/agentic-qe --skill sherlock-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

proffesor-for-testing

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 proffesor-for-testing/agentic-qe at 124d8c735e.

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

Commit
124d8c735e
Manifest
assets/skills/sherlock-review/SKILL.md
Scanned
6 files, 1,160 lines
Copies in repo
2 — all of them scanned
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

What it does

The Sherlock Review skill helps AI agents analyze code claims and related data to determine their validity. It uses a structured investigative process, inspired by Sherlock Holmes, to gather evidence (code changes, tests, behavior), deduce whether reality matches the claim, and ultimately conclude with a supported verdict. The tool focuses on verifying claims made in pull requests or commit messages through rigorous examination of code and testing results.

When to use it

  • Verifying claims made in pull request descriptions or commit messages.
  • Assessing the accuracy of reported bug fixes or new feature implementations.
  • Determining whether code changes are fully supported by accompanying tests.
  • Investigating discrepancies between expected behavior and actual runtime output.
  • Analyzing code contributions to ensure they align with stated goals.

Key capabilities

  • Evidence Gathering: Collects data like git diff outputs, test coverage reports, and observed behavior.
  • Deductive Analysis: Compares claims against gathered evidence to identify inconsistencies.
  • Verdict Levels: Categorizes findings as TRUE, PARTIALLY TRUE, FALSE, or NONSENSICAL.
  • Investigation Template: Provides a structured format for documenting the investigation process and results.
  • Holmesian Principles: Applies principles like prioritizing data collection and eliminating impossible scenarios.

Example prompts

  • "Analyze this pull request claim: 'Fixes issue #123 by updating the login function.'"
  • "Verify if the commit message 'Adds new feature X' is supported by the code changes and tests."
  • "Investigate the claim that bug Y has been resolved in this branch."

Tips & gotchas

  • The skill relies on access to Git repositories and testing frameworks. Ensure the agent has appropriate permissions and environment setup.
  • The "Evidence Collection Checklist" provides guidance on what data to gather for a thorough investigation.
  • Focus on reproducible evidence; avoid assumptions or subjective interpretations.