Skip to content
TrustedSkillsbeta
Back to all skills

Trust But Verify

Checked
wojons·vlatest·other·MIT

This skill automatically checks generated content against trusted sources to ensure accuracy and mitigate potential misinformation – a vital safeguard for reliable outputs.

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 wojons/skills --skill trust-but-verify -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

wojons

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 wojons/skills at 5fe7152c66.

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

Commit
5fe7152c66
Manifest
skills/trust-but-verify/SKILL.md
Scanned
4 files, 390 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

What it does

The trust-but-verify skill allows an AI agent to critically evaluate its own outputs and identify potential errors or inconsistencies. It can re-examine previous steps, cross-reference information from different sources, and generate alternative solutions for comparison. This helps improve the reliability and accuracy of the agent's responses.

When to use it

  • Complex Reasoning Tasks: When an AI is performing multi-step reasoning that requires high accuracy.
  • Generating Code: To verify code snippets for syntax errors or logical flaws before execution.
  • Summarizing Documents: To ensure the summary accurately reflects the original content and doesn’t introduce inaccuracies.
  • Decision Making: When making important decisions, to explore alternative options and assess risks.

Key capabilities

  • Self-evaluation of outputs
  • Cross-referencing information
  • Generating alternative solutions
  • Re-examination of previous steps

Example prompts

  • "Trust but verify my reasoning for this conclusion."
  • "Can you generate an alternate solution and compare it to the current one?"
  • "Review your previous steps to ensure accuracy."

Tips & gotchas

This skill is most effective when used proactively. It's beneficial to explicitly instruct the agent to "trust but verify" its work, rather than relying on it to do so automatically in all situations.