Skip to content
TrustedSkillsbeta
Back to all skills

Verification Before Completion

Checked
obra·vlatest·writing·MIT

This skill checks generated content against a source for accuracy, ensuring reliability and reducing errors – invaluable for trustworthy 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 obra/superpowers --skill verification-before-completion -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

obra

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 obra/superpowers at 8ca22dba9a.

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

Commit
8ca22dba9a
Manifest
skills/verification-before-completion/SKILL.md
Scanned
1 file, 107 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

This skill ensures AI agent outputs are verified before being finalized. It checks the response against a provided source or context, confirming accuracy and relevance. The skill aims to reduce hallucinations and improve the reliability of generated content by validating information before completion.

When to use it

  • Generating code: Verify that the generated code compiles and produces the expected output based on documentation.
  • Writing summaries: Confirm that a summary accurately reflects the key points in a provided article or document.
  • Creating reports: Validate data presented in a report against source datasets, ensuring accuracy.
  • Drafting emails: Check email content for factual correctness and alignment with specified guidelines.

Key capabilities

  • Response verification against provided context.
  • Accuracy validation of generated content.
  • Hallucination reduction.
  • Reliability improvement.

Example prompts

  • "Verify this code snippet: [code]"
  • "Summarize the following article and confirm it aligns with the original text: [article]"
  • “Check this email draft for accuracy against these guidelines: [email draft]”

Tips & gotchas

The quality of verification depends heavily on the clarity and completeness of the provided context. Ensure that the source material is accurate and relevant to the task at hand for best results.