Back to Skills Library
VerificationQualityAnti-hallucinationAI Agent Skill

verification-before-completion

Forces a verification pass before declaring anything "done" - cross-checking every claim against its original source instead of trusting the summary.

obra/superpowers
187.6k stars
187.6k installs
Updated: 2026-08-12

Install Options

Install into Claude Code, Cursor, Codex, or Antigravity with:

$ npx skills add obra/superpowers@verification-before-completion

Real Work Situation Solved

Filter out hallucinations and over-extrapolations in AI feedback summaries

AI summarized 100 user tickets into a neat report - how do you verify it didn't invent trends?

5-Step Action Framework

  1. 1Require the AI to attach direct ticket IDs or exact verbatim quotes to every listed insight.
  2. 2Spot-check 5 random citations against raw logs - if even one is fabricated, reject the summary.
  3. 3Force the AI to output exact mention counts rather than vague qualifiers like 'most users'.
  4. 4Compare summary points against lowest-rated (1-star) feedback to ensure critical negative signals were not smoothed away.
  5. 5Retain only insights backed by at least 3 distinct, independent feedback instances.
Before

"The AI summary reads smoothly and makes sense, forward it straight to leadership."

After

"Caught AI fabricating a 'huge demand for dark mode' from a single mention. Enforced ticket citations and counts: only 3 issues with >10 occurrences made the roadmap."

Related Course Lesson

AI LiteracyLesson 3

Go to Lesson

SKILL.md Source Instructions

SKILL.md • Read-only preview
# Verification Before Completion Skill

Before accepting a summary or report as final, spot-check its claims against the underlying raw data; if even one claim doesn't hold up, the whole summary is rejected.