Doublecheck
Run structured claim-by-claim verification on copy, specs, or research drafts so you catch disputed stats and fabrication risk before you ship messaging or bet on the idea.
Overview
doublecheck is an agent skill most often used in Validate (also Launch, Grow) that produces a claim-by-claim verification report with five confidence ratings.
Install
npx skills add https://github.com/github/awesome-copilot --skill doublecheckWhat is this skill?
- Extracts individual claims from target text and scores each one
- Five-tier rating model: VERIFIED, PLAUSIBLE, UNVERIFIED, DISPUTED, FABRICATION RISK
- Flags DISPUTED and FABRICATION RISK items first in a dedicated section
- Outputs a verification report with sources, notes, and per-claim recommendations
- 5 claim confidence ratings (VERIFIED through FABRICATION RISK)
Adoption & trust: 3.1k installs on skills.sh; 34.6k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your draft copy or research memo mixes solid facts with unsourced statistics you cannot defend if challenged.
Who is it for?
Indie founders validating positioning, pricing narratives, or launch copy where factual errors have outsized cost.
Skip if: Purely internal technical READMEs with no factual claims about the outside world, or work that already has professional legal sign-off without needing a draft pass.
When should I use this skill?
You have draft text with factual assertions, statistics, or citations that need structured verification before you rely on them.
What do I get? / Deliverables
You receive a prioritized verification report listing verified, plausible, unverified, disputed, and high-risk claims with sources and fix recommendations.
- Verification report with summary table
- Flagged DISPUTED and FABRICATION RISK section
- Per-claim sources and recommendations
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Validate is where you prove assumptions; factual claim checks belong before you commit scope, pricing stories, or public copy. Scope subphase fits decisions that depend on whether assertions in docs, landing pages, or plans are trustworthy.
Where it fits
Verify TAM and competitor feature claims in a one-page scope doc before building an MVP.
Run doublecheck on long-form SEO article drafts that cite benchmarks and third-party studies.
Re-verify annual update posts that reuse last year’s statistics with new citations.
Check user-visible error messages or docs that state compliance or performance guarantees.
How it compares
Structured claim verification report, not a single-pass “sounds good” editorial review.
Common Questions / FAQ
Who is doublecheck for?
Solo builders and small teams who publish research, marketing, or product claims and want a systematic fact-check pass before committing or shipping.
When should I use doublecheck?
In Validate when scoping market or competitor assertions, in Launch before publishing landing or SEO pages, and in Grow when refreshing content that cites stats or third-party rankings.
Is doublecheck safe to install?
Check the Security Audits panel on this Prism page; the skill may trigger web lookups—review network permissions and do not paste secrets into text under verification.
SKILL.md
READMESKILL.md - Doublecheck
# Verification Report ## Summary **Text verified:** [Brief description of what was checked] **Claims extracted:** [N total] **Breakdown:** | Rating | Count | |--------|-------| | VERIFIED | | | PLAUSIBLE | | | UNVERIFIED | | | DISPUTED | | | FABRICATION RISK | | **Items requiring attention:** [N items rated DISPUTED or FABRICATION RISK] --- ## Flagged Items (Review These First) Items rated DISPUTED or FABRICATION RISK. These need your attention before you rely on the source material. ### [C#] -- [Brief description of the claim] - **Claim:** [The specific assertion from the target text] - **Rating:** [DISPUTED or FABRICATION RISK] - **Finding:** [What the verification found -- what's wrong or suspicious] - **Source:** [URL to contradicting or relevant source] - **Recommendation:** [What the user should do -- e.g., "Verify this citation in Westlaw" or "Remove this statistic unless you can find a primary source"] --- ## All Claims Full results for every extracted claim, grouped by confidence rating. ### VERIFIED #### [C#] -- [Brief description] - **Claim:** [The assertion] - **Source:** [URL] - **Notes:** [Any relevant context about the source] ### PLAUSIBLE #### [C#] -- [Brief description] - **Claim:** [The assertion] - **Notes:** [Why this is rated plausible rather than verified] ### UNVERIFIED #### [C#] -- [Brief description] - **Claim:** [The assertion] - **Notes:** [What was searched, why nothing was found] ### DISPUTED #### [C#] -- [Brief description] - **Claim:** [The assertion] - **Contradicting source:** [URL] - **Details:** [What the source says vs. what the claim says] ### FABRICATION RISK #### [C#] -- [Brief description] - **Claim:** [The assertion] - **Pattern:** [Which hallucination pattern this matches] - **Details:** [Why this is flagged -- e.g., "citation not found in any legal database"] --- ## Internal Consistency [Any contradictions found within the target text itself, or "No internal contradictions detected."] --- ## What Was Not Checked [List any claims that could not be evaluated -- paywalled sources, claims requiring specialized databases, unfalsifiable assertions, etc.] --- ## Limitations - This tool accelerates human verification; it does not replace it. - Web search results may not include the most recent information or paywalled sources. - The adversarial review uses the same underlying model that may have produced the original output. It catches many issues but cannot catch all of them. - A claim rated VERIFIED means a supporting source was found, not that the claim is definitely correct. Sources can be wrong too. - Claims rated PLAUSIBLE may still be wrong. The absence of contradicting evidence is not proof of accuracy. --- name: doublecheck description: 'Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.' --- # Doublecheck Run a three-layer verification pipeline on AI-generated output. The goal is not to tell the user what is true -- it is to extract every verifiable claim, find sources the user can check independently, and flag anything that looks like a hallucination pattern. ## Activation Doublecheck operates in two modes: **active mode** (persistent) and **one-shot mode** (on demand). ### Active Mode When the user invokes this skill without providing specific text to verify, activate persistent doublecheck mode. Respond with: > **Doublecheck is now active.** I'll verify factual claims in my responses before presenting them. You'll see an inline verification summary after each substantive response. Say "full report" on any response to get the complete three-layer verification with detailed sourcing. Turn it off anytime by saying "turn off doublecheck." Then follow ALL of the rules below for the remainder of the conversation: **Rule: Classify