More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Claim Check: Every Result Backed by Its Data

    1

    This skill makes your agent back every sentence about a result with its data: each number, verdict word and citation checked against the results file it cites.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Claim Check: Every Result Backed by Its Data

    Claim Check: Every Result Backed by Its Data

    Example session with this skill installed

    Check my results section and claims list against the results files before I send them to my co-authors. Put a corrected copy of the results section in research/paper/results-checked.md so I can compare.

    • Read your context and instructions
    • Compiled the claim check

    I checked the results section and the claims list against the results files, and saved a corrected copy of the results section to research/paper/results-checked.md. The claim checker gives no errors or warnings on the corrected copy. On your original it found 6 errors and 9 warnings.

    "…test accuracy of 0.874 … against 0.860": TileMix's stored value is 0.87346, which rounds to

    0.873, not 0.874. Split into two sentences, each with its own 95% interval and seed count.
    2.

    "significantly better calibrated, lowering ECE by 0.0049": the interval for the difference runs from −0.018 to 0.0078, which includes zero. Now: "−0.0049 (95% CI −0.018 to 0.0078, 5 seeds), not distinguishable from zero at this sample size."
    3.

    "improves accuracy by 2.8%": the stored value is 0.02755 as a fraction, so "2.8%" is a conversion done by hand, and it reads as a relative change. Now: "raised accuracy … by 0.028 (95% CI 0.019 to 0.036, 5 seeds)."
    4.

    "at no extra training cost": the interval from −0.69 to 2.35 minutes includes zero, but it doesn't show zero cost. Now the estimate and interval.
    5.

    "generalises … outperforms the baseline (0.791 vs 0.774)": each arm is a single run, with no interval and no stored difference. Now each run in its own sentence, with "one run each can't separate the gap from seed-to-seed variation".
    6.

    "This is because mixing tiles forces…": no experiment isolated the mechanism. Now "One explanation…, not tested here, is…"

    Passed unchanged: "The paired difference was 0.013 (95% CI 0.010 to 0.016, 5 seeds)."

    Claims list: C1 checked; C2–C4 revised (replacement sentences given); C5 open: needs RegionalCover runs on several seeds per arm with the paired difference stored, and even then supports "on RegionalCover", not "generalises to larger regional datasets".

    Connects securely to your tools. The creator never sees your data.

    About this skill

    What it does

    A results section is where reviewers hold your sentences against your numbers. This skill makes your agent back every sentence about a result with its data: each number, verdict word and citation checked against the results file it cites. Point it at a results paragraph, a caption, an abstract or a claims list, and it checks each claim against its evidence (the estimate, its interval, its n) and rewrites only what fails:

    • Numbers match the data. Every number in a cited sentence must sit in the cited result within rounding. A mis-rounded estimate, a value copied from the wrong entry, a dropped minus sign or a fraction turned into a percent by hand is caught and fixed.
    • No verdict without the evidence for it. "Improves", "outperforms" and "significantly better" need a stored difference whose interval excludes zero. "No effect", "matches" and "no extra cost" need an equivalence test, not a wide interval. The skill writes the estimate and interval instead, or "not distinguishable from zero at this sample size".
    • One fact per citation. Two arms, two conditions or a raw value and its difference each get their own sentence and their own citation.
    • Scope stays where it was measured. A single-seed result is reported as one run; "generalises" needs evidence at every setting; a mechanism no experiment isolated becomes "one explanation, not tested here".
    • Reread before returning. An 8-step procedure, ending with a fact-by-fact reread of every claim sentence against its entry, then the checker, resolving every error it reports.

    The checker

    check_claims.py (Python 3.10+, standard library, no network) resolves every [results/<file>.json: <entry>] citation in your prose and claims.md and reports errors and warnings: number mismatches within rounding, hand unit conversions, verdict words over an interval that includes zero, equivalence words with no equivalence test, verdicts on n = 1 or with no interval, comparison words with no stored difference, citations that cover several results, and broken citations. In the demo it found 6 errors and 9 warnings in a draft results section and 0 in the corrected copy.

    How it differs from citation auditors

    Citation auditors check that a reference supports a sentence. Claim Check checks your own results: it opens the JSON your sentence cites and verifies the numbers and verdict words against the stored value, interval and n.

    What's included

    • SKILL.md: the citation syntax, the 8-step procedure, a quick-reference table and worked examples
    • references/verdict-words.md: nine families of verdict words (comparison, significance, equivalence, magnitude, mechanism, scope, trend, confirmation, ranking) and what evidence each needs
    • references/hard-cases.md: phrasing for null results, overlapping intervals, single runs, n = 1, missing intervals, many comparisons, percent versus percentage points
    • scripts/check_claims.py: the deterministic checker

    Part of the Aurora Lab research pipeline

    Works entirely on its own: with a research/ folder it reads research/results/*.json and updates research/claims.md; without one it works from the numbers you paste. Pairs well with Aurora Lab's Scientific Voice (how sentences read) and Test Readers (how a cold reader takes the paper), but needs neither.

    It checks claims against the evidence they cite; it does not run experiments or compute statistics, and it never invents a missing number: a claim that needs a result you have not stored (such as a paired difference or an equivalence test) is marked open with exactly what is missing. The checker matches verdict words from a fixed list, so a paraphrase ("edges out", "a clear gain") passes it and an innocent use ("we increased the batch size") draws a warning. A number passes the checker when it equals any value stored in the cited entry within the rounding it is written at, interval bounds included, so a mis-rounded estimate that equals a bound, or a small whole number that equals an unrelated count, slips through; numbers written as words are not checked. The checker cannot judge scope, mechanism or whether the right entry was cited: the agent's reread covers those, and it is a careful review, not a guarantee. The checker reads citations in the [results/<file>.json: <entry>] form; other ways of pointing at evidence are checked by the agent only. It does not check references to the literature.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 29 days ago

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    research/results/**
    research/claims.md
    research/paper/**
    research/figures/*.md

    Reads the results files your sentences cite (research/results/*.json), your claims list (research/claims.md) and the prose you ask it to check (research/paper/*, figure captions), or numbers you paste. Writes claims.md (sentences and status) and edits paper text or captions only when you ask for edits rather than a review; a corrected copy goes where you say. The checker reads files and writes nothing. Never modifies your results files. No network access.

    Listed29 days ago

    What's inside

    Frequently Asked Questions

    Citation auditors check that a paper you cite supports your sentence. Claim Check checks your own results: it opens the JSON file your sentence cites and verifies every number within rounding, every verdict word against the stored interval, and that each citation names one result. It does not check literature references.

    One JSON object per result, or a list of them, with value (or mean or estimate), and ideally ci (or ci_low/ci_high), n, unit and a note on what n counts. A sentence cites one entry as [results/main.json: acc_diff] by its metric, name or id, or by a dotted path. With no research/ folder, paste the numbers and the agent applies the same rules.

    No. It matches verdict words from a fixed list and numbers within rounding. Paraphrases such as "edges out" pass it, innocent uses of a listed word draw a warning, a small whole number can match an unrelated count, a mis-rounded number that equals an interval bound passes, and numbers written as words are not checked. That is why the procedure ends with the agent rereading each sentence fact by fact against its entry.

    When you ask for a review it reports each failing sentence with the fix and the reason, lists what passed unchanged, and leaves your files alone (it can update claims.md statuses). When you ask for edits, or for a corrected copy as in the demo, it writes them. Sentences that already pass are never rewritten.

    No. It never writes a number it computed in its head. If a claim needs a number that is not stored, such as the paired difference between two arms, it either computes it with code and stores it with its interval and n in a results file, or marks the claim open with exactly what needs computing.

    Yes. The procedure works on any text, and the checker reads LaTeX source as well as Markdown (escaped percent signs included) as long as citations use the [results/...] form, for example in a % comment. Strip the citations from the submitted text and keep them in claims.md.

    New in Research & Analysis