lilmgenius/paperthin

factchk

Verify reality-grounded claims against external sources in both directions before they ship: could the 'absurd' be real, could the 'obvious' be false or long-established?

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/lilmgenius/paperthin --skill factchk

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Check claims against reality in both directions before they ship.

Goal

The author's judgment of what is plausible, absurd, or novel is the least reliable line in an artifact. Human priors fail both ways: they exclude the real (desert frogs exist) and normalize the impossible (weightless crates). factchk checks reality-grounded claims against external sources, then fixes errors or flags judgment calls. It checks claims about the world, not the soundness of a validation or the survival of a whole plan.

Workflow

  1. Scan for reality-grounded assertions that call something plausible, realistic, absurd, novel, or impossible because of a factual premise. Include claims you are about to write. Collect worth judgments too (overrated, legendary) for the rule below.
  2. Verify each against external sources (web search, open references) in both directions: could the "absurd" be real? Could the "obvious" or "novel" be false or long-established? If you cannot reach a source, flag it; never assert from intuition.
  3. Fix or flag: correct mechanically clear errors, such as wrong dates, misattributed sources, or falsified numbers, with a cited source. Surface contested or interpretive claims as judgment calls; do not silently rewrite them.
  4. Report each claim, its verdict, the source, and which direction a failed claim failed.

Rules

  • Target claims asserted as reality-grounded, never deliberate fiction ("in our world, boxes float" is a declared choice). If it is unclear whether a claim is an in-world choice or a real-world assertion, flag, don't fix.
  • Flagging only the unrealistic catches half the errors.
  • A claim about a person (a title, a past role, a school, an age) is read from that person's own profile or record, and where the source allows two values the artifact states the one that cannot overstate, such as the younger age when a birthday is unknown.
  • A worth judgment (overrated, legendary) states no fact. Check the factual premise it rests on, if any (an "overrated" inventor whose credited work was mostly a team's), and report the judgment itself as a judgment call. When it decides whether a person or thing belongs in a list or set, report that fit question for paperthin:scopechk without judging it here.
  • Metacognitive doubt triggers the check. You cannot know every domain; when you are about to assert a checkable fact from a feeling, verify it.
  • A pass that finds nothing changes nothing.

Verification

Before finishing, confirm that every verdict traces to a citable external source. The report distinguishes fixes from flags; it does not restate prior intuitions.

同じリポジトリから

関連する Skills

すべての Skills
lilmgenius
コミュニティ

re0-order

Move items only, reword nothing; realign a listing whose order has gone arbitrary (a list, table, catalog, sections, an enum) into a logical sequence under one stated principle. Nothing is added or removed. Use when the user names a listing, or a scope holding one, whose order no longer helps a reader follow the set, or when a pipeline the user invoked passes that scope on. Acts only inside that scope.

1時間の導入数
5
GitHub Stars
1463
更新日
11月15日
lilmgenius
コミュニティ

readback

Verify the model's understanding of a user's instruction before spending non-trivial work. Use when a request is long, bundled, high-stakes, hard to undo, or has ambiguous scope or referents such as this, that, it, the other one, whatever is cleaner, or whichever order makes sense. Restate internally, cross-check against available context, proceed silently when resolved, and surface only a genuine surviving fork.

1時間の導入数
5
GitHub Stars
1463
更新日
11月15日
lilmgenius
コミュニティ

whychk

Right after you pick an option, have a fresh outsider find the sharpest gap in the choice, then explain that gap in your own words, one gap at a time.

1時間の導入数
5
GitHub Stars
1463
更新日
11月15日
lilmgenius
コミュニティ

aim

When data lands with a thin ask (files, a repo, a paste, a chat scrollback), read it and propose what the user is trying to do with it for them to confirm. Use the moment material arrives without a fully-formed ask, or when the ask reads thinner than the data suggests.

1時間の導入数
4
GitHub Stars
1463
更新日
11月15日