@vasanthsreeram/learn-verify
@vasanthsreeram/learn-verify — AI coding skill
| name | learn-verify |
| description | > |
| license | MIT |
Learn verify
Trust is engineered. Check the claim before it is taught as fact.
When to run
- Empirical, historical, bibliographic, or API/tool claims
- Named theorems, identities, or "standard facts" you cannot reconstruct
- Anything you were about to present with unearned certainty
Skip a full search only when you can derive the statement in-session and the learner does not need an external citation. Still say that it was derived, not sourced.
Method
- Write the claim in one falsifiable sentence.
- Fetch or search primary-ish sources (paper, textbook, official docs, standard reference). Do not cite a URL you did not open.
- Quote or paraphrase the supporting line. Note edition / year if it matters.
- Mark disagreements. Prefer the source the field actually uses.
- Return a verdict.
Verdict
## Claim
…
## Verdict
confirmed | qualified | contradicted | unknown
## Sources
- <title> — <url or citation> — <what it says>
## Teach as
<one sentence the teacher may now say, with any hedge>
qualified = true under stated assumptions (dimension, characteristic, gauge, version).
unknown = do not teach it as fact. Say you could not verify.
Rules
- No invented papers, quotes, or page numbers.
- One claim per run. Batch only if they are the same fact in different words.
- Write the verdict into the session file if a teach session is open.
Loading...
Select a file to preview
Analyzing security...
Checking scan reports and verification data.
Bill of Materials
Everything this skill can do — files, network, commands, and more.