verifying-proofs SKILL.md skillA
verifying-proofs from chgagne/claude-skills-research is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add chgagne/claude-skills-research/verifying-proofs@git:20260817.78f3c11Pins git:20260817.78f3c11 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- chgagne/claude-skills-research
- Path
verifying-proofs/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260817.78f3c11, committed Aug 17, 2026
- First version recorded
- Aug 16, 2026
- Size
- 25,328 bytes
- Repository stars
- 5
- License
- MIT
Use when checking the mathematics of a paper rather than its claims — verifying a theorem's proof, an algebraic derivation, a bound, or an appendix full of lemmas. Triggers on "check this proof", "verify the derivation", "is Lemma 3 correct", "does the algebra work", a paper directory containing theorem/proof environments, or a referee asking whether a mathematical argument holds.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Verifying Proofs ## Overview **A proof is refuted one step at a time, and reported one gap at a time.** The useful output of this skill is rarely "the theorem is false" — it is *this step needs a hypothesis nobody stated*, *this induction has no base case*, *this lemma's appendix restatement drops a condition its proof uses*. **Core principle: the tool may never report its own limitations as the paper's mistakes.** Every rule below exists to keep that true. A checker that says "counterexample at $x = -11/5$" about a step that plainly meant $x > 0$ has not found an error; it has taught its reader to ignore the next twenty findings. Two consequences, both measured on real papers: - **A symbol whose domain the paper never stated can never produce a counterexample.** On arXiv:1509.01240, 54 of 61 symbols had no readable domain. Sampling those freely would have produced dozens of "errors" against correct mathematics. - **The default run is a hygiene checker, not a correctness checker.** Measured against six papers with documented, localised proof errors, the no-CAS engines found **none of them**. What they do find — a dependency cycle, an induction …
Read the whole file at its exact version.
How to install
mdr add chgagne/claude-skills-research/verifying-proofs@sha256:9bf45ff47a8f8f75The line at the top of this page pins the label git:20260817.78f3c11, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_yb3movpbnbtvhtcx)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 16, 2026 and Aug 17, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260817.78f3c11 latest | 2026-08-17 | 78f3c11 | 25,328 B | A | view · diff |
| git:20260817.49db450 | 2026-08-17 | 49db450 | 23,364 B | A | view · diff |
| git:20260817.e1eb8ef | 2026-08-17 | e1eb8ef | 20,370 B | A | view · diff |
| git:20260816.e0a2f7c | 2026-08-16 | e0a2f7c | 19,287 B | A | view · diff |
| git:20260816.b092bb5 | 2026-08-16 | b092bb5 | 18,885 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (25328 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
chgagne/claude-skills-research · 5 stars · license MIT · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_yb3movpbnbtvhtcx GET https://markdownregistry.com/api/v1/resolve?ref=chgagne/claude-skills-research/verifying-proofs GET https://markdownregistry.com/api/v1/blob/9bf45ff47a8f8f754d90d90189eadc3ea6fa86635c85e72f927cad11fb4fad2e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.