prove SKILL.md skillA

prove from dylan/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dylan/skills/prove@git:20261109.5ef7913

Pins git:20261109.5ef7913 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
dylan/skills
Path
plugins/rigor/skills/prove/SKILL.md
Versions recorded
1
Latest version
git:20261109.5ef7913, committed Nov 9, 2026
Size
3,988 bytes
Repository stars
2
License
none declared

Finds and runs the check that could show a result is wrong. It splits a finished result, claim, fix or answer into testable claims and picks a check for each that can fail and doesn't rely on the model or the user. It writes each pass condition down before running the check, runs it, and reports passed, failed or unverified with evidence. Use when the user runs /prove, asks to prove, verify or check that something is right, asks "how do we know this works", or wants evidence about finished…

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

# Prove

Show whether a result is right with a check that could have shown it wrong. The skill produces evidence, not a review.

## What makes this work

- Testable claims. Nobody can check "the fix works". Anyone can check "the request that returned 500 now returns 200, and the existing suite still passes".
- An outside check. Neither the model rereading its own work nor the user eyeballing it can disagree with the result. Running code, taking a measurement, reproducing a number or reading the primary source can.
- Pass conditions written first. Writing down what counts as a pass before seeing the outcome keeps the goalposts from moving to fit it.
- Running the check. A check that is only described proves nothing, so an unrun check leaves its claim unverified.

## Input

The skill's argument names the result to check: a claim, a diff, an answer, a document or a number. With no argument, check the most recent result in this conversation, including the agent's own. If there is nothing to check, ask what to check.

## Step 1: State the claims
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_ymj3klxtxt5x2oy3/11a54756853418d1163e6a9b360f3633e9815b8230ac4174d186615cee7bcd23.json

Then /plugin install prove@markdownregistry-ymj3klxtxt5x2oy3 in Claude Code. It installs git:20261109.5ef7913, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add dylan/skills/prove@sha256:11a54756853418d1

The line at the top of this page pins the label git:20261109.5ef7913, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ymj3klxtxt5x2oy3.svg)](https://markdownregistry.com/a/art_ymj3klxtxt5x2oy3)

3 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in dylan/skills/prove since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of prove from somewhere else? Ask it: where did my prove come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Nov 9, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261109.5ef7913 latest2026-11-09 5ef7913 3,988 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3988 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

GitHub

dylan/skills · 2 stars · license none declared · pushed 2026-11-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ymj3klxtxt5x2oy3
GET https://markdownregistry.com/api/v1/resolve?ref=dylan/skills/prove
GET https://markdownregistry.com/api/v1/blob/11a54756853418d1163e6a9b360f3633e9815b8230ac4174d186615cee7bcd23

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.

More from dylan/skills

dylan Plugin marketplace
dylan/skills · .claude-plugin/marketplace.json · Plugins and agent skills by Dylan, installable as Claude Code plugins or into any agent with npx skills. (4 plugins…
git:20261109.bb97235 · audit A · 2 stars
AGENTS.md AGENTS.md file
dylan/skills · AGENTS.md
git:20261109.891d382 · audit A · 2 stars
c64-hardware SKILL.md skill
dylan/skills · plugins/c64/skills/c64-hardware/SKILL.md · Commodore 64 reference with exact numbers: 6510 opcodes and cycle counts, VIC-II registers and raster timing, raster…
git:20261109.bb97235 · audit A · 2 stars
nato-name SKILL.md skill
dylan/skills · plugins/nato-name/skills/nato-name/SKILL.md · Pick an unused NATO reporting name as a placeholder project name. Use when starting a new project or when asked for a…
git:20261109.5ef7913 · audit A · 2 stars
deepen SKILL.md skill
dylan/skills · plugins/rigor/skills/deepen/SKILL.md · Deepens a task prompt before it runs. It names what a top professional in the field would do that the prompt doesn't…
git:20261109.5ef7913 · audit A · 2 stars
narrow SKILL.md skill
dylan/skills · plugins/rigor/skills/narrow/SKILL.md · Cuts a task prompt down to the question that matters before it runs. It names the real question behind the prompt, what…
git:20261109.5ef7913 · audit A · 2 stars
swift-api-design SKILL.md skill
dylan/skills · plugins/swift-api-design/skills/swift-api-design/SKILL.md · Apply when writing, reviewing, or designing any Swift code — functions, types, protocols, closures, or local functions…
git:20260906.c04923b · audit A · 2 stars

Every file in dylan/skills

Other files named prove

prove SKILL.md skill
wenlan-app/wenlan · .claude/skills/prove/SKILL.md · Per-surface verification loops for wenlan — daemon, cli, mcp, plugin, suite strength (mutation), behavior trace, weekly…
git:20261019.1b4e3ca · audit A · 498 stars
prove SKILL.md skill
7xuanlu/wenlan · .claude/skills/prove/SKILL.md · Per-surface verification loops for wenlan — daemon, cli, mcp, plugin, suite strength (mutation), behavior trace, weekly…
git:20261019.1b4e3ca · audit A · 441 stars
prove SKILL.md skill
nyelonong/galdr · skills/prove/SKILL.md · Use before you change production code, before you claim that work is complete, or when you audit a document against…
git:20261115.1faad52 · audit A · 13 stars

Browse by kind, by grade A, or by owner.