proof SKILL.md skillA
proof from sanexxxx777/curated-claude-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add sanexxxx777/curated-claude-code/proof@git:20260907.9950df7Pins git:20260907.9950df7 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- sanexxxx777/curated-claude-code
- Path
skills/proof/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260907.9950df7, committed Sep 7, 2026
- Size
- 7,506 bytes
- Repository stars
- 16
- License
- MIT
Prove — or honestly fail to prove — a specific technical claim: "the fix works", "it's deployed", "the service is running", "the site is done", "there are no vulnerabilities". Atomizes the claim, picks the shortest decisive signal on the evidence ladder, and returns a verdict from a fixed vocabulary (pass / partial / fail / skip) with an explicit coverage boundary. NOT code review, NOT a fix, NOT orchestration — only "what is proven, and what we merely hope". Triggers — "prove it works…
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
# /proof — prove it, or say honestly that you can't
Claim under test: $ARGUMENTS
An agent's most expensive habit is not being wrong. It's reporting *done* on work that was never checked, in language indistinguishable from work that was. This skill makes the difference legible: for every claim, the shortest signal that would actually decide it, and a verdict that admits when no such signal was collected.
**Not this skill's job:** finding bugs (`pre-push`, code review), fixing them, deciding what to build. It only grades evidence.
## Step 1 — atomize the claim
"The service works" is not one claim. It's four: the code was changed, the change is in the running process, the process is doing the work, and the work has the intended effect. Each is provable separately, and they fail independently — a deployed process can be running week-old code, and a live feature can be silently dead.
Write the atoms down before collecting anything. A claim that resists atomizing ("it's better now") isn't provable — reformulate it into an outcome or return `skip`.
## Step 2 — the evidence ladder
…Read the whole file at its exact version.
How to install
mdr add sanexxxx777/curated-claude-code/proof@sha256:f5c73cc545c355a5The line at the top of this page pins the label git:20260907.9950df7, 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_bv4chwp4b3ssceho)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 7, 2026.
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 (7506 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
sanexxxx777/curated-claude-code · 16 stars · license MIT · pushed 2026-09-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bv4chwp4b3ssceho GET https://markdownregistry.com/api/v1/resolve?ref=sanexxxx777/curated-claude-code/proof GET https://markdownregistry.com/api/v1/blob/f5c73cc545c355a55432cec0e66bddc32a7017d1951944a3fd19a3325e102ae8
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 sanexxxx777/curated-claude-code
Every file in sanexxxx777/curated-claude-code