diagnosis-evidence SKILL.md skillA
diagnosis-evidence from kamiazya/whiteboard is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kamiazya/whiteboard/diagnosis-evidence@git:20261015.4ac2e19Pins git:20261015.4ac2e19 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kamiazya/whiteboard
- Path
.claude/skills/diagnosis-evidence/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261015.4ac2e19, committed Oct 15, 2026
- First version recorded
- Aug 16, 2026
- Size
- 11,836 bytes
- Repository stars
- 10
- License
- Apache-2.0
Make a diagnosis prove it measured what it claims — before reporting a cause, a "not a regression", a mutation check, or a passing verification. Use when debugging a failing test, a CI failure, a flake, or verifying a fix by hand.
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
# A diagnosis is only as good as the proof that you measured what you think `measured-change` is about instrumenting a CHANGE whose effect you cannot see. This is about the step before: a FAILURE you are explaining, or a fix you are calling verified. Both fail the same way — a number arrives, it looks like evidence, and nothing in it says what was actually exercised. Every rule below cost a wrong public conclusion in one session. ## Pick an observation that could REFUTE the claim The rule the others are instances of. Three wrong conclusions in one session shared this shape: the observation taken was CONSISTENT with the claim and could not have contradicted it, so it read as confirmation while testing nothing. - A mutant reported `failed 1 test` and was read as killed. The failing test was a flake, in a file the mutated line cannot reach; three full runs of the mutated build all passed. One failure is equally consistent with killed and with a flake — only WHICH test failed tells them apart. - A survivor at `elements[0]?.attrs?.[name]` was hand-checked by mutating both optional chains. It went red, and the reported mutant was only one of them. …
Read the whole file at its exact version.
How to install
mdr add kamiazya/whiteboard/diagnosis-evidence@sha256:3eea8a29a29b9802The line at the top of this page pins the label git:20261015.4ac2e19, 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_yes45uck5acysej3)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Aug 16, 2026 and Oct 15, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261015.4ac2e19 latest | 2026-10-15 | 4ac2e19 | 11,836 B | A | view · diff |
| git:20261015.69103cd | 2026-10-15 | 69103cd | 11,580 B | A | view · diff |
| git:20261015.cf7a9f9 | 2026-10-15 | cf7a9f9 | 11,435 B | A | view · diff |
| git:20261003.a71f44f | 2026-10-03 | a71f44f | 10,714 B | A | view · diff |
| git:20260921.c38b541 | 2026-09-21 | c38b541 | 10,502 B | A | view · diff |
| git:20260831.7d13b8f | 2026-08-31 | 7d13b8f | 8,897 B | A | view · diff |
| git:20260830.65e6c5d | 2026-08-30 | 65e6c5d | 7,033 B | A | view · diff |
| git:20260816.46b8939 | 2026-08-16 | 46b8939 | 5,274 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 (11836 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
kamiazya/whiteboard · 10 stars · license Apache-2.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_yes45uck5acysej3 GET https://markdownregistry.com/api/v1/resolve?ref=kamiazya/whiteboard/diagnosis-evidence GET https://markdownregistry.com/api/v1/blob/3eea8a29a29b980274d4d5341f5bbe4f07328c11894eff586c2ed5de0c63dfe3
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.