evaluate-skill SKILL.md skillA

evaluate-skill from edonadei/caliper is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add edonadei/caliper/evaluate-skill@git:20261009.dff52c2

Pins git:20261009.dff52c2 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: edonadei/caliper
Path: skills/evaluate-skill/SKILL.md
Versions recorded: 6
Latest version: git:20261009.dff52c2, committed Oct 9, 2026
First version recorded: Sep 25, 2026
Size: 7,902 bytes
Repository stars: 217
License: MIT

Run, read, and diagnose a skill's Caliper eval — its success rate over k attempts, whether it fires, and whether it beats the agent without it. Use when the user wants to run, validate, interpret, or compare a skill's eval, or write an .eval.yaml spec whose tasks they have already decided.

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

# Evaluate Skill

Operate Caliper: run a skill's eval, read what the results say, and trace each failure to the place that fixes it.

## Prerequisites

The `caliper` CLI must be on `PATH`. This skill can be copied into an agent without the Caliper repo, so install it if missing:

```bash
pipx install caliper-eval
```

`caliper <command> --help` is the authority on flags. [REFERENCE.md](REFERENCE.md) covers the full spec format, engines, and what the results mean.

## The four questions

A skill eval answers four separate questions. Each has its own measurement and its own fix location, so keep them apart: a blended number hides which half broke.

| Question | Measured by | A failure is fixed in |
|---|---|---|
| **Fires**: does the agent reach for the skill when it should, and only then? | `activates:` on tasks, and trigger probes | the skill's `description` frontmatter |
| **Works**: once it fires, does it get the job done? | `expect:` / `assert:`, scored as the success rate | the skill's body |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add edonadei/caliper/evaluate-skill@sha256:21df2e6831a51a8e

The line at the top of this page pins the label git:20261009.dff52c2, 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](https://markdownregistry.com/badge/art_xryxmicsyi6q3yyj.svg)](https://markdownregistry.com/a/art_xryxmicsyi6q3yyj)

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

Versions

The registry has recorded 6 versions of this file, between Sep 25, 2026 and Oct 9, 2026, about one every 3 days.

version	committed	commit	size	audit
git:20261009.dff52c2 latest	2026-10-09	dff52c2	7,902 B	A	view · diff
git:20260928.40029d0	2026-09-28	40029d0	7,595 B	A	view · diff
git:20260925.74cacc3	2026-09-25	74cacc3	7,545 B	A	view · diff
git:20260925.6642b75	2026-09-25	6642b75	7,709 B	A	view · diff
git:20260925.641b59e	2026-09-25	641b59e	4,548 B	A	view · diff
git:20260925.7d6a2a9	2026-09-25	7d6a2a9	4,526 B	A	view

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 (7902 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

edonadei/caliper · 217 stars · license MIT · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_xryxmicsyi6q3yyj
GET https://markdownregistry.com/api/v1/resolve?ref=edonadei/caliper/evaluate-skill
GET https://markdownregistry.com/api/v1/blob/21df2e6831a51a8e120d72a99c6f25d214ee9adb36b85289474c1e9a6b63561c

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 edonadei/caliper

AGENTS.md AGENTS.md file

edonadei/caliper · AGENTS.md

git:20261003.9a1a549 · audit A · 217 stars

save-note SKILL.md skill

edonadei/caliper · examples/01-false-success/SKILL.md · Save a short note to a file. Use when asked to record, save, or jot down a note.