agent-evaluation SKILL.md skillA
agent-evaluation from fmind/dot is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add fmind/dot/agent-evaluation@git:20261107.e294cb4Pins git:20261107.e294cb4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- fmind/dot
- Path
skills/agent-evaluation/SKILL.md- Versions recorded
- 15
- Latest version
- git:20261107.e294cb4, committed Nov 7, 2026
- First version recorded
- Sep 6, 2026
- Size
- 3,476 bytes
- Repository stars
- 13
- License
- MIT
Evaluate prompt, model, retrieval, and agent changes with graded trials.
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
# Agent Evaluation Decide whether a stochastic candidate improves observable outcomes under comparable conditions. [system-prompts](../agent-frameworks/references/system-prompts.md) prepares prompt changes; [python-testing](../python-stack/references/python-testing/GUIDE.md) owns deterministic software proof. Keep datasets and execution commands in the project or provider's existing evaluation workflow. ## Workflow 1. **Declare the decision first**: baseline, candidate, success criteria, blocking regressions, trial budget, and stopping rule in an [evaluation brief](references/evaluation-brief.md); a small probe supports iteration, not reliability claims. 1. **Change one factor at a time**: freeze code, prompt, tools, retrieval snapshot, model version, settings, and grader versions; label unpinned provider behavior as a reproducibility limit. 1. **Keep held-out cases sealed**: never tune on decision cases and still call them unseen. 1. **Grade outcomes, not prose**: prefer executable checks and inspected state; calibrate semantic judges against labeled examples, blind candidate identity, and escalate consequential disagreements to a human. …
Read the whole file at its exact version.
How to install
mdr add fmind/dot/agent-evaluation@sha256:339eafe644fa04e3The line at the top of this page pins the label git:20261107.e294cb4, 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_aiasjlcled63gzou)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 15 versions of this file, between Sep 6, 2026 and Nov 7, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261107.e294cb4 latest | 2026-11-07 | e294cb4 | 3,476 B | A | view · diff |
| git:20261031.ad68ebd | 2026-10-31 | ad68ebd | 3,411 B | A | view · diff |
| git:20261029.727fb3c | 2026-10-29 | 727fb3c | 3,409 B | A | view · diff |
| git:20261025.6c4dd76 | 2026-10-25 | 6c4dd76 | 3,418 B | A | view · diff |
| git:20261024.2349818 | 2026-10-24 | 2349818 | 3,365 B | A | view · diff |
| git:20261021.01ebf0c | 2026-10-21 | 01ebf0c | 3,368 B | A | view · diff |
| git:20261007.18f5c20 | 2026-10-07 | 18f5c20 | 3,350 B | A | view · diff |
| git:20261007.fbd724a | 2026-10-07 | fbd724a | 3,370 B | A | view · diff |
| git:20261005.e9af7a2 | 2026-10-05 | e9af7a2 | 4,258 B | A | view · diff |
| git:20261004.f03a551 | 2026-10-04 | f03a551 | 4,247 B | A | view · diff |
| git:20260926.626254b | 2026-09-26 | 626254b | 4,108 B | A | view · diff |
| git:20260916.50d6810 | 2026-09-16 | 50d6810 | 4,019 B | A | view · diff |
| git:20260911.616be7a | 2026-09-11 | 616be7a | 4,043 B | A | view · diff |
| git:20260909.892d859 | 2026-09-09 | 892d859 | 3,873 B | A | view · diff |
| git:20260906.a4e0ec8 | 2026-09-06 | a4e0ec8 | 3,231 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 (3476 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
fmind/dot · 13 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_aiasjlcled63gzou GET https://markdownregistry.com/api/v1/resolve?ref=fmind/dot/agent-evaluation GET https://markdownregistry.com/api/v1/blob/339eafe644fa04e3dfabf45c34fdbc3ca15789dee0b6e622aeaa99b1995ad2de
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.