skill-eval SKILL.md skillA
skill-eval from greglas75/zuvo is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add greglas75/zuvo/skill-eval@git:20260906.015072fPins git:20260906.015072f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- greglas75/zuvo
- Path
skills/skill-eval/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260906.015072f, committed Sep 6, 2026
- First version recorded
- Jul 10, 2026
- Size
- 34,529 bytes
- Repository stars
- 7
- License
- MIT
Behavioral evaluator for zuvo skills. Runs a skill against its eval corpus (evals/<skill>.evals.json) in fresh executor sub-agents, grades each run transcript against the corpus assertions with an injection-hardened grader, and writes a per-assertion pass/fail report to zuvo/reports/. Supports old-vs-new comparison via --compare <ref>. Dev-only (needs the repo's evals/ + .git).
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
# zuvo:skill-eval — Behavioral skill evaluator Measure whether a skill's own instructions lead a competent agent to the correct behavior. For each eval case in the skill's corpus, a fresh **executor** sub-agent runs the skill against the case prompt; a fresh **grader** sub-agent then scores that run's transcript against the case's assertions — judging only real tool calls, never prose or marker text. The output is a per-assertion pass/fail report with verbatim evidence, plus an optional old-vs-new score diff. This skill is **dev-only**: it reads the repo's `evals/` corpus and (for `--compare`) `.git` history, so it is deliberately NOT distributed into installed plugin caches. --- ## Argument Parsing | Token | Meaning | Default | |-------|---------|---------| | `[skill-name]` | The skill to evaluate; resolves its corpus at `evals/<skill-name>.evals.json`. | required unless `--all-evals` | | `--compare <ref>` | Also score the OLD version of the skill materialized from git `<ref>` and report an old-vs-new diff. | off (grade current version only) | | `--all-evals` | Evaluate every `evals/*.evals.json` corpus in the repo, not just one skill. | off | …
Read the whole file at its exact version.
How to install
mdr add greglas75/zuvo/skill-eval@sha256:d4e033917f1df53aThe line at the top of this page pins the label git:20260906.015072f, 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_ab5ooyvlojgbvgp2)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 10, 2026 and Sep 6, 2026, about one every 14 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260906.015072f latest | 2026-09-06 | 015072f | 34,529 B | A | view · diff |
| git:20260810.40e315f | 2026-08-10 | 40e315f | 34,753 B | A | view · diff |
| git:20260806.6edffe2 | 2026-08-06 | 6edffe2 | 34,277 B | A | view · diff |
| git:20260802.56ae227 | 2026-08-02 | 56ae227 | 33,590 B | A | view · diff |
| git:20260710.02267d3 | 2026-07-10 | 02267d3 | 33,572 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 (34529 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
greglas75/zuvo · 7 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ab5ooyvlojgbvgp2 GET https://markdownregistry.com/api/v1/resolve?ref=greglas75/zuvo/skill-eval GET https://markdownregistry.com/api/v1/blob/d4e033917f1df53a2a3bfe40467c224557c75331f87e2fb31d575dcac2e79f76
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.