kelly-agent-eval skillA
kelly-agent-eval is agent-read markdown (skill) from mr-kelly/skills: Review board (Busabase App-in-Skill) that runs a fixed suite of mock test cases against a baseline vs candidate agent version and surfaces rubric-scored regressions before a release. Use when the user invokes $kelly-agent-eval or /kelly-agent-eval, wants to review agent-version regressions, compare baseline vs candidate quality, triage a release, or record a release approve/block decision. Deterministic mock rubric scores only — not a real LLM-judge call, and it never deploys anything..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
How to install
mdr add mr-kelly/skills/kelly-agent-eval@git:20260824.d18190amdr add mr-kelly/skills/kelly-agent-eval@sha256:579eca52dad5c3a2Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_lv5zev4x3i2bzxhk)
0 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260824.d18190a latest | 2026-08-24 | d18190a | 9,068 B | A | view · diff |
| git:20260808.5ce8d82 | 2026-08-08 | 5ce8d82 | 8,739 B | A | view · diff |
| git:20260806.bed1b85 | 2026-08-06 | bed1b85 | 8,658 B | A | view · diff |
| git:20260711.c9add96 | 2026-07-11 | c9add96 | 6,655 B | A | view · diff |
| git:20260710.afe1046 | 2026-07-10 | afe1046 | 6,665 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 (9068 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
mr-kelly/skills · 5 stars · license MIT · pushed 2026-09-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lv5zev4x3i2bzxhk GET https://markdownregistry.com/api/v1/resolve?ref=mr-kelly/skills/kelly-agent-eval GET https://markdownregistry.com/api/v1/blob/579eca52dad5c3a2a12c30dd4d4cd0529f6d1400522e60eb3f1564ca1abab490