eval-regression SKILL.md skillA
eval-regression from reidemeister94/development-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add reidemeister94/development-skills/eval-regression@git:20261031.a82a617Pins git:20261031.a82a617 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- reidemeister94/development-skills
- Path
skills/eval-regression/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261031.a82a617, committed Oct 31, 2026
- First version recorded
- Mar 23, 2026
- Size
- 2,536 bytes
- Repository stars
- 12
- License
- MIT
Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.
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
# Eval regression Use deterministic repository tests first. Stop when the target has no behavioral diff. Resolve the plugin from the argument or cwd. Its catalog is `evals/evals.json`; the runner is `scripts/run_evals.py` in this skill. The runner can load the operator's settings and other installed plugins. Its results do not isolate this plugin's effect. For the native Claude routing cases, use `claude plugin eval` with `--no-publish` and an agreed case and run count. Require the user to choose agent, model, and effort. Never select a costly model or high effort silently. ## Normal check 1. Select cases by changed paths with `--changed-from <base>`, or name them with `--case`. Do not select the full catalog implicitly. 2. Run the command without `--run`. The runner prints cases, modes, repeats, sessions, timeout, and maximum duration without starting an agent. 3. An approved plan that names this exact run already authorizes it. For a standalone eval, present the run plan and stop once. 4. After approval, repeat the same command with `--run`. Default to candidate-only, one run per case, 180 seconds, and four sessions maximum. …
Read the whole file at its exact version.
How to install
mdr add reidemeister94/development-skills/eval-regression@sha256:05e4d1ca22e8faf5The line at the top of this page pins the label git:20261031.a82a617, 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_qubgpqnzdwagjbwe)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Mar 23, 2026 and Oct 31, 2026, about one every 44 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261031.a82a617 latest | 2026-10-31 | a82a617 | 2,536 B | A | view · diff |
| git:20260919.a9f7da5 | 2026-09-19 | a9f7da5 | 2,298 B | A | view · diff |
| git:20260724.ba2c70f | 2026-07-24 | ba2c70f | 2,427 B | A | view · diff |
| git:20260713.d210701 | 2026-07-13 | d210701 | 1,699 B | A | view · diff |
| git:20260617.174aad8 | 2026-06-17 | 174aad8 | 4,784 B | A | view · diff |
| git:20260323.6a51c16 | 2026-03-23 | 6a51c16 | 11,407 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 (2536 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
reidemeister94/development-skills · 12 stars · license MIT · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qubgpqnzdwagjbwe GET https://markdownregistry.com/api/v1/resolve?ref=reidemeister94/development-skills/eval-regression GET https://markdownregistry.com/api/v1/blob/05e4d1ca22e8faf5c44e23ba827463e3082a7482f657be703d0a9f547557e4e5
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.