eval-loop SKILL.md skillA
eval-loop from lokeshrana9999/shipyard is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lokeshrana9999/shipyard/eval-loop@git:20261104.05cf5ddPins git:20261104.05cf5dd in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lokeshrana9999/shipyard
- Path
plugins/shipyard-delivery/skills/eval-loop/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261104.05cf5dd, committed Nov 4, 2026
- First version recorded
- Nov 4, 2026
- Size
- 8,866 bytes
- Repository stars
- 4
- License
- MIT
Improves prompt, skill, or instruction text in scored rounds against locked eval cases, with a frozen grader hash, replicates, holdout cases, and a human read of raw transcripts before pass. Use when asked to "run the evals and fix the prompt", "make the bot pass its cases", "is the new prompt better", or "iterate on this SKILL.md until the evals pass". Not for test suites or a one-off eval run.
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 loop Improve text that steers a model (a bot's system prompt, a `SKILL.md`, agent instructions) the way code is improved: a locked case set, a score per round, and a delta that means something. A grader change, a single run, or a tally shown as "pass" each break the comparison, so this skill refuses them. ## Inputs - **The text under improvement**: the file or files the change edits. Everything else in the round is read-only. - **Arguments**: a note of what changed, which goes in the round's `kind` cell; `baseline` forces a new baseline round; `pass` runs step 8 on the current best round; `round` runs the next fix round. With none, the report decides which round comes next. - **Cases**: the project's eval cases, by default in the layout of [references/case-format.md](references/case-format.md) (a folder per case: `case.yaml`, `graders/*.md`); any layout the runner understands works. A **holdout** folder holds cases that are run and scored but never opened by whoever edits the text. …
Read the whole file at its exact version.
How to install
mdr add lokeshrana9999/shipyard/eval-loop@sha256:5c06b96fc6d87c29The line at the top of this page pins the label git:20261104.05cf5dd, 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_potv5elrxm4b346g)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Nov 4, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261104.05cf5dd latest | 2026-11-04 | 05cf5dd | 8,866 B | A | view · diff |
| git:20261104.770639b | 2026-11-04 | 770639b | 8,732 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 (8866 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
lokeshrana9999/shipyard · 4 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_potv5elrxm4b346g GET https://markdownregistry.com/api/v1/resolve?ref=lokeshrana9999/shipyard/eval-loop GET https://markdownregistry.com/api/v1/blob/5c06b96fc6d87c297fce2697d27805888e87581de2000036e4ccf3fdba8a2044
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.