eval-grader SKILL.md skillA
eval-grader from byerlikaya/claude-starter-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add byerlikaya/claude-starter-kit/eval-grader@git:20260926.aaa5dbcPins git:20260926.aaa5dbc in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- byerlikaya/claude-starter-kit
- Path
plugin/skills/eval-grader/SKILL.md- Versions recorded
- 6
- Latest version
- git:20260926.aaa5dbc, committed Sep 26, 2026
- First version recorded
- Jul 19, 2026
- Size
- 4,729 bytes
- Repository stars
- 26
- License
- MIT
Measure output quality, don't vibe it: score a generative task with a two-layer grader — deterministic code metrics + per-dimension LLM-as-judge — over a fixed task set, as signed deltas vs a pinned baseline. Grades cost alongside correctness (pass-slow).
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 Grader <!-- routing-eval reads the next line; why it sits in the body: AGENT_TEMPLATE.md --> Trigger phrases: "eval", "grader", "measure output quality", "LLM-as-judge", "score the output" **Measure every change; don't vibe it.** When you iterate on a prompt, an agent, or any generative output (docs, slides, UI, a summary, an extraction), a two-layer grader over a fixed task set turns "feels better" into a signed number you can trust. This is the **external, machine-grounded verifier** the `iterate` skill asks for — a model grading its *own* output inflates; a separate grader on a fixed suite does not. > **Crewforth adaptation (local, .claude/):** use when tuning a generative task; the scorecard goes to `docs/EVAL.md` > (§4.3). Stack-agnostic — graders are ordinary code + judge calls. §4 Prohibitions apply. ## Two layers - **Layer 1 — code graders** (deterministic, near-free, run every time): structural metrics over the artifact — *did it produce a valid result?* plus counts, sizes, schema validity, "wall-of-text" / clutter flags. They catch gross regressions a judge shouldn't be spent on. Ground truth is **computed from the source**, not hand-authored. …
Read the whole file at its exact version.
How to install
mdr add byerlikaya/claude-starter-kit/eval-grader@sha256:26796bf81de32e1fThe line at the top of this page pins the label git:20260926.aaa5dbc, 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_wsxz76x7a3tp3t6e)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jul 19, 2026 and Sep 26, 2026, about one every 14 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260926.aaa5dbc latest | 2026-09-26 | aaa5dbc | 4,729 B | A | view · diff |
| git:20260925.68939f0 | 2026-09-25 | 68939f0 | 4,723 B | A | view · diff |
| git:20260924.a457823 | 2026-09-24 | a457823 | 4,721 B | A | view · diff |
| git:20260730.0bf7183 | 2026-07-30 | 0bf7183 | 4,901 B | A | view · diff |
| git:20260729.9ca4378 | 2026-07-29 | 9ca4378 | 4,622 B | A | view · diff |
| git:20260719.763560b | 2026-07-19 | 763560b | 2,996 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 (4729 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
byerlikaya/claude-starter-kit · 26 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wsxz76x7a3tp3t6e GET https://markdownregistry.com/api/v1/resolve?ref=byerlikaya/claude-starter-kit/eval-grader GET https://markdownregistry.com/api/v1/blob/26796bf81de32e1f9706ca1e238d5365f18c4e00c546f6c632026855238c6128
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.
More from byerlikaya/claude-starter-kit
Every file in byerlikaya/claude-starter-kit