eval SKILL.md skillA
eval from ariaxhan/kernel-claude is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ariaxhan/kernel-claude/eval@git:20261017.fd085caPins git:20261017.fd085ca in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ariaxhan/kernel-claude
- Path
skills/eval/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261017.fd085ca, committed Oct 17, 2026
- First version recorded
- Mar 8, 2026
- Size
- 6,013 bytes
- Repository stars
- 14
- License
- MIT
Eval-Driven Development (EDD) for AI workflows. pass@k metrics, capability evals, regression evals. Triggers: eval, edd, pass@k, capability, regression, benchmark.
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
<skill id="eval">
<prerequisite>
AgentDB read-start has run. Check for existing eval definitions in _meta/research/.
Understand what behavior you're evaluating before writing evals.
</prerequisite>
<reference>
Skill-specific: skills/eval/reference/eval-research.md
</reference>
<core_principles>
1. DEFINE BEFORE CODE: Evals written first force clear thinking about success criteria.
2. CODE GRADERS > MODEL GRADERS: Deterministic checks beat probabilistic judgments.
3. STRUCTURAL SEPARATION FOR HIGH-STAKES: When stakes are real (security, payments, eval-of-evals, agent quality scoring), use the blind-evaluator agent — never self-score. Self-scoring inflates results ~36% structurally; procedural separation ("I won't peek") does not fix it.
4. TRACK PASS@K: pass@1 (first attempt), pass@3 (within 3 attempts). Target pass@3 > 90%.
5. REGRESSION BEFORE SHIP: Every change must pass existing evals before merge.
6. FAST EVALS GET RUN: Slow evals get skipped. Keep evaluation fast.
</core_principles>
<workflow>
1. DEFINE: Write eval criteria before implementation. (gate: criteria exist in writing before any code)
2. IMPLEMENT: Code to pass defined evals.
…Read the whole file at its exact version.
How to install
mdr add ariaxhan/kernel-claude/eval@sha256:0bedeef3d095c785The line at the top of this page pins the label git:20261017.fd085ca, 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_q4medzewqculvo4u)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Mar 8, 2026 and Oct 17, 2026, about one every 45 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261017.fd085ca latest | 2026-10-17 | fd085ca | 6,013 B | A | view · diff |
| git:20260925.e05bd1d | 2026-09-25 | e05bd1d | 5,213 B | A | view · diff |
| git:20260711.c23e6cb | 2026-07-11 | c23e6cb | 4,860 B | A | view · diff |
| git:20260528.5379829 | 2026-05-28 | 5379829 | 4,777 B | A | view · diff |
| git:20260515.83dfa7b | 2026-05-15 | 83dfa7b | 6,188 B | A | view · diff |
| git:20260308.02f853e | 2026-03-08 | 02f853e | 4,154 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 (6013 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
ariaxhan/kernel-claude · 14 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q4medzewqculvo4u GET https://markdownregistry.com/api/v1/resolve?ref=ariaxhan/kernel-claude/eval GET https://markdownregistry.com/api/v1/blob/0bedeef3d095c7853190f38d3a8433017be61557f813fb2f90a2676aab255e46
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 ariaxhan/kernel-claude
Every file in ariaxhan/kernel-claude