eval-harness SKILL.md skillA

eval-harness from jikig-ai/soleur is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jikig-ai/soleur/eval-harness@git:20261003.57e28a5

Pins git:20261003.57e28a5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jikig-ai/soleur
Path
plugins/soleur/skills/eval-harness/SKILL.md
Versions recorded
10
Latest version
git:20261003.57e28a5, committed Oct 3, 2026
First version recorded
Jun 29, 2026
Size
12,705 bytes
Repository stars
21
License
a license file GitHub does not identify

This skill provides a promptfoo eval harness that measures whether a Soleur skill or agent edit actually improves behavior, comparing a skill arm against a baseline control arm.

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

<!-- soleur-cloud-mode:start -->
**Cloud Mode (Devin):** before pipeline work run `bash "${CLAUDE_PLUGIN_ROOT}/scripts/cloud-detect.sh"`. If `CLAUDE_PLUGIN_ROOT` is unset (cloud exec shells do not export it), resolve the root by IDENTITY, never by script basename: for `d` in `"$HOME/.local/share/devin/cli/plugins/cache"` and `/opt/.devin/plugins`, skip unless `[ -d "$d" ]`, then `MANIFEST="$(find "$d" -path '*/.claude-plugin/plugin.json' -exec grep -l '"name"[[:space:]]*:[[:space:]]*"soleur"' {} + 2>/dev/null | head -1)"`, `ROOT="${MANIFEST%/.claude-plugin/plugin.json}"` — one resolution, two consumers: `$ROOT/scripts/cloud-detect.sh` and `$ROOT/scripts/precommit-guard.sh`. (Shape check, not authentication: a planted `{"name":"soleur"}` dir passes — ADR-179 A11.) `local` or `not-local:no-devin-env` proceeds normally; any other `not-local:<reason>` applies `<plugin-root>/devin/INSTRUCTIONS.md` §Cloud Mode: emit the `--banner`, fan out sequentially with `Reviewed-Coverage: sequential-fallback` disclosure (never claim an independent review ran), `message_user` ack before any secrets read or production mutation, and run `precommit-guard.sh` before any `git commit` — hooks do not fire…
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jikig-ai/soleur/eval-harness@sha256:078bd101db2fda26

The line at the top of this page pins the label git:20261003.57e28a5, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tqkhwz6de62faaq4.svg)](https://markdownregistry.com/a/art_tqkhwz6de62faaq4)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 10 versions of this file, between Jun 29, 2026 and Oct 3, 2026, about one every 11 days.

versioncommittedcommitsizeaudit
git:20261003.57e28a5 latest2026-10-03 57e28a5 12,705 BA view · diff
git:20260924.a44cf8f2026-09-24 a44cf8f 12,180 BA view · diff
git:20260921.97686452026-09-21 9768645 11,456 BA view · diff
git:20260919.dd5c52f2026-09-19 dd5c52f 11,124 BA view · diff
git:20260916.6c1dbcb2026-09-16 6c1dbcb 10,917 BA view · diff
git:20260711.65d5c8b2026-07-11 65d5c8b 10,001 BA view · diff
git:20260710.5003c772026-07-10 5003c77 10,001 BA view · diff
git:20260630.0e410e62026-06-30 0e410e6 9,481 BA view · diff
git:20260630.fcc23052026-06-30 fcc2305 9,480 BA view · diff
git:20260629.98bf8642026-06-29 98bf864 8,700 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12705 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

GitHub

jikig-ai/soleur · 21 stars · license a license file GitHub does not identify · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tqkhwz6de62faaq4
GET https://markdownregistry.com/api/v1/resolve?ref=jikig-ai/soleur/eval-harness
GET https://markdownregistry.com/api/v1/blob/078bd101db2fda2600ead0c7dcd1d228a29e8f6a30ef8209a65460701635a3aa

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 jikig-ai/soleur

AGENTS.md AGENTS.md file
jikig-ai/soleur · AGENTS.md
git:20261014.76616e1 · audit A · 21 stars
CLAUDE.md CLAUDE.md file
jikig-ai/soleur · CLAUDE.md
git:20260928.fff36b6 · audit A · 21 stars
AGENTS.md@apps/web-platform AGENTS.md file
jikig-ai/soleur · apps/web-platform/AGENTS.md
git:20261101.075b188 · audit A · 21 stars
zzzprobe SKILL.md skill
jikig-ai/soleur · knowledge-base/project/specs/archive/20261013-051752-feat-one-shot-7450-git-root-anchor-untrusted/arm4-probe/skills/zzzprobe/SKILL.md · This skill should be used when the operator asks to run the loader-substitution probe.
git:20261013.ad1a087 · audit A · 21 stars
zzzprobe SKILL.md skill
jikig-ai/soleur · knowledge-base/project/specs/feat-one-shot-7450-git-root-anchor-untrusted/arm4-probe/skills/zzzprobe/SKILL.md · This skill should be used when the operator asks to run the loader-substitution probe.
git:20260813.449b8c3 · audit A · 21 stars
AGENTS.md@plugins/soleur AGENTS.md file
jikig-ai/soleur · plugins/soleur/AGENTS.md
git:20261105.0b08d38 · audit A · 21 stars
CLAUDE.md@plugins/soleur CLAUDE.md file
jikig-ai/soleur · plugins/soleur/CLAUDE.md
git:20260909.ae44051 · audit B · 21 stars
go SKILL.md skill
jikig-ai/soleur · plugins/soleur/codex/skills/go/SKILL.md · Route your request to the appropriate Soleur workflow or domain agent.
git:20260911.8be1ba1 · audit A · 21 stars
help SKILL.md skill
jikig-ai/soleur · plugins/soleur/codex/skills/help/SKILL.md · List Soleur commands, skills, and domain agents.
git:20260911.8be1ba1 · audit A · 21 stars
sync SKILL.md skill
jikig-ai/soleur · plugins/soleur/codex/skills/sync/SKILL.md · Populate your company knowledge base from the existing codebase.
git:20260911.8be1ba1 · audit A · 21 stars
go SKILL.md skill
jikig-ai/soleur · plugins/soleur/cursor/skills/go/SKILL.md · This skill is the unified entry point that classifies intent and routes to the right workflow skill
git:20261007.8bcbe03 · audit A · 21 stars
soleur-admin-ip-refresh SKILL.md skill
jikig-ai/soleur · plugins/soleur/cursor/skills/soleur-admin-ip-refresh/SKILL.md · This skill should be used to refresh the prod SSH allowlist (Doppler ADMIN_IPS) after operator IP rotation. Detects…
git:20261007.8bcbe03 · audit A · 21 stars

Every file in jikig-ai/soleur

Other files named eval-harness

eval-harness SKILL.md skill
affaan-m/ecc · .agents/skills/eval-harness/SKILL.md · Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles. Use when a…
git:20260918.c752aac · audit A · 299,696 stars
eval-harness SKILL.md skill
affaan-m/ecc · docs/es/skills/eval-harness/SKILL.md · Framework formal de evaluación para sesiones de Claude Code que implementa principios de desarrollo orientado a evals…
git:20260607.ac0f11c · audit A · 299,696 stars
eval-harness SKILL.md skill
a5c-ai/babysitter · library/methodologies/everything-claude-code/skills/eval-harness/SKILL.md · Evaluation harness for testing agent and skill quality through structured benchmarks, regression tests, and quality…
git:20260601.da7723a · audit A · 1,896 stars
eval-harness SKILL.md skill
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/eval-harness/SKILL.md · 正式评估框架,实现 eval-driven development (EDD) 原则。 用于定义 pass/fail 标准、测量 pass@k 指标、创建回归测试套件。
git:20260512.6523792 · audit A · 1,537 stars
eval-harness SKILL.md skill
miaodx/roboclaws · skills/eval-harness/SKILL.md · Select and run Roboclaws validation, product, eval-suite, and live-agent eval rows from a plan, diff, or explicit…
git:20260928.2b353eb · audit A · 6 stars

Browse by kind, by grade A, or by owner.