contrastive-refinement SKILL.md skillA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

contrastive-refinement from moonlight-lupin/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add moonlight-lupin/agent-skills/contrastive-refinement@v0.2.0

Pins v0.2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
moonlight-lupin/agent-skills
Path
plugins/skill-governance/skills/contrastive-refinement/SKILL.md
Versions recorded
1
Latest version
v0.2.0, committed Oct 30, 2026
Size
15,896 bytes
Repository stars
114
License
MIT

Use when a skill or harness edit needs evidence before it lands — probe candidates on the same task, compose from contrasts, keep lessons with evidence.

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

# Contrastive Skill Refinement

Refine a skill or harness edit with measured behavior, not judgment alone.
Before an edit lands, run candidate versions of the skill on the SAME probe
task, compare deliverables blind, and compose the surviving edit. Every
recorded lesson carries an evidence line naming the observed contrast. This
skill only changes skill definitions; for application code changes use
`build-review-loop`.

Pattern source: Harness² (google-research/harness2, Apache-2.0,
arXiv:2610.14224) — the Propose–Probe–Compose loop and the evidence-required
lesson format, ported to Hermes skill dirs. See
`references/harness2-adaptation.md` for what was ported and what was not.

## When to Use

- An edit to a skill promises better output but nobody has measured it
- Two candidate edits both look right and you must pick one
- A skill failed a real task and you want a proven fix, not a guess
- A lesson about a skill needs to be written down and should carry evidence

**Don't use for:** typo and frontmatter fixes (no behavior change), live code
repos (`build-review-loop`), first drafts of brand-new skills (nothing to
contrast yet).
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add moonlight-lupin/agent-skills/contrastive-refinement@sha256:ead9d02dd29d682c

The line at the top of this page pins the label v0.2.0, 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_ey2a5yq5sdfrxznp.svg)](https://markdownregistry.com/a/art_ey2a5yq5sdfrxznp)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 30, 2026.

versioncommittedcommitsizeaudit
v0.2.0 latest2026-10-30 8bbdc1b 15,896 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 (15896 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

moonlight-lupin/agent-skills · 114 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ey2a5yq5sdfrxznp
GET https://markdownregistry.com/api/v1/resolve?ref=moonlight-lupin/agent-skills/contrastive-refinement
GET https://markdownregistry.com/api/v1/blob/ead9d02dd29d682ca0490196ada118047cd619730ef11116560b06e1c132885f

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 moonlight-lupin/agent-skills

claude-plugin-converter SKILL.md skill
moonlight-lupin/agent-skills · agent-ops/claude-plugin-converter/SKILL.md · Use when converting Claude Code plugins into self-contained Hermes plugins — discovery analysis then full conversion.
v1.0.0 · audit A · 114 stars
hermes-onboarding SKILL.md skill
moonlight-lupin/agent-skills · agent-ops/hermes-onboarding/SKILL.md · Use when onboarding a new customer — configure gateway, dashboard, memory, services for production.
v1.3.0 · audit B · 114 stars
input-token-overheads SKILL.md skill
moonlight-lupin/agent-skills · agent-ops/input-token-overheads/SKILL.md · Use when the context window fills too fast, per-turn input token cost is too high, or the aggregate input token bill…
v1.9.0 · audit A · 114 stars
log-analyzer SKILL.md skill
moonlight-lupin/agent-skills · agent-ops/log-analyzer/SKILL.md · Use when parsing agent log files to identify error patterns, rate limit hits, timeout clusters, tool failures, and…
v1.1.0 · audit A · 114 stars
operator-brain SKILL.md skill
moonlight-lupin/agent-skills · agent-ops/operator-brain/SKILL.md · Use when communicating, deciding, or reporting as a senior operator — 8 behavioral modules from Anthropic's Fable…
v1.1.0 · audit A · 114 stars
clips-studio SKILL.md skill
moonlight-lupin/agent-skills · creative/clips-studio/SKILL.md · Use when the user wants to "make a video/clip", "generate a video from text", "animate this image/photo", "create a…
v1.2.2 · audit A · 114 stars
image-studio SKILL.md skill
moonlight-lupin/agent-skills · creative/image-studio/SKILL.md · Use when the user wants image generation or editing through the local fal.ai three-stage studio workflow — brainstorm a…
v1.3.2 · audit A · 114 stars
pexels-stock-photos SKILL.md skill
moonlight-lupin/agent-skills · creative/pexels-stock-photos/SKILL.md · Use when the user wants a REAL photo — 'find a photo of X', 'search for pictures of Y', 'stock image of Z', 'I need a…
v1.0.0 · audit A · 114 stars
disk-cleanup SKILL.md skill
moonlight-lupin/agent-skills · devops/disk-cleanup/SKILL.md · Use when df says disk is above 80% full or the user wants to reclaim storage space on a VM.
v1.3.1 · audit B · 114 stars
model-compare SKILL.md skill
moonlight-lupin/agent-skills · mlops/model-compare/SKILL.md · Blind side-by-side multi-model comparison. Send one prompt to 2-4 models simultaneously, present responses anonymously…
v1.2.0 · audit A · 114 stars
contrastive-refinement SKILL.md skill
moonlight-lupin/agent-skills · plugins/contrastive-advisor/skills/contrastive-refinement/SKILL.md · Use when a skill or harness edit needs evidence before it lands — probe candidates on the same task, compose from…
v0.2.0 · audit A · 114 stars
grill SKILL.md skill
moonlight-lupin/agent-skills · plugins/dev-pipeline/skills/grill/SKILL.md · Use when a plan is fuzzy and needs hardening before a spec — decision-tree grilling in frontier rounds, every open…
v1.1.0 · audit A · 114 stars

Every file in moonlight-lupin/agent-skills

Other files named contrastive-refinement

contrastive-refinement SKILL.md skill
moonlight-lupin/agent-skills · plugins/contrastive-advisor/skills/contrastive-refinement/SKILL.md · Use when a skill or harness edit needs evidence before it lands — probe candidates on the same task, compose from…
v0.2.0 · audit A · 114 stars

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