cross-model-review SKILL.md skillA

cross-model-review from kalyvask/winning-writing is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kalyvask/winning-writing/cross-model-review@git:20260829.ba6993d

Pins git:20260829.ba6993d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
kalyvask/winning-writing
Path
skills/cross-model-review/SKILL.md
Versions recorded
3
Latest version
git:20260829.ba6993d, committed Aug 29, 2026
First version recorded
May 6, 2026
Size
5,669 bytes
Repository stars
17
License
MIT

Independent second-model gate for cold emails before send. Must run on a DIFFERENT model than the one that drafted (e.g., draft on Opus, review on Sonnet — or vice versa). Acts as a binary pass/fail gate, not a regrade or rewrite. Names the specific failure mode from a 14-mode catalog (strategy / personalization / posture). Always surfaces the most likely counter-question the recipient will reply with. Triggers on "second pass," "cross-model review," "independent review," "review before send…

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

# Cross-model review

Source: `points/named-failure-modes.md`, `points/banned-jargon.md`, `points/pre-send-checklist.md`, `points/cold-email-rules.md`, `points/ai-writing-rules.md`. Read those first.

## Why this exists

The model that drafted the email rationalizes its own choices. It picked the personalization, so the angle feels genuine. It used the word, so the word doesn't read as jargon. It made the claim, so the claim feels supported.

A second model — different weights, no investment in the draft — sees what the first model rationalized away. That's the whole point. If this skill runs on the same model that drafted, it adds nothing.

## The contract

You are NOT here to make the email better. You are here to decide whether it ships.

Two verdicts only:

- `PASS` — ship it
- `FAIL` — block, with the specific named failure modes listed

Borderline → fail. Cost of a block is one rewrite cycle. Cost of a templated email is the recipient's read of the sender forever.

## Invocation rule

The orchestrator (`coach.html`, `cold-email-coach`, or the user) routes to a different model than the drafter. This skill assumes routing already happened.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kalyvask/winning-writing/cross-model-review@sha256:2c1af0e33a01b488

The line at the top of this page pins the label git:20260829.ba6993d, 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_jb7pksjiyst3uoan.svg)](https://markdownregistry.com/a/art_jb7pksjiyst3uoan)

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

Versions

The registry has recorded 3 versions of this file, between May 6, 2026 and Aug 29, 2026, about one every 58 days.

versioncommittedcommitsizeaudit
git:20260829.ba6993d latest2026-08-29 ba6993d 5,669 BA view · diff
git:20260506.b46a5552026-05-06 b46a555 5,207 BA view · diff
git:20260506.c3433dd2026-05-06 c3433dd 4,519 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 (5669 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

kalyvask/winning-writing · 17 stars · license MIT · pushed 2026-09-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jb7pksjiyst3uoan
GET https://markdownregistry.com/api/v1/resolve?ref=kalyvask/winning-writing/cross-model-review
GET https://markdownregistry.com/api/v1/blob/2c1af0e33a01b488a8ec5c9c68e70eb8459aefbf103caead99206574f7af20d1

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 kalyvask/winning-writing

winning-writing SKILL.md skill
kalyvask/winning-writing · catalog/SKILL.md · Mode-aware writing critic. Distilled from Rachel Konrad's Stanford GSB "Winning Writing" course (spring 2026), the 10…
git:20260528.67d18b2 · audit A · 17 stars
bluf-rewriter SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/bluf-rewriter/SKILL.md · Reorganizes a memo, email, status update, or report so the bottom line is up front. Implements Kramon's BLUF (Bottom…
git:20260610.8b6b2b8 · audit A · 17 stars
compression SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/compression/SKILL.md · Cuts a draft to a target word count without losing substance. Two modes behind one skill. target-count hits a specific…
git:20260610.8b6b2b8 · audit A · 17 stars
feedback-rephraser SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/feedback-rephraser/SKILL.md · Rewrites blunt downward or peer feedback as "what I like plus what I would like," focused on the work rather than the…
git:20260522.8896ed6 · audit A · 17 stars
fun-angle SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/fun-angle/SKILL.md · Finds the unexpected, dry, or self-deprecating angle that makes an email memorable. Turns "professional and polite"…
git:20260522.8896ed6 · audit A · 17 stars
headline-as-claim SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/headline-as-claim/SKILL.md · Rewrites section titles, slide titles, op-ed headlines, email subject lines, and chapter headings from category labels…
git:20260522.8896ed6 · audit A · 17 stars
irrelevant-detail-killer SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/irrelevant-detail-killer/SKILL.md · Cuts cinematic details that don't serve the main point. The opposite move from vividness. Vividness adds sensory…
git:20260522.8896ed6 · audit A · 17 stars
pick-a-lane SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/pick-a-lane/SKILL.md · Diagnoses drafts that tell three half-stories instead of one full story, and rewrites them around the single strongest…
git:20260522.8896ed6 · audit A · 17 stars
style-tells SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/style-tells/SKILL.md · Scrubs the three surface tells that make prose feel AI-generated, padded, or jargon-heavy. Three targets behind one…
git:20260522.8896ed6 · audit A · 17 stars
tell-them-something-new SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/tell-them-something-new/SKILL.md · Cuts opening sentences that recap what the recipient already knows about themselves, their company, or their own work…
git:20260522.8896ed6 · audit A · 17 stars
vividness SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/vividness/SKILL.md · Pushes a draft from abstract toward concrete at two scales. Noun-level (replaces "dog" with "German shepherd,"…
git:20260522.8896ed6 · audit A · 17 stars
warmth-and-competence SKILL.md skill
kalyvask/winning-writing · side-panel-coach/rules/skills/warmth-and-competence/SKILL.md · Audits a draft on Susan Fiske's two-axis model of social judgment — warmth (do I like and trust this person?) and…
git:20260522.8896ed6 · audit A · 17 stars

Every file in kalyvask/winning-writing

Other files named cross-model-review

cross-model-review SKILL.md skill
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/cross-model-review/SKILL.md · 跨模型第二意见技能,融合 gstack 的 cross-model second opinion 能力。 当检测到高风险改动时,可选触发不同模型提供独立审查意见, 作为 multi-perspective-review 的可选叠加层。
git:20260512.6523792 · audit A · 1,537 stars

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