peer-review SKILL.md skillA

peer-review from sno-ai/sno-station-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add sno-ai/sno-station-skills/peer-review@git:20261013.fdbd8e1

Pins git:20261013.fdbd8e1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
sno-ai/sno-station-skills
Path
skills/J-peer-review-and-audit/peer-review/skill/SKILL.md
Versions recorded
3
Latest version
git:20261013.fdbd8e1, committed Oct 13, 2026
First version recorded
Oct 1, 2026
Size
33,452 bytes
Repository stars
481
License
Apache-2.0

Adversarial review and fix loop for code, specs, plans, and migration manifests.

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

# Peer Review

Classify → gather context → **run bundled adversarial-review script** → root cause → fix/report → repeat until clean.

"Owner" below means whoever owns the work, usually the user.

Prerequisites: Linux, bash, python3, jq, GNU `date`, `timeout`, `sha1sum`, `pgrep` and GNU `xargs`, Sno's quota pick and answer-provider commands, plus an installed, logged-in reviewer CLI on another vendor. Without python3 the findings ledger and receipts do not work.

The bundled script's adversarial-review pass is the authoritative reviewer. It runs in a fresh, separate headless session that has none of the caller's conversation. Only an answer from a different model vendor counts: the script walks Sno's ordered reviewer candidates and discards failed, empty, unknown-vendor or same-vendor answers. There is no same-vendor fallback. The active agent gathers context, investigates root causes, and applies fixes — it never overrides, filters, softens, or rewords the nested reviewer's findings. Every authoritative finding reaches the user; tag suspected false positives `[Possible FP]` with your reasoning instead of dropping them. Findings the active agent adds on its own are labeled…
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add sno-ai/sno-station-skills/peer-review@sha256:abe81ecd0bdc8a2a

The line at the top of this page pins the label git:20261013.fdbd8e1, 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_hsuaz723sb6zzpiv.svg)](https://markdownregistry.com/a/art_hsuaz723sb6zzpiv)

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

Versions

The registry has recorded 3 versions of this file, between Oct 1, 2026 and Oct 13, 2026, about one every 6 days.

versioncommittedcommitsizeaudit
git:20261013.fdbd8e1 latest2026-10-13 fdbd8e1 33,452 BA view · diff
git:20261007.9784a782026-10-07 9784a78 31,849 BA view · diff
git:20261001.8e39faf2026-10-01 8e39faf 31,347 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 (33452 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

sno-ai/sno-station-skills · 481 stars · license Apache-2.0 · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hsuaz723sb6zzpiv
GET https://markdownregistry.com/api/v1/resolve?ref=sno-ai/sno-station-skills/peer-review
GET https://markdownregistry.com/api/v1/blob/abe81ecd0bdc8a2a5b8223b21f518de941c2c976aa1ec02367ebb5f01d212116

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 sno-ai/sno-station-skills

AGENTS.md AGENTS.md file
sno-ai/sno-station-skills · AGENTS.md
git:20261008.302514f · audit A · 481 stars
CLAUDE.md CLAUDE.md file
sno-ai/sno-station-skills · CLAUDE.md
git:20261008.302514f · audit B · 481 stars
agentic-time-estimate SKILL.md skill
sno-ai/sno-station-skills · skills/H-reporting-and-visibility/agentic-time-estimate/skill/SKILL.md · Answer how long agent work will take, how much longer active work needs, or what clock time applies. Estimate full…
git:20261007.9784a78 · audit A · 481 stars
away-brief SKILL.md skill
sno-ai/sno-station-skills · skills/H-reporting-and-visibility/away-brief/skill/SKILL.md · Give the owner one page when they come back from sleep, a meeting or a long run: what got done, what is stuck, what…
git:20261007.9784a78 · audit A · 481 stars
catch-report SKILL.md skill
sno-ai/sno-station-skills · skills/H-reporting-and-visibility/catch-report/skill/SKILL.md · Report how many problems the two brains found: mutual review (the other model checks the work, from the peer-review…
git:20261013.fdbd8e1 · audit A · 481 stars
agentic-walkthrough SKILL.md skill
sno-ai/sno-station-skills · skills/J-peer-review-and-audit/agentic-walkthrough/skill/SKILL.md · Prove that a reported run caused its intended real effect. Walk the executor path from entry to effect, capture one…
git:20261001.8e39faf · audit A · 481 stars
e2e-environment-preflight SKILL.md skill
sno-ai/sno-station-skills · skills/J-peer-review-and-audit/e2e/skills/e2e-environment-preflight/SKILL.md · Check external services, hosts, browser sessions, model endpoints, and agents before an end-to-end run. MANUAL-ONLY…
git:20261001.8e39faf · audit A · 481 stars
e2e-red-triage SKILL.md skill
sno-ai/sno-station-skills · skills/J-peer-review-and-audit/e2e/skills/e2e-red-triage/SKILL.md · Classify one unexpected end-to-end test failure as a product defect or an environment fault needing a new preflight…
git:20261001.8e39faf · audit A · 481 stars
first-principles-review SKILL.md skill
sno-ai/sno-station-skills · skills/J-peer-review-and-audit/first-principles-review/skill/SKILL.md · MANUAL-ONLY: challenge a product idea, design, PRD, or architecture from first principles. Use only when the user names…
git:20261001.8e39faf · audit A · 481 stars
less-is-more SKILL.md skill
sno-ai/sno-station-skills · skills/J-peer-review-and-audit/less-is-more/skill/SKILL.md · Write the least code that works, and cut what an AI agent over-built. Use on any coding task: write, fix, refactor, or…
git:20261001.8e39faf · audit A · 481 stars
owner-intent-audit SKILL.md skill
sno-ai/sno-station-skills · skills/J-peer-review-and-audit/owner-intent-audit/skill/SKILL.md · Check agent-produced plans, tests, or code against the owner's actual intent. Find missing meaning, unrequested work…
git:20261001.8e39faf · audit A · 481 stars
medic SKILL.md skill
sno-ai/sno-station-skills · skills/M-build-and-rollout/medic/skill/SKILL.md · Check that this machine's agent team can work and say what is wrong in plain lines: tools installed, core skills…
git:20261007.9784a78 · audit A · 481 stars

Every file in sno-ai/sno-station-skills

Other files named peer-review

peer-review SKILL.md skill
k-dense-ai/scientific-agent-skills · skills/peer-review/SKILL.md · Prepares evidence-bounded, constructive peer-review drafts and structured manuscript assessments. Supports authorized…
v2.4 · audit B · 53,159 stars
peer-review SKILL.md skill
tobihagemann/turbo · codex/skills/peer-review/SKILL.md · Run an independent peer review via Claude. Use when the user asks to "peer review", "peer review my code", "peer review…
git:20260904.804c1ff · audit A · 414 stars
peer-review SKILL.md skill
tobihagemann/turbo · claude/skills/peer-review/SKILL.md · Run an independent peer review via Codex. Use when the user asks to "peer review", "peer review my code", "peer review…
git:20260904.804c1ff · audit A · 414 stars
peer-review SKILL.md skill
aperivue/medsci-skills · skills/peer-review/SKILL.md · Use when reviewing someone else's manuscript for a journal, such as after a review invitation or for a revised R1/R2…
git:20261005.b7f0eaf · audit B · 346 stars
peer-review SKILL.md skill
oleafly/oleafly · src-tauri/resources/skills/peer-review/SKILL.md · Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments. Use for authorized…
v2.2 · audit B · 258 stars
peer-review SKILL.md skill
yha9806/academic-writing-toolkit · archive/skills/peer-review/SKILL.md · Review another author's manuscript, paper, thesis chapter, proposal, or preprint as an external reviewer. Use when…
git:20260816.d958232 · audit A · 49 stars
peer-review SKILL.md skill
a-lottes/aspark · skills/peer-review/SKILL.md · Start the Review phase of the SPARK loop: the Reviewer audits the diff produced by /increment — plan conformance…
git:20260917.3f27eda · audit A · 24 stars

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