second-opinion SKILL.md skillA

second-opinion from arcasilesgroup/ai-engineering is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add arcasilesgroup/ai-engineering/second-opinion@git:20261106.9932b24

Pins git:20261106.9932b24 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
arcasilesgroup/ai-engineering
Path
skills/second-opinion/SKILL.md
Versions recorded
1
Latest version
git:20261106.9932b24, committed Nov 6, 2026
Size
9,861 bytes
Repository stars
65
License
Apache-2.0

Get an independent review of code you just wrote by spawning a fresh reviewer instance — a separate one-shot agent session with read-only tools that cannot see your reasoning. Use this immediately after finishing ANY implementation — a feature, a bugfix, a refactor, a migration, a schema change — before you tell the user the work is done. Also use whenever the user says "review this", "double-check that", "get a second opinion", "have another agent look at it", or asks whether an…

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

# Second opinion

Spawn an independent reviewer — a fresh model instance that cannot see your reasoning — to review the implementation you just finished, triage what it finds, and fix the real bugs.

## Why this catches things you cannot catch yourself

When you re-read code you just wrote, you check it against your intent. You remember what each line was *for*, so you read the intent into the code and skip right over the place where the code says something slightly different. That is not carelessness — it is unavoidable. You cannot un-know your own plan.

A fresh reviewer has no plan to un-know. It sees only the task and the code, so a gap between them shows up as a gap. That is the entire mechanism, and it is also why the one thing that ruins this technique is leaking your reasoning into the review packet.

## The rule that makes or breaks it

**Give the reviewer the spec and the code. Never give it your justifications.**

Concretely, keep all of these out of the packet:

- "I handled the empty case by …" — if the handling is real, the reviewer will see it in the code; if you have to point at it, that is exactly the claim worth testing
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add arcasilesgroup/ai-engineering/second-opinion@sha256:d6d6d601a43858ac

The line at the top of this page pins the label git:20261106.9932b24, 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_rntzs6d23pobegbe.svg)](https://markdownregistry.com/a/art_rntzs6d23pobegbe)

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

Versions

The registry has recorded 1 version of this file, committed on Nov 6, 2026.

versioncommittedcommitsizeaudit
git:20261106.9932b24 latest2026-11-06 9932b24 9,861 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 (9861 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

arcasilesgroup/ai-engineering · 65 stars · license Apache-2.0 · pushed 2026-11-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rntzs6d23pobegbe
GET https://markdownregistry.com/api/v1/resolve?ref=arcasilesgroup/ai-engineering/second-opinion
GET https://markdownregistry.com/api/v1/blob/d6d6d601a43858ac079a22ad59d462b3410be2f9607d4a5adf9f5ab9b7e44abf

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 arcasilesgroup/ai-engineering

AGENTS.md AGENTS.md file
arcasilesgroup/ai-engineering · AGENTS.md
git:20261004.3e3bd00 · audit A · 65 stars
a11y-audit SKILL.md skill
arcasilesgroup/ai-engineering · skills/a11y-audit/SKILL.md · Audit the UI for accessibility defects against WCAG 2.2 AA — semantic structure, keyboard operability, focus…
git:20261106.9932b24 · audit A · 65 stars
ai-adversarial-loop SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-adversarial-loop/SKILL.md · Coordinate a multi-round debate between two agents until the code is clean. adversarial-reviewer (the critic) assumes…
git:20261106.9932b24 · audit A · 65 stars
ai-agents-md SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-agents-md/SKILL.md · Creates, audits and maintains the AGENTS.md a repository owes its coding agents, following the agents.md convention…
git:20260929.4338d92 · audit A · 65 stars
ai-architect SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-architect/SKILL.md · Advises on project strategy, architecture, stacks, services, costs, comparables, prior art, or repo design before…
git:20261106.9932b24 · audit A · 65 stars
ai-audit-code SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-audit-code/SKILL.md · Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen…
git:20261004.3e3bd00 · audit A · 65 stars
ai-audit-design SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-audit-design/SKILL.md · Use when a web interface needs its visual defects found and fixed with measurements rather than opinions — misaligned…
git:20261106.9932b24 · audit B · 65 stars
ai-audit-docs SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-audit-docs/SKILL.md · Audits docs against repo state for dead links, false claims, stale versions, and nonexistent commands. Input: paths or…
git:20261106.9932b24 · audit A · 65 stars
ai-brainstorm SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-brainstorm/SKILL.md · Use when the user brings a fuzzy idea that must be pinned down before research or planning — "handshake", "get on the…
git:20260929.3986acb · audit A · 65 stars
ai-codegraph SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-codegraph/SKILL.md · Uses local CodeGraph MCP for symbol relationships, call chains, and blast radius. Trigger: "how does X work", "what…
git:20261106.9932b24 · audit A · 65 stars
ai-config-to-project SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-config-to-project/SKILL.md · Adapts a governed project's architecture rules, config, overrides, and AGENTS.md after ai-eng init. Manual only. Writes…
git:20260929.3986acb · audit B · 65 stars
ai-debug SKILL.md skill
arcasilesgroup/ai-engineering · skills/ai-debug/SKILL.md · Finds the root cause at file:line and writes a failing check before the fix; resolves merge and rebase conflicts by…
git:20261106.9932b24 · audit A · 65 stars

Every file in arcasilesgroup/ai-engineering

Other files named second-opinion

second-opinion SKILL.md skill
trailofbits/skills · plugins/second-opinion/skills/second-opinion/SKILL.md · Gets independent code reviews from Codex or Antigravity for uncommitted changes, branch diffs, and commits. Use when…
git:20260914.f44eeba · audit A · 8,043 stars
second-opinion SKILL.md skill
amirfish1/claude-command-center · plugin/skills/second-opinion/SKILL.md · Use when, before committing to a non-trivial approach, diagnosis, or answer, you want an independent check — it spawns…
git:20261009.a664025 · audit B · 217 stars
second-opinion SKILL.md skill
awrshift/agent-memory-kit · plugins/memory-kit/skills/second-opinion/SKILL.md · Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says…
git:20261022.af5bf98 · audit A · 34 stars
second-opinion SKILL.md skill
microsoft/amplifier-bundle-skills · skills/second-opinion/SKILL.md · Independent review of current work or a past session. USE WHEN a user wants a second opinion. DO NOT USE WHEN ordinary…
v0.4.0 · audit A · 12 stars
second-opinion SKILL.md skill
flurdy/agent-skills · skills/second-opinion/SKILL.md · Query an independent peer or a configurable local/OpenRouter review panel, with distinct quorum and evidence-backed…
v3.9.0 · audit A · 9 stars
second-opinion SKILL.md skill
photostructure/coding-skills · plugins/coding/skills/second-opinion/SKILL.md · Get second opinions on freshly written code from fresh Codex and Claude reviewers, one small batch at a time, then…
git:20261107.c82c884 · audit A · 5 stars

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