Second Opinion logo

Second Opinion

Organization
vanillagreencom
second-opinion

Load for a cross-model review, challenge, audit, or quick consult.

Overview

Publishervanillagreencom
Repositorykendex
Skill namesecond-opinion
Stars
80
Forks
31
Bundled files
29
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 29 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by vanillagreencom on GitHub. Read the source before you install it.

Installation

Install the Second Opinion AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vanillagreencom/kendex.git /tmp/kendex
mkdir -p .claude/skills
cp -r /tmp/kendex/skills/second-opinion .claude/skills/second-opinion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Second Opinion in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Second Opinion on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Second Opinion is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Second Opinion

Cross-model second opinion via external AI CLI. Every mode walks the SECOND_OPINION_MODELS roster in priority order and takes the first target that is available and runs a different model: Codex from a Claude Code session, Claude from a Codex session; when nothing eligible remains the run refuses and says why. Full contract: second-opinion --help.

bash
.agents/skills/second-opinion/scripts/second-opinion <mode> [options]

Workflows

CommandWorkflowOutput
review [scope]workflows/review.mdReview finding JSON
challenge [description]workflows/challenge.mdStructured critique (text)
audit [path]workflows/audit.mdReview finding JSON
quick [question]workflows/quick.mdText response
detect(built-in)Target name(s) a review would run

Execution Rules

  • Execute all workflow sections in order. The workflow decides what to skip via "Skip if" conditions. Never skip based on your own scope assessment.
  • <output_format> tags are literal templates: fill [PLACEHOLDERS], omit empty lines, add nothing else, do not paraphrase.
  • Pass --target when the user explicitly requests a specific model/CLI (e.g., "use Claude", "ask Codex"). Otherwise omit it. The script selects from the roster and the current session's model. A forced target that runs this session's model is refused; report the refusal, do not work around it.
  • Do not pass --timeout unless the user explicitly asks for a different value for this specific call. The script reads the default from project config.
  • Always pass --cwd with the absolute project root path. Never use --cwd ..
  • Pass --foreground when the call can outlast the harness foreground cap. This detaches the run and prints its artifact, deadline, and wait command.
  • Execute the exact printed wait command and follow its exit handling in second-opinion --help until terminal.
  • For quick mode, you can pass the question inline: .agents/skills/second-opinion/scripts/second-opinion quick "your question here" --cwd /path --foreground.

Session identity

Cross-model is enforced in every mode: a run with no eligible target exits 1 naming every candidate and its reason, writing nothing and invoking nothing. In a multi-model front end (Pi, OpenCode, Cursor) or an undetected harness, export SECOND_OPINION_CURRENT_MODEL in that session's own environment (none when there is no session model), never in a project settings file. Identity resolution, normalization, and the refusal rules: second-opinion --help.

Multi-lane review

SECOND_OPINION_COUNT of 2 or more makes review run up to that many distinct eligible models in parallel on one pinned scope and write a single union artifact. Lane resolution, merge rules, artifact placement and permissions, scratch durability, and the failure taxonomy: references/multi-lane.md.

Configuration

Set non-sensitive defaults in kendex.settings.toml under [env]; .env.local wins over it, and a .env file is never read. SECOND_OPINION_FOREGROUND_CAP is session-only; a project-file foreground-cap declaration is refused, and shipped workflows pass --foreground directly. This skill marks no key # required, so an install writes nothing into kendex.settings.toml; assign a key there only to change a default the scripts already read (SECOND_OPINION_TARGET has none). Keys, defaults, and the built-in claude/codex commands: second-opinion --help.

Error Handling

On script failure, stderr carries a JSON error object ({"error": "description", "target": "codex"}) or a plain Error: line for pre-flight configuration errors; exit codes, preserved-response paths, and the output-clearing/ownership rules are in second-opinion --help. Report the stated reason. An ineligible-target refusal is fixed by installing the CLI or adjusting SECOND_OPINION_<NAME>_CMD, SECOND_OPINION_MODELS, or SECOND_OPINION_CURRENT_MODEL, never by forcing the same model. For a timeout, suggest a larger --timeout or a narrower --range.

If the script fails during the orch review-pr or submit-pr (local pre-PR review) workflows, continue. External review is advisory.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Second Opinion AI skill do?

Load for a cross-model review, challenge, audit, or quick consult.

Why use Second Opinion on TypingMind?

Because you install it once and use it with any model. Second Opinion is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Second Opinion in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vanillagreencom/kendex/tree/main/skills/second-opinion. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Second Opinion?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Second Opinion?

As many as you like. As long as a model supports skills, you can use Second Opinion with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Second Opinion AI skill free?

Yes. It is published on GitHub by vanillagreencom under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
multica-ai logo

Karpathy Guidelines

multica-ai
OrganizationPopular

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define…

21.6K
213.7K
Instructions
View
microsoft logo

Create Agent

microsoft
OrganizationPopular

Create a custom agent (.agent.md) for a specific job.

42.7K
192.7K
Instructions
View
microsoft logo

Create Hook

microsoft
OrganizationPopular

Create a hook (.json) to enforce policy or automate agent lifecycle events.

42.7K
192.7K
Instructions
View
microsoft logo

Generate Run Commands

microsoft
OrganizationPopular

Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

42.7K
192.7K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇