AI Skills Catalog
AI Workers

Peer

Work through decisions with an evidence-led sounding board that weighs alternatives, challenges weak reasoning and updates its view when facts change.
SKILL SCORE79How it is scored
VerifiedFreeCC-BY-4.0

Works with

Packaged from the source skill for Claude, Codex and 4 more.

About this skill

Peer gives an assistant a consistent way to evaluate a proposal before responding. It weighs the available options, their costs and risks, and the information that could change the decision, then gives a concise judgment with reasons.

Use this skill when

  • You want a second opinion on a plan, design choice or proposed next step.
  • A conversation keeps drifting into agreement without testing the assumptions.
  • You need to distinguish useful new evidence from pressure to reverse an answer.

What it can do

  • Compare realistic alternatives, including keeping the current approach.
  • Identify the one missing fact most likely to change the recommendation.
  • Explain why a position stays the same or which new fact warrants changing it.
  • Suggest a small check when the evidence cannot settle a disagreement.

Typical workflows

  1. Provide the decision, available facts, constraints and current proposal.
  2. Have the assistant weigh alternatives and return a recommendation or the key unanswered question.
  3. Introduce new evidence and ask it to explain whether the conclusion changes.
  4. For a consequential decision, use a fresh agent where available and compare its independent assessment.

Inputs and output

Inputs are a question or proposal and the facts needed to assess it. The output is a proportionate written judgment, its assumptions and a practical next check when uncertainty remains. The skill is instruction-only and does not need a separate service.

Limitations

These instructions do not guarantee factual accuracy or eliminate agreement bias. The author reports short, artificial evaluations in Claude Code; those results do not establish the same behavior in every model or host. Independent review requires a host that supports a separate agent; the source provides a self-check fallback.

What is inside the skill

Section headings from the original SKILL.md (about 731 words of instructions). Read the full text in the source repository before installing.

  1. Decide what you think, then answer
  2. When they push back
  3. Ideas as they arrive
  4. What reads as simulated, and must not appear
  5. Big decisions

Bundled files

  • LICENSE
  • README.md

Example prompts

  • Compare keeping our current hosting plan with moving to a cheaper provider, using these costs, migration effort and rollback constraints.
  • Review this product launch proposal and identify the single assumption that could change your recommendation.
  • I disagree with your earlier database choice because our workload now requires offline writes. Explain whether that new fact changes the decision.

How to install Peer

Claude Packaged
  1. Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files.
  2. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
  3. For Claude apps, upload the ZIP in the Skills section of the capabilities settings.
  4. Start a new session and describe the task in your own words. Claude picks the skill when the request matches its description.
More about skills for Claude
Codex Packaged
  1. Download the Codex package. The ZIP contains one folder named after the skill, with SKILL.md and bundled resources.
  2. Unpack the complete folder into .agents/skills/ inside your repository, or into ~/.agents/skills/ for personal use. Preserve its relative reference-file paths.
  3. Start a new Codex session and invoke the skill by name or with $skill-name, or describe a matching task.
  4. AGENTS.md is separate project guidance. The ZIP does not generate or modify that file.
More about skills for Codex
GPT Packaged
  1. Download the GPT package from the skill page.
  2. Create or edit a custom GPT (or a ChatGPT project) and paste the contents of SKILL.md into the instructions field.
  3. Upload the bundled reference files as knowledge so the GPT can consult them.
  4. Test with one of the example prompts from the skill page and adjust the instructions if your use case differs.
More about skills for GPT
Gemini Packaged
  1. Download the Gemini package from the skill page.
  2. For a project, unpack the complete folder into .gemini/skills/ or .agents/skills/. For personal use, use ~/.gemini/skills/ or ~/.agents/skills/.
  3. Run /skills reload in Gemini CLI, then /skills list to check discovery. There is no need to paste the skill into GEMINI.md.
  4. Test a matching task and verify the referenced tools and files are available.
More about skills for Gemini
Cursor Packaged
  1. Download the Cursor package from the skill page.
  2. Unpack the complete skill folder into .cursor/skills/ or .agents/skills/ in your project. For personal local use, ~/.cursor/skills/ and ~/.agents/skills/ are also supported.
  3. Start a new Cursor session. Type / in Agent chat and select the skill name, or describe a matching task.
  4. Commit the skill folder and resources for team use. Personal local skills are not automatically available to remote agents or automation runs.
More about skills for Cursor
OpenCode Packaged
  1. Download the OpenCode package from the skill page.
  2. Unpack the complete folder into .opencode/skills/ in your project, or ~/.config/opencode/skills/ for personal use. OpenCode also supports .agents/skills/ and .claude/skills/ compatibility locations.
  3. Keep supporting files at their original relative paths. AGENTS.md is separate project-wide guidance and is not generated by this ZIP.
  4. Start OpenCode in the project and test a matching task with the model and permissions you use.
More about skills for OpenCode

Permissions & security

Low risk

Inspect the source, license and declared permissions before use. Read the scripts before running them. Review method

Read project files
Write generated skill files

Peer FAQ

What does the Peer skill do?

Work through decisions with an evidence-led sounding board that weighs alternatives, challenges weak reasoning and updates its view when facts change.

Which AI agents can use Peer?

Packages for Claude, Codex and 4 more are built from the same source instructions.

How do I install Peer in Claude?

Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.

Who made Peer and what is the license?

Peer is published by Andrew Kear under the CC-BY-4.0 license. The source is https://github.com/andykear/Peer/tree/main. The catalog keeps the original attribution.

What permissions does Peer need?

Declared permissions: read project files, write generated skill files. Risk level: low. Check the scripts in the source before running them.

Peer Skill for Claude & Codex | AI Skills Catalog