SkillsAdd

hunvreus/skill-issue · Archived

second-opinion

Ask another local AI CLI for feedback on a proposal, architecture, feature plan, refactor, review, or technical decision, then compare the feedback and produce a revised assessment.

First seen Jun 8, 2026

Installation

$ npx skills add hunvreus/skill-issue --skill second-opinion
View on skills.sh ↗ GitHub repository ↗

Summary

  • Ask another local AI CLI for feedback on a proposal, architecture, feature plan, refactor, review, or technical decision, then compare the feedback and produce a revised assessment.
  • Use when the user wants another model's opinion or asks to check a plan with Gemini, Claude, Codex, Cursor, or another installed AI tool.

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

refactor Same source · more installs
hunvreus/skill-issue

Review and refactor code within a specified scope. Use when the user asks to clean up, simplify…

15 installs
test Same source · more installs
hunvreus/skill-issue

Add, update, or repair tests for behavior, regressions, and test-first development. Use when th…

14 installs
document Same source · more installs
hunvreus/skill-issue

Create or update project documentation, README sections, architecture docs, API docs, examples,…

13 installs
release Same source · more installs
hunvreus/skill-issue

Prepare, validate, document, tag, or publish a software release. Use when the user asks to cut …

12 installs

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

second-opinion Similar name
trailofbits/skills

Runs external LLM code reviews (OpenAI Codex or Google Antigravity CLI) on uncommitted changes,…

4.4K installs
contrarian-and-opinion Similar name
social-media-skills/skills

The point-of-view content type — articulate, sharpen, and argue a genuinely-held contrarian sta…

188 installs

Also in this package

Other skills from hunvreus/skill-issue · top by installs.

npx skills add hunvreus/skill-issue
refactor 15 test 14 document 13 release 12 review 11 deploy 11 overhaul 11 handoff 11 debug 11 prototype 10

Browse all from hunvreus/skill-issue

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Declared
Codex Declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Declared
Cline Not declared
OpenCode Declared

Repository health

Stars 36
License LICENSE
Default branch main
Open issues 0
Status Archived

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents claude-code cursor codex gemini opencode

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,911 B
  • docs SUMMARY.md 341 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 10 installs

SKILL.md

Second Opinion

Input

  • A proposal, architecture, feature plan, refactor plan, implementation approach, review finding, or technical decision to sanity-check.
  • Use explicit input first; otherwise infer the proposal and target AI from context.
  • Safest default: detect available local AI CLIs and ask which one to use.

Workflow

  1. Clarify target and input. Identify the proposal to review and the AI CLI to ask. If either is missing, infer from context or ask one focused question.
  2. Detect available CLIs. Check likely commands with command -v, such as claude, gemini, codex, cursor, opencode, and aider. Do not assume a CLI exists.
  3. Verify invocation. Use the selected CLI's help output before running it. Prefer non-interactive prompt modes and avoid commands that open editors, mutate files, install packages, or start long-lived sessions.
  4. Write the proposal. Create a temporary directory with mktemp -d and write the proposal, relevant constraints, and explicit questions to a file such as proposal.md.
  5. Ask the other AI. Pass the proposal file content to the selected CLI. Ask for critique, missed risks, alternatives, and concrete changes to the proposal.
  6. Capture feedback. Save the raw response in the same temporary directory. If the CLI fails, report the command, failure mode, and closest safe fallback.
  7. Compare judgments. Separate useful objections from weak or irrelevant feedback. Do not accept the other AI's answer just because it came from another model.
  8. Revise if warranted. Produce a final assessment, noting what changed, what did not, and why.

Output

  • Target AI and CLI used
  • Proposal file path and feedback file path
  • Other AI's strongest points
  • Points rejected or deprioritized
  • Final assessment
  • Revised proposal when useful

Examples

  • second-opinion with gemini on this architecture plan
  • ask Claude for a second opinion on the refactor
  • get another model to critique this feature proposal
  • compare our deploy plan with Codex

Guardrails

  • Do not send secrets, credentials, private keys, tokens, customer data, or unnecessary proprietary context to another CLI.
  • Do not run a paid, networked, or external AI CLI unless the user requested that tool or approved it.
  • Do not let the other AI mutate the repository; use it for feedback only.
  • Keep the prompt focused. Send the proposal and constraints, not the entire repo, unless explicitly requested.
  • Treat second opinions as advisory evidence, not authority.