Critical Perspective

Reframes one-sided conversations into open questions that surface hidden assumptions and gaps.

Tested · Works

Test report

Verdict
Tested · Works
Score
9.6/10
Tested
Jul 13, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 18, 2026 · 71da233

Given the same 'go 100% paid ads, organic takes too long' pitch, the plain baseline gave a pros/cons list and a recommendation; running the skill's assumption-surfacing technique instead produced a single open question exposing the unexamined 'speed vs. compounding' framing and the bottom-of-funnel-only reach gap that 100%-paid leaves uncovered — a genuinely different, more exploratory response, exactly as the description promises.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 9/10
  • Docs & honesty 5/5

What Critical Perspective does

Critical Perspective turns Claude into a curious interlocutor that questions assumptions, proposes alternative viewpoints, and names unexplored gaps instead of just answering directly. It triggers when a discussion is one-dimensional, converging too fast, or needs its blind spots checked, and explicitly stands down when the user just wants a straight answer or emotional support. Optional InfraNodus MCP tools (knowledge-graph, gap, and research-question generation) layer on structural discourse analysis but are not required for the core prompt technique to work.

How to install Critical Perspective

git clone https://github.com/infranodus/skills
cd skills
mkdir -p ~/.claude/skills
cp -r skill-critical-perspective ~/.claude/skills/critical-perspective

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Critical Perspective

  • /critical-perspective Reframes one-sided conversations into open questions that surface hidden assumptions and gaps.

It also activates on plain-language prompts like these:

  • Challenge the assumptions in my go-to-market plan
  • What blind spots am I missing in this strategy?
  • Play devil's advocate on my product decision

Frequently asked questions

Is the Critical Perspective skill free?
Yes. The skill itself is free from infranodus/skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Critical Perspective work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Given the same 'go 100% paid ads, organic takes too long' pitch, the plain baseline gave a pros/cons list and a recommendation; running the skill's assumption-surfacing technique instead produced a single open question exposing the unexamined 'speed vs. compounding' framing and the bottom-of-funnel-only reach gap that 100%-paid leaves uncovered — a genuinely different, more exploratory response, exactly as the description promises.
What is the Critical Perspective SkillProof Score?
9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Critical Perspective?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Critical Perspective with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.