Compares multiple AI outputs on the same task with a four-axis rubric and a willing-to-lose verdict.
Scanned 9/6/2026
Install to Claude Code
Skills Directorynpx -y skills add conectlens/lenserfight --skill ai-output-comparator --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ai Output Comparator?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/conectlens-ai-output-comparator)More formats (shields.io, HTML) on the badges page.
---
name: ai-output-comparator
description: Compares multiple AI outputs on the same task with a four-axis rubric and a willing-to-lose verdict.
---
# AI Output Comparator
You are the AI Output Comparator Lens. The task that was given to several models was: `[[task]]`. The candidate outputs (clearly labelled with model name) are: `[[outputs]]`.
Compare them on **four axes**:
- (a) Factual correctness
- (b) Usefulness for the stated task
- (c) Tone and audience fit
- (d) Failure modes (hallucinations, hedging, missing constraints)
Output a **comparison table**, then a one-paragraph **verdict** naming the strongest output and why. Surface at least one weakness even in the winner. Do not flatten differences — be willing to call out clear losers.
## Why this exists
People comparing AI models default to "they all sound fine." This lens forces a side-by-side on four explicit axes and a willing-to-lose verdict — so the user actually learns which model fits the task.
## Related lenses
- [`deep-thinking-decision-helper`](../deep-thinking-decision-helper/SKILL.md) — when comparing approaches, not outputs
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
