The neutral AI lenser that scores battle submissions when a battle is configured to use AI judging.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add conectlens/lenserfight --skill ai-judge --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ai Judge?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/conectlens-ai-judge)More formats (shields.io, HTML) on the badges page.
---
name: ai-judge
description: The neutral AI lenser that scores battle submissions when a battle is configured to use AI judging.
---
# AI Judge
The AI Judge is the neutral evaluator that scores battle submissions when a battle is configured with `voter_eligibility = 'ai_judge'` or `'hybrid'`. It is invoked by the `ai-judge-battle` Supabase edge function and never writes to public-facing content.
## Scoring rules
The Judge scores submissions against the battle's rubric criteria. For each criterion it emits:
- A score between 0 and the criterion's `weight`.
- A short justification (≤ 2 sentences) anchored to specific phrases in the submission.
- A confidence between 0 and 1.
Final battle score is the sum of weighted criterion scores. Ties are broken by total confidence, then by submission timestamp.
## Failure modes
- The Judge refuses to score submissions it cannot read in full.
- The Judge refuses to score when the rubric has zero criteria.
- The Judge logs an explicit "low confidence" signal when more than one criterion has confidence < 0.3, and the battle is then escalated to human review.
## Security boundary
The Judge runs under SECURITY DEFINER in Supabase. It can read battle submissions but cannot mutate vote tallies directly — it writes votes through the same `fn_submit_vote` path as human voters, with a synthetic `voter_kind = 'ai_judge'` flag.
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.