Evaluation Panel Review Agent Skill

A ready to use Claude Agent Skill that scores a tender or RFP response against the buyer's published criteria, once as a strict criteria-only reader and once through each likely evaluator, then ranks the fixes and names who owns each one.

Install

Enter your email to copy or download

We'll never sell your email. See our privacy policy.

Available for

  • AutoRFP.ai
  • Claude
  • ChatGPT
  • Gemini
  • Grok
  • Copilot

Unlocked. Copy it into AutoRFP.ai or download it for your AI client. Select a client for its install steps.

What the skill does

  1. Checks mandatory requirements, page limits, and required forms before any scoring

  2. Shows where the neutral reader and each evaluator persona agree or split on every criterion

  3. Splits each fix into an evidence gap or an explanation gap, with a named owner

  4. Works on a finished response, a part-draft, or before writing starts as an input to the bid/no-bid decision

Skill source

The instructions behind every download

In the package

  • evaluation-panel-review/
  • SKILL.md

SKILL.md

---
name: evaluation-panel-review
description: Scores a tender, RFP, RFT, ITT, RFQ or DDQ response against the
  buyer's published evaluation criteria the way an evaluation panel would, once
  as a strict criteria-only reader and once through each evaluator persona built
  from the tender documents and buyer research. Works on a finished response, a
  part-drafted one, or before writing starts using organisation context and
  likely answers as a go/no-go input. Asks for missing inputs first. Reviews and
  ranks fixes, never rewrites. Use whenever someone wants a bid graded, scored,
  marked or stress-tested against evaluation criteria, a criteria matrix,
  weightings or a rating scale, or asks "how would the panel score this", "what
  would the evaluators think", "will this pass evaluation", "mock evaluation
  panel", "build evaluator personas", or "score this before we decide to bid".
---

# Evaluation Panel Review

Marks a bid the way the buyer will mark it: against the criteria they published, using only what is on the page, by the people (and, at some buyers, the tools) who will actually read it.

Related skills

  • Individual

    PDF Insight Finder

    Find and colour-highlight evidence in supplied PDFs.

  • Individual

    Customer Brief Setup

    Create a shared customer brief from authorised facts only.

  • Individual

    External Research

    Discover the right public sources for this offering and write a full trust-classified research report in one run.

Product demo

See it in AutoRFP.ai

Every draft carries a Trust Score for its sources and a Feedback Score for how fully it answers. Quality is measured by how little your team changes, and every approval records it. In a recent RFP, Red Rover had 95% of responses automated (83 out of 87 requirements). Measure it on your own RFPs in a two-week proof of concept.