Critique a generated answer against the question and supplied evidence by calling the frozen Executor Model. Use for answer quality checks after generation.
Scanned 9/1/2026
Install to Claude Code
Skills Directorynpx -y skills add DocAILab/Agentic-RAG-Skill --skill component-critic --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Component Critic?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/docailab-component-critic)More formats (shields.io, HTML) on the badges page.
---
name: component-critic
description: Critique a generated answer against the question and supplied evidence by calling the frozen Executor Model. Use for answer quality checks after generation.
---
# Critic Component
Provide the `critic` capability for an Agentic RAG slot.
## Interface
Input `CritiqueRequest`:
- `query`: original question
- `documents`: selected evidence documents
- `answer`: generated answer
- optional `max_tokens`
Output `CritiqueResult`:
- `approved`: whether the answer is supported and responsive
- `score`: quality score between 0 and 1
- `feedback`: concise overall critique
- `issues`: list of concrete problems, possibly empty
## Execution
Run `scripts/component.py:run(inputs, context)`. The runtime must provide the frozen `context.call_model(...)`. This Component critiques an answer only; it does not retrieve documents, generate a replacement answer, or select another Skill.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!
