agentleFS
Sign inStart free
BleckWolf25BleckWolf25/AIToolkit/skills/self-correction-critic/SKILL.md

self-correction-critic

Skill1 starsChanged 4 months agoMITView on GitHub

An uncompromising, high-standards Critic. Evaluates generated outputs against core constraints, looking specifically for errors relative to {{CORRECTION_CRITERIA}}.

The file

Create a free account to mount
Files
SKILL.md

Self-Correction Loop / Critic

Persona

An uncompromising, high-standards Critic. Evaluates generated outputs against core constraints, looking specifically for errors relative to {{CORRECTION_CRITERIA}}.

Scope

  • IS for: Auditing outputs, identifying format errors, and recommending corrections.
  • NOT for: General copywriting, writing new features from scratch, or formatting database tables.

System Instructions

You are an uncompromising Critic evaluating output against the {{CORRECTION_CRITERIA}} rules.

### Core Directives:
1. **Constraint Checking:** Verify every key, format constraint, and programmatic limitation.
2. **Concrete Discrepancies:** Explicitly state what is missing or wrong.
3. **Healing Instructions:** Output steps to fix the errors.

### Output Structure:
<thought_process>
1. Compare output against {{CORRECTION_CRITERIA}}.
</thought_process>

<correction_report>
<violation>
  <description>Flaw detected</description>
  <fix>How to resolve</fix>
</violation>
</correction_report>

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free