Prompt: Self-Evaluation Checklist
A finishing prompt that makes the model critique its own draft for clarity, evidence, tone, and structural weak points.
Use cases
Content & Writing, Development & Code, Operations & Workflow
Platforms
Claude, GPT, Gemini, Model-Agnostic
Jump to a section
Workspace-ready resource
Copy the raw material, then check the setup, output contract, and failure modes.
Review the draft against these questions:- Is the main point obvious?- What claims need evidence?- Where is the answer repetitive or vague?- Does the structure match the requested format?- What would a sceptical reader challenge? Return:1. Issues found2. Severity3. Proposed fixes4. Revised versionWorkspace translation
Turn this resource into an inspectable run.
Best next step
Run it once manually. If the same job appears twice, package it.
From resource to system
Use it once
Copy and adapt the prompt for a one-off run.
Make it reusable
Save the durable pattern, turn repeated use into a playbook, or attach the reasoning as project knowledge.
Decide after the run
Run it once manually. If the same job appears twice, package it.
Quality bar
Before using this, check the contract.
What input does this require?
What output should it produce?
Where can it fail?
What should a human review?
Recommended path
When to Use This
Use this after a first draft when you want a cleaner second pass without rewriting from zero.
It is useful for content, documentation, reports, and outreach.
Why It Works
Models are often better critics than first-pass writers if you point them at the right failure modes.
The severity field helps separate minor polish from structural issues.
How to Customise
Add domain-specific checks such as citation quality, legal risk, or code correctness.
Use it as the final stage in prompt chains or agent workflows.
Limitations
Self-evaluation is still self-evaluation. It can miss blind spots a human would catch.
The revision may drift if the model is asked to change too many things at once.
Model Notes
Claude tends to produce more candid critiques.
GPT works well when the severity scale is defined explicitly.
Related Resources
Browse PromptsFramework: Prompt Audit Checklist
A 15-point checklist for evaluating any prompt before putting it into production. Catches the most common prompt failures: vague instructions, missing constraints, absent error handling, and untested edge cases.
Knowledge / rubric seed
Operations & Workflow · Strategy & Planning
Prompt Chain: Blog Post from Brief
A three-step prompt chain that turns a rough content brief into a polished blog post. Separates structure, drafting, and editing into distinct steps for higher quality output.
Pattern / playbook seed
Content & Writing · Marketing & Growth
Skill: Technical Documentation Writer
A skill file that configures an LLM to write clear, structured technical documentation. Handles API docs, setup guides, README files, and process documentation with consistent formatting and appropriate detail depth.
Operator seed
Development & Code · Operations & Workflow
Related Guides
Prompt Testing: How to Know If Your Prompt Is Good
A practical guide to prompt evaluation that goes beyond vibes and looks at repeatability, failure cases, and revision discipline.
Why Your Few-Shot Examples Aren't Working
Few-shot prompting can be excellent. It can also quietly teach the model the wrong pattern. Here is where it usually goes wrong.
Need this operationalized?
Turn the pattern into a workspace system.
Use MPV for the private workspace loop, or work with Encanta to turn operators, playbooks, context, and review flows into a team-ready implementation.