- Home
- Skills
- Business & Operations
- self evaluating meta prompt template
Works with the AI Agents you already use
self evaluating meta prompt template
An iterative meta-prompting tool that generates, critiques, and refines high-stakes professional reports.
$19
self evaluating meta prompt template
Example session with this skill installed
I need a Monitoring and Evaluation (M&E) framework for a clean water initiative in a rural district. The project lasts 2 years.
- Read your context and instructions
- Compiled the self evaluating meta
I have generated an initial M&E framework, evaluated it against five quality criteria, and revised the draft to address gaps in data collection methodology and risk mitigation.
Revised M&E Framework: Clean Water Initiative
1. Logic Model
- Input: $500,000 funding, technical staff, 20 drilling rigs.
- Activities: Geophysical surveying, borehole drilling, community water committee training.
- Outputs: 15 functional solar-powered boreholes, 30 trained maintenance technicians.
- Outcomes: 80% reduction in water-borne diseases within the district.
2. Indicator Matrix
| Indicator | Definition | Frequency | Source |
|---|---|---|---|
| Water Access Rate | % of households within 500m of source | Annual | Household Survey |
| Technical Uptime | % of time boreholes are functional | Monthly | Maintenance Logs |
| Pathogen Count | CFU/100ml in community taps | Quarterly | Lab Reports |
3. Self-Evaluation & Revisions
Quality Criteria & Scores:
- Technical Feasibility: 5/5
- Data Verifiability: 3/5
- Local Context Integration: 4/5
- Risk Management: 3/5
- Strategic Alignment: 5/5
Weaknesses Identified:
- The initial draft lacked specific data sources for technical uptime.
- Risk mitigation for seasonal groundwater fluctuations was too vague.
Key Changes Made:
- Integrated specific maintenance log requirements into the Indicator Matrix.
- Added a dedicated section for "Environmental Contingency" to address drought risks.
Next steps
- Review the Indicator Matrix to ensure local staff have the tools for lab reporting.
- Confirm the geophysical survey timeline with the technical team.
Connects securely to your tools. The creator never sees your data.
About this skill
High-stakes deliverables like business proposals and M&E frameworks often suffer from hidden logical gaps and inconsistent quality. This skill forces a self-correction loop into the generation process to ensure the final output meets professional standards.
What it does
- Multi-step generation produces a comprehensive draft for complex business or technical documents.
- Criterion definition establishes five specific quality benchmarks tailored to the output type.
- Quantitative scoring assigns a 1-5 value to each criterion to identify performance gaps.
- Weakness identification isolates the two most critical areas requiring improvement.
- Iterative revision rewrites the initial draft to address the identified flaws.
- Impact reporting explains exactly how the final version was improved during the revision process.
How it works
- Provide the specific context and the type of document you need (e.g., a Monitoring and Evaluation framework).
- The agent generates the initial draft based on your requirements.
- The agent performs a self-critique by defining success metrics and scoring its own work.
- A revised final version is produced that targets the weaknesses found during evaluation.
Frameworks & tools
This skill is framework-agnostic and works for any structured professional documentation including M&E (Monitoring and Evaluation), RFPs, and strategic reports.
Why this beats prompting it yourself
Standard prompts usually result in a "one-and-done" output that requires manual editing to fix logical inconsistencies. This skill automates the critique-and-revise workflow, ensuring the model identifies its own hallucinations or surface-level analysis before you ever see the final text.
Use cases
- Drafting Monitoring and Evaluation frameworks for non-profit programs.
- Creating competitive business proposals for high-value contracts.
- Building structured strategic reports that require internal consistency.
- Developing complex project briefs where accuracy is non-negotiable.
Known limitations
The skill requires the user to provide clear context and output type to be effective. It is designed for structured documents rather than creative or informal writing.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Business & Operations.
Requires explicit context and output type to function. Works best for structured professional documents rather than creative writing.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 7 days ago
- Accounts
Google Drive
Notion
Airtablen8n
- Software
- Required (to use any skill at all):Claude CodeorCursororGitHub Copilot
Python 3.xPowerShell
- Optional
- , and only for specific skills (not a purchase requirement):
A host app that supports the Agent Skills format. That's it. copying the skills/ folder is the entire install. only to act on design-unified-google-drive-notion-workspace-two-domain-structure or google-workspace-automation-local-cloud-integration-architecture. only to act on…