- Home
- Skills
- Technical Documentation
- rubric rewrite
rubric rewrite
Rewrite weak or generic drafts using explicit quality rubrics and exemplar analysis to ensure factual accuracy.
Free
Works with the AI Agents you already use
rubric rewrite
Example session with this skill installed
Rewrite this draft for a DevOps engineer audience. Draft: 'Our tool helps you manage servers better.' Context: It is a CLI tool for automating AWS EC2 instance tagging.
- Read your context and instructions
- Compiled the rubric rewrite
I have revised the draft to focus on technical utility for DevOps engineers, using a rubric centered on technical specificity and task-oriented benefits.
Rubric Rewrite Results
| Section | Content |
|---|---|
| Revised Draft | Automate AWS EC2 resource organization by applying consistent tags via the CLI. Ensure your infrastructure-as-code deployments maintain metadata compliance without manual console entry. |
| Material Changes | Swapped vague "manage servers" for specific "EC2 instance tagging." Focused on CLI and IaC workflows instead of generic "better" management. |
| Short Rubric Check | Technical Specificity: High. Mentions AWS, EC2, and CLI. Target Audience Alignment: High. Addresses the pain point of manual tagging and metadata compliance. |
| Unresolved Questions | Does the tool support bulk tagging across multiple regions? Does it integrate directly with Terraform or CloudFormation? |
Next steps
- Confirm if the tool supports multi-region tagging to resolve the factual question.
- Provide an example of a specific CLI command to include as a concrete exemplar.
- Review the "metadata compliance" claim to ensure it aligns with your specific product value.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop publishing generic, hollow copy that fails to connect with your target audience. This skill forces clarity by establishing objective quality criteria before a single word is changed. It targets developers and writers who need to turn technical drafts into purposeful communication without losing factual accuracy.
What it does
- Rubric Generation creates small, observable quality criteria like concrete benefits and logical ordering.
- Exemplar Analysis extracts structural principles from provided examples without imitating a specific voice.
- Fact Preservation ensures core technical details and attributions remain unchanged during the rewrite.
- Conflict Resolution identifies and explains tradeoffs when different quality criteria contradict each other.
- Gap Identification flags unsupported claims or unresolved factual questions rather than inventing details.
How it works
- Define the artifact's audience, purpose, and static facts that must not be altered.
- Select or define a specific rubric based on the desired outcome and explain any trade-offs.
- Analyze provided exemplars to extract structural techniques and principles.
- Execute the revision by applying the rubric to the draft while preserving original meaning.
Frameworks & tools
This skill is platform-agnostic and works within any LLM environment. It follows a logic-first workflow inspired by the Three-Prompt Pattern to ensure structural improvements over surface-level polishing.
Why this beats prompting it yourself
Generic "rewrite this" prompts often hallucinate benefits or adopt a "marketing fluff" tone that alienates technical users. This skill anchors the revision to a specific rubric and prevents the AI from inventing claims or ignoring constraints.
Use cases
- Transform generic "innovative solution" taglines into concrete feature benefits.
- Align technical documentation with the specific knowledge level of an end-user.
- Refine internal project proposals to meet specific organizational reporting standards.
- Clean up draft API descriptions to ensure they follow consistent naming and structural principles.
Known limitations
This skill is not for simple typo fixes or grammar checks. It does not have authority to publish content or approve new claims on behalf of the user.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Technical Documentation.
Not for simple typo fixes. Only for drafting; cannot publish or approve claims. Requires user-provided context or exemplars for best results.
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
1 use
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 24 days ago
- Free with an Agensi account
Permissions
No special permissions declared or detected