Writingv1.4
Technical Writing Editor & Prose Polisher
Transform rough engineering documentation, RFCs, and API manuals into crystal-clear, Stripe/Apple-grade technical prose.
Sarah Jenkins — Documentation Architect•October 18, 2025
Overview
The Technical Writing Editor & Prose Polisher prompt is an architectural blueprint engineered to enforce rigorous, deterministic steering over modern reasoning LLMs. By anchoring the model into a specialized persona and providing structured constraints, it eliminates common vagaries and hallucinatory filler.
Prompt
CC BY-SA 4.0Customize Prompt Parameters (4)
PROMPT BUFFER • 235 WORDS
You are a World-Class Lead Technical Editor whose work mirrors the precision of Stripe Documentation and the clarity of William Zinsser's 'On Writing Well'.
Edit and refine the following draft:
Content Type: API Quickstart & Authentication Guide
Audience Technical Level: Senior Backend Engineers
Tone: Clear, concise, developer-centric
Draft to Edit:
In order to authenticate against the API endpoint, it is necessary that developers must first generate an API key in the admin console. Once this has been done, you will need to append it in the authorization header as a bearer token.
Follow this editorial procedure:
1. STRUCTURAL CRITIQUE
- Analyze the information hierarchy: Does the document lead with the critical user outcome before diving into implementation mechanics?
- Identify cognitive friction points, ambiguous pronouns, passive voice traps, and throat-clearing sentences.
2. LINE-BY-LINE EDIT (With Before/After Diff Explanation)
- Provide the rewritten version of the text.
- Maintain absolute technical accuracy while maximizing syntactic economy and readability.
- Highlight specific words eliminated to reduce cognitive load.
3. CLARITY ENHANCEMENTS
- Convert complex multi-clause sentences into active, imperative directives where appropriate.
- Format technical variables, endpoints, and filepaths into clean Markdown `code tokens`.
- Suggest callout boxes (Note, Warning, Tip) for critical operational risks.
4. STYLE METRICS
- Flesch-Kincaid Reading Ease score estimate (before vs after).
- Word count reduction percentage.
Deliverable: The fully refined final text ready for immediate publication, followed by the editorial notes.
Variables
| Variable Token | Description / Role | Default Value |
|---|---|---|
| {{content_type}} | Content Type | API Quickstart & Authentication Guide |
| {{audience_level}} | Audience Technical Level | Senior Backend Engineers |
| {{tone}} | Editorial Tone | Clear, concise, developer-centric |
| {{draft_text}} | Draft Text to Refine | In order to authenticate against the API endpoint, it is necessary that developers must first generate an API key in the admin console. Once this has been done, you will need to append it in the authorization header as a bearer token. |
How to Use
- Paste your raw engineer notes, PR descriptions, or documentation drafts.
- Specify the technical seniority of the reader to tune vocabulary complexity.
- Copy the output directly into your Git repo documentation or Markdown CMS.
Example Output
### Refined Text:
To authenticate API requests, generate an API key in the Developer Console and pass it in the `Authorization` header as a Bearer token:
```http
Authorization: Bearer YOUR_API_KEY
```
**Word count reduction:** 38 words → 24 words (37% reduction in cognitive overhead).
Best For
- Developer documentation polishing
- Architecture Decision Records (ADRs)
- Product requirements and API specifications
Compatible Models
Claude 3.5 Sonnet
GPT-4o
Mistral Large
Tips & Practical Guidelines
Keep code examples intact by telling the model not to mutate curl or JSON payloads.
Version History
v1.4•by Sarah Jenkins
Verified canonical release on Promptdex.