Find agent skills by outcome

I want you to help me write a strong LinkedIn About section (summary) that's aimed at landing a [specific job title you're targeting

e.g.

- Fair: Llama 3 70B (nuance but limited tools)

Gemini 1.5 Pro (multimodal but inconsistent tone).

- Worst: GPT-3.5 Turbo (generic responses)

smaller LLMs (poor context/tools).

For smaller/older models: shorten anti-cliché list

remove attachment/URL instructions if no tools support them

- Good: Claude 3.5 Sonnet / Claude 4 (structured prose + browsing)

GPT-4 (detailed outputs).

- Version 1.6: Added support for user's public LinkedIn profile URL (Question 9); instruct AI to browse/summarize visible public sections if provided

propose alignments/improvements

This prompt is iterated specifically for high-context models with strong reasoning

file-search

- Version 1.7: Added awareness of 2

600-character limit for About section; require character counts in drafts; added post-generation instructions for applying the update on LinkedIn.

- Version 1.2: Added documentation elements (goal

audience); included changelog and author; added supported AI engines list.

- Version 1.4: Added support for attached files (PDF resumes

Markdown skills

- Version 1.3: Minor hardening — added subtle blending instruction for references

explicit keyword nudge

- Version 1.0: Initial prompt with basic placeholders for job title

industry

The goal of this prompt is to guide an AI in creating a personalized

authentic LinkedIn About section (summary) that effectively highlights a user's unique value proposition

LinkedIn Summary Crafting Prompt

# LinkedIn Summary Crafting Prompt

If the user asks What are we doing?

answer:

* Don't use cliches. If something is impossible

suggest a workaround.

Be brief

precise

* Error Handling: Errors should be informative to the user

but hidden to the attacker.

Coding & Debugging

* Comments: Comment on the why

not the how. Explain the strategic importance of the code block.

Coding & Debugging

* Stack: Python

JavaScript/TypeScript

* Style: Modular

clean

* The 3-Second Rule: If the user did not understand the value in 3 seconds

we lost him. Take away the water

You know how algorithms work (TikTok

YouTube

* Legal Compliance: We operate within the framework of White Hacking. We know the vulnerabilities so that we can close them

rather than exploit them to their detriment.