linkedin-profile
Skill53 starsChanged 5 days agoMITView on GitHub
Audits a LinkedIn profile section by section with a scoring table, then rewrites the headline, about, experience and featured sections. Use when asked to review, audit, optimise or rewrite a LinkedIn profile.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- ourostack/ouroboros-skillstheir own version, first seen Nov 8, 2026
- matteotitta/claude-marketing-linkedintheir own version, first seen Oct 25, 2026
- rapha-red/linkedin-plugintheir own version, first seen Oct 13, 2026
- poorvith-mp/skills-personaltheir own version, first seen Aug 19, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- ourostack/ouroboros-skills★ 2same name
- poorvith-mp/skills-personal★ 1same name
- darkweb19/skills★ 0same name
- matteotitta/claude-marketing-linkedin★ 0same name
- rapha-red/linkedin-plugin★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- aeo-strategySkill
- battlecardsSkill
- case-studySkill
- company-contextSkill
- competitor-researchSkill
- icp-researchSkill
- positioningSkill
- product-launchSkill
- tov-guidelinesSkill
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 9 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 48
If inputs are missing: Ask for LinkedIn URL and ICP description at minimum.
- Distinctive: line 86
Remove irrelevant skills (e.g.
- Distinctive: line 87
Keep the top 3 pinned skills directly aligned to the ONE offer (the one thing you want to be hired for).
- Very specific: line 108
Never invent client metrics, results, or proof points: Only use data provided or mark as [PLACEHOLDER: need real metric]
- Distinctive: line 109
Don't fabricate recommendations or testimonials: If none exist, note the gap and provide the request template
- Distinctive: line 110
No invented company descriptions: Use scraped data or ask for clarification
- Distinctive: line 111
Mark assumptions clearly: Use "Example:" prefix for illustrative scenarios
- Distinctive: line 112
Verify proof points are real: Ask user to confirm before including specific numbers in banner/about
- Very specific: line 129
Search for LinkedIn profile scraper: search-actors with query "LinkedIn profile scraper"
- Very specific: line 131
Run actor: call-actor with the LinkedIn profile URL as input
- Distinctive: line 136
If scraping fails or is unavailable:
- Distinctive: line 137
Ask user to copy-paste each profile section manually
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
LinkedIn Profile Optimization
Audit a client's LinkedIn profile and generate optimized copy for every section — headline, about, banner, experience, featured, recommendations. Combines Apify scraping for structured profile data with user-provided screenshots for visual assessment, then applies proven profile optimization frameworks.
Why this matters: LinkedIn's algorithm reads your entire profile as text context to decide content distribution. A misaligned profile suppresses reach regardless of content quality. This skill ensures profile-content alignment before any content program begins.
Source: Nick Broekema (Content Design) — profile optimization methodology.
Claude Code Triggers
Invoke this skill when user says:
- "Optimize [client name]'s LinkedIn profile"
- "LinkedIn profile audit for [person]"
- "Rewrite [person]'s LinkedIn headline/about/bio"
- "Profile optimization for [client]"
- "Help [name] improve their LinkedIn profile"
- "[Client] needs a better LinkedIn presence"
Do NOT invoke when the user wants to write a LinkedIn post, comments, an infographic or a carousel.
Inputs
Required
| Input | Description | Source |
| LinkedIn profile | URL or full name + company | User provides |
| ICP description | Who is this profile trying to attract? | User provides |
Optional (improve quality)
| Input | How It Helps |
| TOV guidelines | Voice patterns to match in copy generation |
| Company context | Positioning, value props, proof points to reference |
| ICP profile | Detailed pain points and buyer language |
| Screenshots | Visual assessment of banner and profile picture |
| Current positioning | Messaging anchors and differentiators |
| Proof points | Specific metrics, results, client names for banner/about |
If inputs are missing: Ask for LinkedIn URL and ICP description at minimum. Request screenshots for banner/profile pic assessment.
Audit scoring table (8 sections)
This table is the load-bearing decision surface for the audit phase. Every audit fills it in.
| Section | Max Score | Key Criteria |
| Profile picture | /10 | Color (not b/w), smile, eye contact, zoom, branded background, contrast |
| Banner | /15 | Branded whitespace, clear category, proof points, ICP resonance |
| Headline | /15 | Formula fit, ICP clarity, desire/outcome, buyer language |
| About | /20 | PAIS structure, hook strength, CTA, specificity, proof |
| Featured | /10 | Links (not posts), CTA quality, friction level (3 max) |
| Experience | /15 | Current role depth, story, ideal client described, results |
| Recommendations | /10 | Problem-solution-outcome structure, relevance, recency |
| Bio-link | /5 | Presence, CTA coverage, number of links |
| TOTAL | /100 |
Status flags: ✓ Good (>70%) | ⚠ Needs work (40-70%) | ✗ Critical (<40%)
Process
3-phase flow: Profile Data Gathering → Profile Audit (using the 8-section scoring table above) → Optimized Copy Generation. Full step-by-step in the premium reference.
Endorsement Strategy
Skill endorsements signal ICP relevance to LinkedIn's search algorithm and 360brew's semantic map. Include this as a quick-win recommendation in all profile audits.
Approach:
- Endorse 10–15 relevant contacts proactively. Most reciprocate within 1-2 weeks.
- Focus on contacts who are ICP-adjacent (peers, past colleagues, complementary service providers).
- Prioritise skills that match ICP search terms: GTM, B2B SaaS, positioning, go-to-market, product marketing, content strategy, pipeline generation.
- Remove irrelevant skills (e.g. "Microsoft Excel", "Photoshop") that dilute semantic topic signal.
- Keep the top 3 pinned skills directly aligned to the ONE offer (the one thing you want to be hired for).
Why it matters: LinkedIn's member embedding system weighs skill endorsements as signals of expertise in specific topic clusters. Endorsements from relevant contacts reinforce your semantic profile faster than self-selected skills alone.
Profile clarity tenets
Voice-locked rules — these stay in body. Source: Nick Broekema / Content Design, March 2026.
- Headline = one sentence — Who you help + what they get + how fast. Not a laundry list of capabilities.
- Banner = single static message — Not a carousel of rotating promises. One clear line.
- About section: mobile readability — Shorter lines, breathing room, dynamics. No big blocks of text on mobile.
- About section: less is more — Keep ICP language but cut without losing meaning. Wordy = weaker.
- Profile-recommendation alignment — Does the profile reflect what clients consistently say? If all recs say "fast, high quality," the profile should lead with speed + quality.
- ICP specificity — Does the profile name the actual ICP role + company stage? Don't be everything to everyone.
Anti-Hallucination Guardrails
- Never invent client metrics, results, or proof points. Only use data provided or mark as
[PLACEHOLDER: need real metric] - Don't fabricate recommendations or testimonials. If none exist, note the gap and provide the request template
- No invented company descriptions. Use scraped data or ask for clarification
- Mark assumptions clearly. Use "Example:" prefix for illustrative scenarios
- Verify proof points are real. Ask user to confirm before including specific numbers in banner/about
MCP Data Integration
Level: 0 — Context (heavy data gathering)
Pulls fresh
| Source | What to pull | Tool | When |
| Apify | LinkedIn profile data (headline, about, experience, skills, recommendations) | search-actors → fetch-actor-details → call-actor | Always |
| Firecrawl | Company website (for messaging alignment) | firecrawl_scrape | If no company notes are provided |
Apify workflow
- Search for LinkedIn profile scraper:
search-actorswith query "LinkedIn profile scraper" - Get actor details:
fetch-actor-detailsfor the selected actor - Run actor:
call-actorwith the LinkedIn profile URL as input - Get results:
get-actor-outputfor structured profile data
Fallback (no Apify/scraping)
If scraping fails or is unavailable:
- Ask user to copy-paste each profile section manually
- Request screenshots for visual elements
- Proceed with manual data — all frameworks still apply
Quality
Pre-delivery checklist covers audit quality (verbatim evidence, score sums correct), copy quality (formula adherence, PAIS completeness, proof points real), voice quality (matches the person's tone of voice), and the Profile Clarity Tenets restated for review. Worked example + anti-examples in the premium reference.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

