profile-optimizer
Skill21 starsChanged 4 months agoMITView on GitHub
Audits and rewrites LinkedIn/X profiles element by element — a headline built on who-you-help + outcome + proof, an About section with a three-line hook and scannable body, a banner brief, featured-section picks, and a keyword pass for search — delivering a before/after for every element. Use when the user says "roast my LinkedIn profile", "my profile gets views but no DMs", "rewrite my headline", or "optimise my X bio before this launch".
7 other projects use a version of this.
Adopted by
Most recently taken up by
- juanASP/mercurytheir own version, first seen Nov 1, 2026
- mthines/agent-skillstheir own version, first seen Oct 30, 2026
- charlie947/social-media-skillstheir own version, first seen Sep 15, 2026
- moses607/socialforgetheir own version, first seen Jul 15, 2026
- wltn7810-dotcom/claude-skilltheir own version, first seen Jul 13, 2026
- mahiunfiltered/claude-code-skillstheir own version, first seen Jul 8, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- charlie947/social-media-skills★ 4.4ksame name
- mthines/agent-skills★ 20same name
- FlavioZanoni/mercury★ 8same name
- moses607/socialforge★ 3same name
- mahiunfiltered/claude-code-skills★ 1same name
- juanASP/mercury★ 0same name
- wltn7810-dotcom/claude-skill★ 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 repository63 other files it gives its agents.
- account-intelligenceSkill
- account-researchSkill
- ad-creativeSkill
- agent-evaluationSkill
- agent-reliabilitySkill
- ai-adoption-leadSkill
- ai-data-stewardSkill
- ai-seoSkill
- ai-workflow-architectSkill
- appsec-reviewSkill
- audit-supportSkill
- brand-guidelinesSkill
- call-prepSkill
- cash-flow-snapshotSkill
- chief-of-staffSkill
- claude-memSkill
- close-managementSkill
- compliance-checkSkill
- context7Skill
- copywritingSkill
- croSkill
- cto-advisorSkill
- customer-researchSkill
- draft-outreachSkill
- financial-statementsSkill
- frontend-designSkill
- growth-engineeringSkill
- growth-experimentsSkill
- growth-strategySkill
- hook-generatorSkill
- invoice-chaseSkill
- journal-entrySkill
- lead-magnetsSkill
- legal-risk-assessmentSkill
- lifecycle-growthSkill
- margin-analyzerSkill
- mcp-builderSkill
- objection-handlerSkill
- pipeline-reviewSkill
- plan-payrollSkill
- post-writerSkill
- proposal-builderSkill
- reconciliationSkill
- reels-scriptingSkill
- revenue-operationsSkill
- review-contractSkill
- run-campaignSkill
- signature-requestSkill
- skill-creatorSkill
- skill-vettingSkill
- superpowersSkill
- tasteSkill
- tax-prepSkill
- token-accountantSkill
- transitionsSkill
- triage-ndaSkill
- ui-ux-pro-maxSkill
- variance-analysisSkill
- vendor-checkSkill
- voice-builderSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Before an outbound or content push, when the profile has to convert the click.
- Distinctive: line 32
Write the banner brief: one message, a text overlay of seven words or fewer, where the proof element (logo, metric, artifact) sits, and …
“Common” is measured: kept by at least 6 in 10 of the 7 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
Profile Optimizer — Profile Doctor
"Optimise your profile"
When to use
- A profile gets impressions but no follows, DMs, or inbound leads.
- "Roast my LinkedIn profile." / "Why does nobody message me?"
- "Rewrite my headline — I'm repositioning from freelancer to agency."
- Before an outbound or content push, when the profile has to convert the click.
- New role, new niche — and the profile still sells the old you.
Workflow
- Collect the raw material: current headline, About, banner description, featured items, pinned posts — plus who the profile must attract and the one action they should take (DM, follow, book a call).
- Diagnose. Score each element 1–5 against its actual job: headline (search + hook), banner (positioning billboard), About (hook, then proof), featured (path to the action). Name the single biggest leak in one sentence.
- Rewrite the headline on the formula who you help + outcome + proof — e.g. "I help B2B SaaS founders turn content into pipeline — $12M sourced in 2025." Deliver three options: safe, sharp, spicy.
- Rebuild the About: the first three lines are a hook that survives the fold, then scannable proof blocks (results, method, credibility), then exactly one CTA. First person, short paragraphs, zero third-person bio-speak.
- Write the banner brief: one message, a text overlay of seven words or fewer, where the proof element (logo, metric, artifact) sits, and colour guidance so the profile photo still pops against it.
- Pick three featured items that ladder to the goal — lead magnet, best-performing post, booking link — and rewrite each title as a promise, not a label.
- Keyword pass: weave the 3–5 terms the target audience actually searches into the headline, About, and experience titles. Natural placement only — no stuffing.
- Deliver a before/after for every element, plus a do-this-first list that fits in 20 minutes.
Output format
## Profile Audit: <name> — <platform>
Goal: <who it must attract → the one action they should take>
Biggest leak: <one sentence>
### Headline
BEFORE: <current>
AFTER (safe): <rewrite>
AFTER (sharp): <rewrite>
AFTER (spicy): <rewrite>
### About
BEFORE: <first three lines + one-line verdict>
AFTER: <full rewritten About, paste-ready>
### Banner brief
Message: <...> | Overlay: "<7 words max>" | Proof: <...> | Colour: <...>
### Featured (in this order)
1. <item> — <why it earns the slot>
2. <item> — <why>
3. <item> — <why>
### Keywords woven in
<term> → <headline | About | experience title>
### Do this first (20 minutes)
1. <step>
2. <step>
3. <step>Quality bar
- Headline names who you help and the outcome — never a bare job title or "Passionate about...".
- The first three About lines work standalone above the fold.
- Every element ships a before AND an after — no advice without the rewrite.
- Claims carry proof (numbers, names, artifacts), not adjectives.
- Keywords sit in the headline and About without reading as stuffed.
- The whole audit is implementable in one sitting via the do-this-first list.
Example
Invocation: "My LinkedIn gets 500 views a week but zero DMs. I'm a fractional CFO for e-commerce brands."
Produces: a full audit naming the leak (headline reads "Finance Executive" — a title, not an offer), three headline rewrites (sharp: "Fractional CFO for 7-figure e-com brands — I find the 6% of revenue you're leaking"), a rebuilt About that opens with a client result, a banner brief ("Your margin is hiding in your ops"), three featured picks ending in a booking link, a keyword pass for "fractional CFO e-commerce", and a 20-minute implementation order.
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.

