← ClaudeAtlas

li-profilelisted

Score a LinkedIn profile out of 100 against a 13-part rubric built for a builder with a founder-style persona, then rewrite the parts that lose the most points: headline, About, Featured, Experience, Projects, banner. Use when the user says "optimize my profile", "score my LinkedIn", "rewrite my headline", "fix my About", "make my profile founder-ready", or pastes their profile.
reportedguy/li-stack · ★ 0 · Data & Documents · score 68
Install: claude install-skill reportedguy/li-stack
# li-profile A profile isn't a resume. A resume answers "what have you done". A profile answers "should I message this person", in about four seconds, from the headline and the first two lines of About. For a builder, the reader is usually a **founder or another builder** who just saw a post or a comment. They're looking for proof you ship and think clearly about products. ## Input Ask the user to paste: headline, About, experience entries, projects, and whether they have a banner, Featured items and recommendations. A screenshot of the top card is enough for a first pass. **Don't log in to LinkedIn or scrape the profile.** Read `~/.claude/linkedin/voice.md` and `story-bank.md`: the receipts for the rewrite come from there, never invented. ## 1. Score Read `rubric.json` in this folder. Score all 13 items, show the table, give the total. Be honest: most first-pass profiles land in the 30s-40s. ``` PROFILE SCORE 43/100 headline 4/12 "Student at {{college}}", no role, no proof, no keywords about_open 2/10 opens with "Passionate about" featured 0/10 empty projects 3/8 listed, no numbers or links ... ``` ## 2. Rewrite, biggest loss first Don't rewrite everything at once: the user has to paste each piece in. **Headline (220 characters).** Formula: `{target role / what you build} | {proof} | {keywords}` - "Building {{what}} with AI | Shipped {{N}} open-source apps | Digitised a {{kind of}} business | AI, SaaS, B2B"