hunter-linkedin

hunter-linkedin

Recruiters search LinkedIn by keyword, and the hiring manager will open the profile before the coffee chat. This skill makes the profile say what the user really does in the words the job description uses, inside LinkedIn's limits, and shows the before and after.

What the user typed after /hunter-linkedin: $ARGUMENTS

Tool in this folder (standard library Python, never touches LinkedIn):

python3 "${CLAUDE_SKILL_DIR}/profile.py" --help

What it reads and writes

• hunter/linkedin.json: {"current": {...}, "draft": {...}}, each with headline, about, skills (a list) and experience (title, company, description). Shape and the reel's example: linkedin.example.json.
• The target job description as a text file, for example hunter/jd/<role-id>.txt (copy it from the posting the scout found).
• Truth sources for the check: hunter/profile.json skills and the resume (--resume hunter/resumes/<role-id>.md).
• limits.json: the limits and where each one comes from.

LinkedIn's limits

Field	Limit	Source
Headline	220 characters	widely reported; the editor's live counter is the authority
About	2,600 characters	widely reported; the editor's live counter is the authority
Skills	100 skills	LinkedIn Help 35265: "You can add a maximum of 100 skills to your profile."
Position title / description	100 / 2,000 characters	widely reported
Invitation note	200 characters, 3 a month without Premium	LinkedIn Help 46662

profile.py limits prints them with their sources.

The rules

• Only what is true. Rewrite and reorder the user's real experience. Never add a skill, title, employer, degree, date or number they do not have. The check lists every term the draft claims that the resume, the profile skills and the current LinkedIn never mention: ask the user about each one before it stays.
• LinkedIn's terms forbid automation. Its User Agreement (section 8.2, quoted on LinkedIn Help a1341387) prohibits bots and automated methods that access the site, add contacts or send messages, and software that scrapes profiles. So this skill never logs in, never scrapes and never edits the profile. The user pastes the text and clicks Save themselves.
• No promises. LinkedIn shows profile strength and search appearances in the user's own dashboard. This tool measures keyword coverage only and does not predict either.

Steps

1. Get the real profile into current: the user pastes their headline, About, skills and experience (or saves their profile as a PDF from LinkedIn and shares the text).

2. Save the job description as text and read its keywords:

   python3 "${CLAUDE_SKILL_DIR}/profile.py" keywords --job hunter/jd/google-swe.txt
   

   Weight 3 means required or minimum qualifications, 2 the body of the posting, 1 preferred or bonus.

3. Write draft: a headline that says the role and the two or three strongest true skills; an About that opens with what the user builds and one or two proven results; skills ordered so the required terms come first; experience bullets from /hunter-resume (a strong verb, a number, the outcome).

4. Check and compare:

   python3 "${CLAUDE_SKILL_DIR}/profile.py" compare --job hunter/jd/google-swe.txt --resume hunter/resumes/base.md
   python3 "${CLAUDE_SKILL_DIR}/profile.py" check --job hunter/jd/google-swe.txt --json
   

   Exit 1 means a field is over its limit. Fix every OVER line, then ask the user about every "Confirm these are true" term.

5. Show the before/after table and the final text, field by field, ready to paste. The user pastes it into LinkedIn and saves.

Example: the reel

Jordan Reyes (fictional) had the default headline "Software Engineer at Brightline Labs", an empty About and six generic skills. Against a Software Engineer, Cloud Infrastructure job description, the draft headline becomes "Software Engineer · Distributed systems, ML infrastructure and fast, reliable APIs" (82 characters), the About tells the payments API story with its real numbers (p99 latency down 38% across 4M requests a day), and the skills put Go, Distributed Systems and System Design first. compare shows keyword coverage 22% before and 86% after, required terms 2/8 to 7/8, and C++ still missing: the posting asks for it, Jordan does not have it, so it stays out. Jordan pastes the draft into LinkedIn himself.

What it never does

• Never invents experience, skills, titles, degrees, dates or numbers.
• Never logs in to LinkedIn, scrapes it, edits a profile or sends anything: LinkedIn's terms forbid bots and automated messaging, and this pack obeys.
• Never claims a profile change will get the user hired or found.