agentleFS
Sign inStart free
JakeschincariolJakeschincariol/hunter-skill/skills/hunter-linkedin/SKILL.md

hunter-linkedin

Skill12 starsChanged 29 days agoMITView on GitHub

The LinkedIn Optimizer. Rewrites the user's LinkedIn headline, About, skills and experience for the job they want, using only what is true, then checks the draft against LinkedIn's field limits (headline, About, skills count, position title and description) and against the keywords of the target job description, with a before/after report: coverage, required terms, what was gained and what is still missing. The user pastes the final text into LinkedIn themselves. Use when the user says "optimize my LinkedIn", "rewrite my headline", "fix my About section", "LinkedIn for this job", "what skills should I list", or "make recruiters find me".

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never add a skill, title, employer, degree, date or number they do not have.

    line 57
  2. Very specific:

    Write draft: a headline that says the role and the two or three strongest true skills.

    line 83
  3. Distinctive:

    Never invents experience, skills, titles, degrees, dates or numbers.

    line 115
  4. Distinctive:

    Never logs in to LinkedIn, scrapes it, edits a profile or sends anything: LinkedIn's terms forbid bots and automated messaging, and this …

    line 116
  5. Distinctive:

    Never claims a profile change will get the user hired or found.

    line 118

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

FieldLimitSource
Headline220 characterswidely reported; the editor's live counter is the authority
About2,600 characterswidely reported; the editor's live counter is the authority
Skills100 skillsLinkedIn Help 35265: "You can add a maximum of 100 skills to your profile."
Position title / description100 / 2,000 characterswidely reported
Invitation note200 characters, 3 a month without PremiumLinkedIn 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.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free