agentleFS
MahashwethaMahashwetha/Job-search-email-system-claude/.claude/skills/update-hr/SKILL.md

update-hr

Skill12 starsChanged 11 days agoMITView on GitHub

This skill should be used when the user wants to find, add, or update HR contacts (recruiters, talent acquisition, hiring managers) for a company in the Excel job tracker. Triggers on phrases like "find HR for [company]", "add recruiter for [company]", "search LinkedIn for [company] recruiter", "update HR contacts", "who recruits at [company]", "add this HR contact".

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Always try the connectors in this order (user rule, 2026-10-29), moving on only when one gives nothing usable:

    line 12
  2. Distinctive:

    If she pastes names/emails she found herself (Hunter or Apollo extension on LinkedIn), use those as-is.

    line 17
  3. Distinctive:

    Only if both give nothing, fall back to the LinkedIn WebSearch in Step 1.

    line 19
  4. Distinctive:

    Use WebSearch with this query:

    line 23
  5. Very specific:

    Run update_hr_contacts.py from the project root.

    line 36
  6. Distinctive:

    Never overwrite manually entered contacts — the script is append-only.

    line 52
  7. Distinctive:

    Write names directly, no [UNVERIFIED] prefix.

    line 53
  8. Distinctive:

    Don't drag the fill handle in Excel after running — it creates ghost rows with duplicated formulas.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Update HR Contacts

Find LinkedIn recruiter profiles for a company and add them to column E of List.xlsx.

Step 0 — Lead tools first: Hunter, then RocketReach

Always try the connectors in this order (user rule, 2026-10-29), moving on only when one gives nothing usable:

  1. Hunter: Domain-Search on the company domain with department: hr. "Reached the limit" = quota gone, move on.
  2. RocketReach: person_search with current_employer, department: HR, country: FR. Needs a paid plan.

Apollo is NOT used (her choice 2026-10-29): its Free plan blocks people search and person match via Claude. If she pastes names/emails she found herself (Hunter or Apollo extension on LinkedIn), use those as-is.

Only if both give nothing, fall back to the LinkedIn WebSearch in Step 1.

Step 1 — Search LinkedIn

Use WebSearch with this query:

"{company}" recruiter OR "talent acquisition" OR "hiring manager" OR "HR manager" OR "people partner" Paris OR France OR EMEA site:linkedin.com/in

Location priority: Paris first, then France, then EMEA as a fallback. Only use EMEA-level contacts when no Paris or France-specific person is found. Ignore contacts based in India, US, or APAC unless the company has no EU presence at all.

Step 2 — Add to the HR_CONTACTS dict

Open update_hr_contacts.py and add or extend the company entry in the HR_CONTACTS dictionary. Use the company name exactly as it appears in column A of List.xlsx. If the company is already in the dict, append the new contacts to its list — don't replace existing ones.

Step 3 — Run the script

Run update_hr_contacts.py from the project root. The script reads existing cell content first and only appends contacts whose names aren't already there. Running it twice produces zero changes the second time.

Step 4 — Verify

The script reports how many rows were updated. Check that the count matches expectations.

Adding a single contact to one row (e.g. a verified recruiter email)

For one contact on one specific row, use the append-only script instead of editing the cell by hand:

python .claude/skills/update-hr/scripts/add_hr_contact.py --row 311 --name "Jane Doe" --url "https://www.linkedin.com/in/..." [--title "Tech Recruiter"] [--email "x@company.com"]
python .claude/skills/update-hr/scripts/add_hr_contact.py --company "Bluecoders" --name ...   (all rows of that company)

It keeps every existing contact, appends the new one with CHAR(10), does nothing if the name is already there, takes the shared tracker lock and backs up List.xlsx first. Never write to column E with ad hoc openpyxl code (that is how row 311's contacts were once overwritten).

Rules

  • Never overwrite manually entered contacts — the script is append-only.
  • Write names directly, no [UNVERIFIED] prefix.
  • To remove a contact: delete it from Excel AND remove it from the HR_CONTACTS dict. That's the only case requiring both steps.
  • Don't drag the fill handle in Excel after running — it creates ghost rows with duplicated formulas.

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.