agentleFS
Vishwajeetkumbhar379Vishwajeetkumbhar379/claude-skills/skills/application-pack/SKILL.md

application-pack

Skill0 starsChanged 41 days agoMITView on GitHub

Build a complete, truthful application for one job (tailored ATS-safe CV and cover letter, email, referral messages, form answers) or an interview prep pack. Use when someone shares a job link and says apply, or asks for interview prep.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check it hasn't been applied to already (sent mail, application log).

    line 16
  2. Distinctive:

    Write: tailored CV (JD language, only real facts), cover letter (300-400 words), email (170-270 words), 2-4 referral notes to real people …

    line 19
  3. Very specific:

    Run the application-humanizer rules on every text.

    line 20
  4. Very specific:

    Check the CV PDF: text-based, reads in order with pdftotext, one column or a clean two-column layout, no text in images.

    line 21

≈ “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

Application pack

The hands-on twin of job-scout. The person is present, so ask when a fact is missing, and never send anything to an employer until they say "send".

Sources of truth

  • The candidate's CV (as text) and profile.md. Never add employers, dates, titles, metrics, budgets, tools, clients, certifications, languages or skills that aren't there.
  • Label every claim VERIFIED (in the CV), DERIVED (follows directly from it) or MISSING (ask). Never turn MISSING into VERIFIED to pass a check.

Mode 1 · Full application

  1. Fetch the job from the official ATS and confirm it is live.
  2. Check it hasn't been applied to already (sent mail, application log).
  3. Evaluate with the job-scout table and score. Below 72, recommend skipping and say why.
  4. Research 1-2 verified company specifics (a launch, a hire, a market move) from official sources, with URLs.
  5. Write: tailored CV (JD language, only real facts), cover letter (300-400 words), email (170-270 words), 2-4 referral notes to real people found by search (never invent people or URLs), and answers to the application form.
  6. Run the application-humanizer rules on every text.
  7. Check the CV PDF: text-based, reads in order with pdftotext, one column or a clean two-column layout, no text in images.
  8. Deliver everything, list any MISSING facts as questions, and wait for "send".

Mode 2 · Interview prep

Company brief with sources; the JD requirement map; 8 likely questions (3 behavioural, 3 role-specific, 2 motivation) with STAR answers built only from real experience (mark TO ADD where a story is missing); 4 sharp questions to ask; salary guidance (published range or a labelled estimate); a 60-second pitch. Offer a mock interview one question at a time, and never answer for the candidate.

Mode 3 · Follow-ups and referrals

Connection note max 200 characters (role, one real proof point, light ask). Follow-up 60-110 words with one new piece of value. Never "just checking in".

Always

Truth beats score. Unknown facts become questions.

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.