agentleFS
delmarstudiosdelmarstudios/job-search-skills/skills/job-form-answers/SKILL.md

job-form-answers

Skill0 starsChanged 19 days agoMITView on GitHub

Fill job application form questions (work authorization, availability, employment history, reasons for leaving, type of business, salary, why this company, short bio) from the candidate's confirmed answer bank. Use whenever application-form questions are pasted, a portal asks for answers beyond the resume, or a role's materials need prefilled answers.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the bank, the config, and the role's JD.

    line 11
  2. Very specific:

    Salary: use the confirmed floor in the config (pay_floor), converted to the unit the form asks for.

    line 16
  3. Distinctive:

    When the candidate answers an open question with a reusable fact, update the bank (replace the ASK USER line) and the facts file, dated.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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 form answers

The answer bank is the file at form_answers_file in config/candidate.json (start from templates/form_answers.template.md). Facts behind it live in the facts file.

Steps

  1. Read the bank, the config, and the role's JD.
  2. For each question, in form order:
    • In the bank: reuse the answer exactly. Employer names, titles, dates and reasons for leaving must be word-for-word identical across applications; background checks compare them.
    • Role-specific (why this company, motivation, a relevant example): write 2–4 specific sentences from the JD and the facts file, then run job-fact-check on them.
    • Marked ASK USER, or not answerable from confirmed facts (salary without a confirmed floor, sponsorship, relocation, criminal record, samples, equipment, anything new): do not guess. Collect them into one short question list for the candidate.
    • Salary: use the confirmed floor in the config (pay_floor), converted to the unit the form asks for. If the posting states a range above the floor, "Within your posted range" is acceptable.
  3. Respect character or word limits by trimming the least relevant sentence first. If line breaks may be lost, use semicolons instead of numbered lines.
  4. Output each answer in its own fenced text block under its question so it can be copied, then the open questions.
  5. When the candidate answers an open question with a reusable fact, update the bank (replace the ASK USER line) and the facts file, dated.

Never

Submit the form, tick consent boxes, answer demographic or EEO questions on the candidate's behalf, or invent a salary, reference, certification or legal status.

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.