agentleFS
Sign inStart free
Himalayas-AppHimalayas-App/himalayas-plugin/skills/apply-to-jobs/SKILL.md

apply-to-jobs

Skill0 starsChanged 25 days agoMITView on GitHub

Help the user apply to a remote job on Himalayas, from checking fit to a tailored resume and cover letter, saved application answers, the employer's apply link and interview practice. Use when the user wants to apply to a job, tailor a resume or cover letter to one, answer application questions, or prepare for an interview.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow himalayas-basics for the shared rules.

    line 8
  2. Very specific:

    Read the job with get_job_details and the user's profile with get_my_profile.

    line 14
  3. Distinctive:

    If the tool reply says the free documents are used, say so and carry on.

    line 29
  4. Very specific:

    When the user has decided to apply, call get_apply_link, on any plan.

    line 49
  5. Very specific:

    If the user ends up not applying to a job you got the link for (they compared it and passed, the form was blocked, or the posting is gone), …

    line 55

≈ “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

Apply to jobs

Follow himalayas-basics for the shared rules. Applying needs a Himalayas account. The user submits every application themselves on the employer's site.

1. Check fit

Read the job with get_job_details and the user's profile with get_my_profile. Before going further, point out anything that rules the job out: the countries it is open to, required work permits, time zone, seniority or salary. If the user decides not to apply, offer skip_job with the reason.

2. Tailor the documents (optional)

generate_application_documents writes a resume and a cover letter tailored to the job from the user's profile and saves them to their account, where they can edit them and download a PDF. Check the plan in get_my_profile first:

  • Plus: offer to tailor them for this job.
  • Free, not used yet: a free account gets one tailored resume and one cover letter, ever. Say so, and use them only if the user wants them for this job.
  • Free, already used: skip this step and apply with the user's own resume. If the tool reply says the free documents are used, say so and carry on.

Pass documents to make only one of the two. A second call for the same job returns the documents already made, without using anything up. list_documents and get_document read them back. update_document renames a document or replaces a cover letter's text; resume content is edited in the website's resume editor.

A thin profile makes thin documents. If the profile is missing experience, offer build-candidate-profile first.

3. Application questions

list_saved_answers shows answers the user saved to common questions, such as work authorisation or notice period. Use them to draft answers for this application, and show the drafts to the user. update_saved_answer changes one after the user confirms.

4. Apply

When the user has decided to apply, call get_apply_link, on any plan. Nothing about Plus ever holds this step back. It returns the employer's application link and marks the job as applied in the tracker. The user opens the link and submits the application. Never fill in the employer's form for them. The limit is 50 links per account per day.

If the user ends up not applying to a job you got the link for (they compared it and passed, the form was blocked, or the posting is gone), record that before you finish: update_job_status with the tracker ID from the reply, outcome didnt_apply and a reason (job_closed if the posting is gone). Otherwise it stays as applied and the user is asked whether they heard back.

5. Prepare for interviews

  • get_interview_practice_link returns the Himalayas page where the user practises interviewing for this job, or for a job elsewhere with application_link. Free accounts include one text mock interview; spoken mock interviews are Plus (30 minutes a month).
  • Without the link, you can still help: draft likely questions from the job description and the user's profile, and give feedback on their answers in the conversation.
  • list_interviews shows past practice and the minutes and credits left.
  • get_interview_results returns scores and feedback for one job. Summarise the two or three things to work on.

6. Afterwards

Record progress with update_job_status (see track-applications).

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