agentleFS
VincenzoImpVincenzoImp/openings/skills/track-applications/SKILL.md

track-applications

Skill7 starsChanged 3 days agoMITView on GitHub

Record and review the progress of Openings applications - "X replied", "I applied to Y", "I got rejected by Z", "track my applications", "what's waiting?", "close the ones that never answered". Records only what the owner reports.

3 other projects use 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. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read openings first. You record what the owner tells you.

    line 11
  2. Very specific:

    Search applications_list by company or title.

    line 16
  3. Very specific:

    Use applications_update; the date is the one the owner gives, today otherwise.

    line 23
  4. Very specific:

    Read workspace_context counts, then applications_list:

    line 38

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Track your applications

Read openings first. You record what the owner tells you; you never learn an outcome from silence and never contact anyone.

Find the application

Search applications_list by company or title. When more than one matches, or the job has a Closed attempt and an open one, ask which. A job with no application yet: start one with applications_create only when the owner says they applied to it.

Record what happened

Use applications_update; the date is the one the owner gives, today otherwise.

  • "I applied": set Applied with the day they sent it.
  • A reply (interview invitation, offer, rejection, or anything else such as a request for references): record it as a reply with a short note in the owner's words. A reply moves the stage by itself; do not set the stage too.
  • A mistake in a recorded reply: correct or delete that reply.
  • "I won't pursue it": close it as not pursued. An employer's rejection is a reply, not this.
  • Details worth keeping (interviewer names, next steps) go in a note on the application.

What's waiting

Read workspace_context counts, then applications_list:

  • Waiting on the owner: Ready applications, deadlines first; Shortlisted ones blocked by a requirement only they can resolve.
  • Waiting on employers: Applied and Interview, with days since sending and the last reply.
  • Overdue: Applied with no reply past the no-reply period.

Close overdue ones as no response only when the owner asks, or Working with me says to. Otherwise list them and ask. Never close an Interview or Offer as no response.

For "how is it going", stats_get gives reply and interview rates; with only a few applications give counts, not percentages.

Report back

In chat: what you recorded, with the stage each application is now in; what waits on the owner, deadlines first; overdue applications and the question whether to close them.

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.