agentleFS
Miracle-AlignerMiracle-Aligner/job-search-hq/.claude/skills/update-status/SKILL.md

update-status

Skill1 starsChanged 5 months agoMITView on GitHub

Use when the user reports progress on a role and wants the board updated. Triggers: /update-status, "move X to tech interview", "I got an HR screen with Y", "Z rejected me", "got an offer from W", "schedule my interview with V". Moves a vacancy through the pipeline, appends a timestamped statusDetail (preserving history), optionally adds a schedule event, honors pipeline-lock rules, and — when an interview is being scheduled — offers to generate interview prep notes.

2 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

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Use today's real date (check the environment date).

    line 29
  2. Very specific:

    If yes, run /interview-prep <id> [eventId] and persist the brief on that event (events[].prep).

    line 49
  3. Very specific:

    If scripts/serve.py is running and the board is open in a browser, the viewer auto-loads the new data on next change.

    line 59

≈ “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

update-status

Reflect a real conversation/outcome on the board. Edits one vacancy in data/vacancies.json (the v2 envelope's vacancies[]).

Steps

  1. Identify the vacancy — by id, or company/role match. If ambiguous, ask.
  2. Set status to the new stage: to_apply · applied · hr_screen · tech_interview · final · offer · rejected · closed · watch · disliked.
  3. Append to statusDetail — never overwrite. Prepend a dated line and keep the prior text:

    2026-06-09 · HR screen booked for the 12th (recruiter: friendly, comp TBD).
    <previous statusDetail…>

    Use today's real date (check the environment date). statusDetail may contain light formatting (<b>, <a href>, …) — the viewer sanitizes it.

  4. Schedule event (optional) — if the update involves a meeting/deadline, add an entry to events[]: {id, kind, at (ISO YYYY-MM-DDTHH:MM), durationMin?, title?, via?, meetingUrl?}. kind ∈ interview · take_home_due · follow_up · offer_deadline · other.

Pipeline-lock rule (sacred)

A real pipeline status — applied, hr_screen, tech_interview, final, offer, rejected — reflects a real conversation. Never silently downgrade it (e.g. a dead posting doesn't turn tech_interview into closed). Only move it on the user's explicit say-so.

Interview-prep prompt (the important bit)

When this update schedules an interview — i.e. you're adding an interview-kind event, or moving the role into hr_screen / tech_interview / final — ask the user:

"Want me to prepare interview prep notes for this? I'll research the company and build a brief tailored to your profile and the JD."

If yes, run /interview-prep <id> [eventId] and persist the brief on that event (events[].prep). If no, just save the status change.

Finish

python3 scripts/validate.py
python3 scripts/build.py --real   # refresh the gitignored file:// snapshot

If scripts/serve.py is running and the board is open in a browser, the viewer auto-loads the new data on next change; a stale open page that tries to save will get a 409 and offer to reload.

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.