agentleFS
MahashwethaMahashwetha/Job-search-email-system-claude/.claude/skills/remove-hot-job/SKILL.md

remove-hot-job

Skill12 starsChanged 11 days agoMITView on GitHub

This skill should be used when the user wants to remove, clear, or blocklist jobs from the Hot Jobs section of the daily email. Triggers on phrases like "remove [company] from hot jobs", "clear hot jobs for [category]", "blocklist [company] hot job", "remove all senior java hot jobs", "clear [category] hot jobs", "I applied to [company] from hot jobs".

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    If a job was applied to (company is in the tracker), do NOT blocklist it — the system auto-removes tracker companies naturally.

    line 14
  2. Distinctive:

    If a job is being dismissed without applying, blocklist it so it doesn't come back.

    line 15
  3. Distinctive:

    If the user didn't specify which jobs they applied to vs dismissed, ask — applied jobs should NOT be blocklisted.

    line 37
  4. Very specific:

    Run from the project root (claude-job-agent/).

    line 42
  5. Distinctive:

    Do NOT run the daily script after editing — changes take effect on the next scheduled run.

    line 57
  6. Very specific:

    Never manually edit daily_hot_jobs.json — always use the script to avoid encoding errors.

    line 58

≈ “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

Remove Hot Jobs

Manage the hot jobs list in daily_hot_jobs.json. Hot jobs are sticky LinkedIn listings shown at the top of the daily email, 5 per category (or 8 for Tech Lead / AI categories).

Key concepts

  • current_jobs: dict of category → list of job objects. Clear a slot by removing from this list — it backfills on next run.
  • blocklist: list of [company, title] pairs. Blocklisted jobs never reappear in that category.
  • If a job was applied to (company is in the tracker), do NOT blocklist it — the system auto-removes tracker companies naturally.
  • If a job is being dismissed without applying, blocklist it so it doesn't come back.

Categories (exact keys in JSON)

  • Senior Java
  • Backend Java
  • Product Owner
  • Assistant Project Manager
  • Tech Lead / Lead Developer
  • AI / GenAI Engineer

What to do based on what the user says

Remove a single job (applied or dismissed) — remove it from current_jobs[category]. If dismissed (not applied), also add [company.lower(), title.lower()] to blocklist.

Clear all jobs in a category — set current_jobs[category] = []. For each job, blocklist it unless the user says they applied to it (or it's already in the tracker).

Remove from blocklist — find and delete the matching [company, title] pair from the blocklist array.

List current hot jobs for a category — read and print current_jobs[category].

Steps

  1. If the user didn't specify which jobs they applied to vs dismissed, ask — applied jobs should NOT be blocklisted.
  2. For each job to blocklist, run the script:
    python .claude/skills/remove-hot-job/scripts/blocklist_job.py "Company Name" "Job Title"
    Run from the project root (claude-job-agent/).
    • Title is optional — omit to blocklist all jobs from that company.
    • The script removes from current_jobs AND adds to blocklist in one shot.
    • Uses ensure_ascii=False so no encoding issues.
  3. Confirm output to the user: removed from current_jobs + blocklisted.

Block ALL current hot jobs ("block all daily jobs"): one command instead of one run per job:

python .claude/skills/remove-hot-job/scripts/blocklist_job.py --all --dry-run   # preview
python .claude/skills/remove-hot-job/scripts/blocklist_job.py --all             # apply

It automatically skips companies already in the tracker (applied jobs clear naturally).

Important notes

  • Clearing slots triggers backfill on the next daily run (11:00 AM).
  • Do NOT run the daily script after editing — changes take effect on the next scheduled run.
  • Never manually edit daily_hot_jobs.json — always use the script to avoid encoding errors.

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.