agentleFS
adriano-labsadriano-labs/applyarc-claude-plugin/skills/pipeline-coach/SKILL.md

pipeline-coach

Skill0 starsChanged 30 days agoMITView on GitHub

Reviews and runs the user's job search pipeline in their ApplyArc tracker. Summarises every stage, spots stale applications, picks the next best actions, moves jobs between stages and drafts follow-up, thank-you and outreach messages. Use when the user asks "what have I applied to", "what should I do next", "review my job search", "weekly job search review", "chase this application", "I got an interview", "I was rejected" or "save this job". For tailoring a new application use job-application; for an offer use offer-negotiation.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Keep the user's job search moving with their ApplyArc tracker, via the ApplyArc MCP server (applyarc).

    line 8
  2. Distinctive:

    Confirm before writing, unless asked directly: When the user names the exact change ("save this job", "move Cleo to interview"), that is …

    line 17
  3. Very specific:

    Call list_my_jobs (raise limit up to 100 if they track many jobs).

    line 31
  4. Very specific:

    If the pipeline is thin (for example fewer than five active applications), say so and suggest saving new roles with save_job.

    line 40
  5. Very specific:

    If the user asks about limits, call check_usage and report what it returns, including the reset date.

    line 65

≈ “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

Pipeline coach

Keep the user's job search moving with their ApplyArc tracker, via the ApplyArc MCP server (applyarc). The tracker is the source of truth; it is also on applyarc.com, so anything you change here shows up there.

Why this shape: job searches stall quietly. A short weekly review with one clear action per stale item keeps momentum and stops good leads going cold.

Ground rules

  1. Confirm before writing, unless asked directly. When the user names the exact change ("save this job", "move Cleo to interview"), that is the yes: do it and confirm in one line. For changes you propose yourself, list them and get one yes for the batch. Never move a job on a guess.
  2. Use returned data exactly. Dates, stages and ids come from list_my_jobs. Do not invent dates or contacts.
  3. Ask before spending. Each generate_for_job call uses one AI generation. Say how many you plan.
  4. Show tool messages as written, including limit or upgrade messages; offer check_usage if limits come up.
  5. British English. No em dashes.

Weekly review

  1. Call list_my_jobs (raise limit up to 100 if they track many jobs).
  2. Group by stage: wishlist, applied, interview, offer, rejected. Show counts.
  3. Flag:
    • Applied and silent for about 10 working days or more: suggest a follow-up.
    • Wishlist items saved more than a week ago: apply, or drop.
    • Interview items: check prep is done and a thank-you was sent.
    • Offer items: hand off to offer-negotiation.
  4. Give the three actions for this week, most valuable first.
  5. If the pipeline is thin (for example fewer than five active applications), say so and suggest saving new roles with save_job.

Actions

  • Log progress: update_job_status with the jobId.
  • Save a new role: save_job with title, company, description, and pay or url when given. If save_job returns alreadyTracked: true, say the job was already in the tracker, not that it was saved, and ask whether to leave it or move its stage. Do not offer to save a second copy.
  • Chase a silent application: generate_for_job with follow-up.
  • After an interview: generate_for_job with thank-you; put names and one specific moment in notes.
  • Warm intro or recruiter message: generate_for_job with outreach-message.
  • Rejection: move to rejected, offer a short note asking for feedback (via follow-up with that aim in notes), and suggest one lesson for the next application. Keep the tone encouraging.

generate_for_job needs the job object (title, company, description, optional location and url). Reuse the fields returned by list_my_jobs; ask the user to paste the description if it is missing.

Allowance

If the user asks about limits, call check_usage and report what it returns, including the reset date.

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.