agentleFS
mayankasthanamayankasthana/applymate/.agents/skills/tailor-application/SKILL.md

tailor-application

Skill1 starsChanged 45 days agoMITView on GitHub

Tailor resume and cover letter for a tracked application from the dossier, register artifacts, and stage them for candidate review.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. CodesWhat/careerrat★ 4same name
    2. manuelschurr/professional-twin★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 5

    Very specific

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

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

    Ensure the job exists and is scored: node bin/applymate.ts job match <jobId>.

    line 8
  2. Very specific:

    If the relevance gate refuses, tell the candidate.

    line 9
  3. Very specific:

    Read the chosen resume plus supporting dossier docs (dossier search).

    line 14
  4. Very specific:

    Write workspace/applications/<appId>/resume.md and cover-letter.md, tailored to the JD with only dossier facts.

    line 15
  5. Very specific:

    Read it and follow it literally.

    line 44

≈ “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

Tailor an application

  1. Ensure the job exists and is scored: node bin/applymate.ts job match <jobId>. If the relevance gate refuses, tell the candidate; proceed only with their explicit --force.
  2. node bin/applymate.ts app start <jobId> — prefer --resume <dossier path> using the best suggestion from job match output (candidate keeps per-company resumes; fall back to the master resume).
  3. Read the chosen resume plus supporting dossier docs (dossier search). Write workspace/applications/<appId>/resume.md and cover-letter.md, tailored to the JD with only dossier facts. Close obvious keyword gaps the dossier truly supports; list real gaps in notes.md instead of inventing. The resume must not contain the target company's name or the target role's title anywhere — no header, objective, summary, or body line. Naming them makes the resume look customized for the posting; tailor the content, keep the document generic. (The candidate's own past employers and titles stay. The cover letter is where company and role belong.) Before registering, run both documents through the humanizer skill — every word that goes out in the candidate's name must pass it (prime directive 6 in AGENTS.md). It strips AI tells so the documents read like the candidate wrote them; facts and claims stay untouched.
  4. Apply the candidate-mandated resume standards (full text in AGENTS.md, "Resume standards"):
    • One title per line — each position is company line, title alone, date range alone. Never join titles/dates on one line (ATS).
    • Meta lines must be parser-friendly (this is what portal resume parsers read to autofill forms — verified on Workday 2026-09-30 where decorative company lines dropped every company): company line is plain text Company, City, Country — no heading markup, no parentheses, no sub-brand names, no em dashes; title line may be bold; date line is MMM YYYY – MMM YYYY (en dash) with nothing else on the line — no italics, no notes ("promoted within 15 months" goes in the description in parentheses); context paragraphs sit plain between dates and bullets, never italic. Company belongs to the line, not the heading.
    • The candidate's own content list — which projects, labs, awards and open-source work must appear, and the exact wording rules for each — is in the workspace, not in this repo: node bin/applymate.ts profile note get resume-standards Read it and follow it literally. If it is missing, ask the candidate to create it (profile note set resume-standards <file.md>) rather than inventing content.
    • Ship as a 2-page A4 PDF: the stock render HTML has no print CSS — apply a print stylesheet and verify the page count before showing the PDF.
    • Upload/submit under a generic filename (candidate's name only) — never the target company/role in the filename; recruiters see it. Per-company names are for the private dossier copies only.
  5. Register artifacts:
    • node bin/applymate.ts app artifact <id> resume applications/<id>/resume.md
    • node bin/applymate.ts app artifact <id> coverLetter applications/<id>/cover-letter.md
  6. node bin/applymate.ts render each artifact; ensure the review UI is running (chat serve) and tell the candidate what to review and where. Portal form work does not start until the candidate has reviewed these artifacts — "apply to X" authorizes the tailoring, not a bypass of the review.
  7. Move status as work completes: matched → tailoring → ready. ready requires the resume artifact (toolbelt-enforced). Submission waits for the candidate's explicit go — always.

$ARGUMENTS

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.