agentleFS
Tdeniz1Tdeniz1/resume-engine-starter/.claude/skills/tailor/SKILL.md

tailor

Skill0 starsChanged 3 months agoMITView on GitHub

Generate a tailored one-page resume PDF for a specific job. Use when the user pastes a job title or description, shares a job posting link, or asks for a resume for a role.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use inbox.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • kv0906Skill

    inbox

    Quick capture mode (with content) or batch processing mode (no content). GTD-style routing of inbox items to proper folders. Use "/inbox thought to capture" or "/inbox" to process.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read AGENTS.md in the repo root first if you have not already.

    line 8
  2. Distinctive:

    Never invent: Every entry references a master id.

    line 36
  3. Distinctive:

    If it is 2 pages, trim bullets and re-render until it is 1.

    line 59

“Common” is measured: kept by at least 6 in 10 of the 7 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

Tailor a resume to a job

Read AGENTS.md in the repo root first if you have not already. It holds the hard rules this skill assumes.

Inputs

Take from the user's message, or ask for: the job description (pasted text, a URL, or a file) and the company name. Derive a short role tag for the filename ("Forward Deployed Engineer" becomes FDE, "Senior Software Engineer" becomes SWE). Confirm the tag only if genuinely ambiguous.

Steps

  1. Set up the application folder. Slug is lowercase company-role, e.g. applications/acme-data-analyst/. Save the job description verbatim to jd.txt there.
  2. Read ALL master data in data/: profile, experience, education, skills, projects, publications, honors, certifications. If any file still contains sample-* ids or FILL_ME, STOP and run /intake first.
  3. Analyze the job description. Extract must-have skills, nice-to-haves, seniority, the keywords an ATS would scan for, and what the role actually rewards: shipping speed, client-facing polish, research rigor, ownership.
  4. Write tailored.yaml in the application folder, using the schema in AGENTS.md (or copy the shape of applications/_example/tailored.yaml).

    Non-negotiable:

    • Never invent. Every entry references a master id. Every bullet is a rewrite of content in that entry. Numbers verbatim from master data.
    • Respect provenance flags in each entry's details. VERIFIED preferred, CLAIMED allowed, CONFLICT forbidden. Follow any standing rule lines the user has written there, including entries to leave off by default and entries to ask about before including.
    • No em dashes anywhere that renders. Comma, colon, semicolon, or parentheses instead. En dashes in ranges are fine.
    • Reverse chronological within every dated section. Relevance decides which entries appear and how many bullets each gets, never their order.
    • Target 12 to 16 bullets total. Cut the least relevant entries entirely rather than shrinking everything.
    • Order SECTIONS to lead with the strongest case for THIS job. Projects before experience for a research role; experience first for consulting.
    • Rephrase bullets to mirror the job description's own vocabulary wherever that is honest.
  5. Validation runs automatically via the PostToolUse hook when you write tailored.yaml. If it errors, fix the tailored file. If a fact is real but missing from master data, ask the user, add it to data/, then retry.
  6. Render: scripts/render.sh applications/<slug>. This validates again, compiles the PDF with the canonical filename, and checks the page count. If it is 2 pages, trim bullets and re-render until it is 1.
  7. Deliver: open the PDF (or give the full path), then 2 or 3 lines on what you emphasized and why. Offer tweaks.
  8. Commit the application folder so there is a record of what was sent where: git add applications/<slug> && git commit. Push if a remote is configured and the repo is private.

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.