agentleFS
keeeakeeea/resume-match-tailor/.agents/skills/resume-tailor/SKILL.md

resume-tailor

Skill0 starsChanged 52 days agoMITView on GitHub

Tailor a selected master resume to one complete target job description, using a validated resume-base-selector handoff or an explicitly chosen base plus verified donor resumes, then produce submission-ready DOCX and PDF files with automated render QA. Use after base selection; do not use to choose among master resumes, write a cover letter, or invent experience facts.

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use application-tracker, job-search and 1 more.

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.
  • xiding-codeSkill

    application-tracker

    Automatically log and track all job applications submitted. Use this skill after every application submission to record the details in a tracking spreadsheet and save relevant documents. Also trigger when the user asks "application status", "what have I applied to", "tracking", or wants to review their application history. Maintains a single source of truth for all job search activity.

    Also in 3 projects that use this

  • rhowardstoneSkill

    job-search

    Search for jobs across multiple boards and company career pages. Use when looking for new positions to apply to.

    Also in 3 projects that use this

  • AnthropicSkill

    interview-prep

    Create structured interview plans with competency-based questions and scorecards. Trigger with "interview plan for", "interview questions for", "how should we interview", "scorecard for", or when the user is preparing to interview candidates.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. 0 are common, 10 are distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check the environment first and never install system packages silently:

    line 14
  2. Very specific:

    If pdf_convert is unavailable, say so, install LibreOffice, or use --docx-only and state clearly that the application is not …

    line 20
  3. Very specific:

    Prefer a validated handoff.json produced by resume-base-selector.

    line 24
  4. Distinctive:

    Do not tailor until this passes.

    line 30
  5. Very specific:

    If no handoff exists, run base selection first, including for a single resume.

    line 32
  6. Very specific:

    Never infer requirements from a title, snippet, or expired link.

    line 33
  7. Very specific:

    Use the local .venv Python for every command.

    line 35
  8. Distinctive:

    Read the handoff, the base structured evidence, the approved donor evidence, and references/evidence-policy.md.

    line 39
  9. Very specific:

    Write applications/<slug>/tailoring-audit.json using references/audit-contract.md and …

    line 52
  10. Distinctive:

    Read references/output-spec.md.

    line 58
  11. Distinctive:

    If no page images could be rendered, say that visual inspection was not possible instead of claiming it passed.

    line 72
  12. Distinctive:

    Never overwrite a master resume or its structured source file.

    line 95
  13. Distinctive:

    Never create or strengthen metrics, scope, ownership, seniority, tools-in-use, employers, titles, dates, degrees, licenses, clearance, …

    line 96
  14. Distinctive:

    Never move a claim to a different employer or employment period.

    line 97
  15. Very specific:

    Do not use ats-added skills anywhere in the submitted resume.

    line 98
  16. Distinctive:

    Do not hide an unmet hard gate with adjacent experience or a Skills entry.

    line 99
  17. Distinctive:

    Do not use historical tailored applications as factual sources unless the user explicitly names one.

    line 100
  18. Very specific:

    Do not call the work complete until both DOCX and PDF exist, verify passes, and the page render was actually inspected.

    line 101

“Common” is measured: kept by at least 6 in 10 of the 27 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

Resume Tailor

Turn one selected base resume into a job-specific resume whose experience claims remain traceable while its positioning, ordering, wording, and Skills section are optimized for the target role.

Runtime and document tools

This skill uses portable tooling only: python-docx for the DOCX, LibreOffice headless (or a configured alternative) for the PDF, and Poppler or a maintained Python library for PDF inspection and page images. There is no dependency on any vendor-specific Documents or PDF tool.

Check the environment first and never install system packages silently:

python3 resume-workflow/scripts/check_dependencies.py

If pdf_convert is unavailable, say so, install LibreOffice, or use --docx-only and state clearly that the application is not submission-ready.

Required inputs

Prefer a validated handoff.json produced by resume-base-selector. It must contain the full JD snapshot, target metadata, selected base, optional donors, structured resume paths, known gaps, and confidence. Read references/handoff-contract.md, then:

python3 resume-workflow/scripts/run_resume_workflow.py validate-handoff --slug <slug>

Do not tailor until this passes. The runner refuses every later step while the handoff is missing or invalid.

If no handoff exists, run base selection first, including for a single resume. Never infer requirements from a title, snippet, or expired link. Import PDF/DOCX via resume-workflow/scripts/import_resumes.py, following the agent's Step 1b. Use the local .venv Python for every command; users never hand-write JSON.

Tailoring workflow

  1. Read the handoff, the base structured evidence, the approved donor evidence, and references/evidence-policy.md.
  2. Choose balanced by default; use ats or hm only when the user asks or the job clearly warrants it. Read references/tailoring-method.md.
  3. Build an internal requirement-to-evidence map. Classify every important requirement as direct, transferable, skills-only, or not-evidenced.
  4. Preserve the base resume's identity: employers, roles, dates, locations, education, and chronology. A donor claim may support only the matching employer and the same underlying employment period.
  5. Draft applications/<slug>/tailored_resume.json using ../../../resume-workflow/schemas/tailored-resume-schema.json. Every summary or experience claim must cite one or more source claim_id values.
  6. Include only evidence-backed skills, marked "evidence_status": "verified". Missing JD keywords belong in the private gap report; never add unsupported skills.
  7. Validate provenance; resolve every error before rendering:

    python3 resume-workflow/scripts/run_resume_workflow.py validate-tailored --slug <slug>
  8. Write applications/<slug>/tailoring-audit.json using references/audit-contract.md and ../../../resume-workflow/schemas/tailoring-audit-schema.json, then:

    python3 resume-workflow/scripts/run_resume_workflow.py validate-audit --slug <slug>
  9. Read references/output-spec.md. Render and verify:

    python3 resume-workflow/scripts/run_resume_workflow.py render --slug <slug>
    python3 resume-workflow/scripts/run_resume_workflow.py verify --slug <slug>
  10. Inspect the rendered pages when page images exist (applications/<slug>/render-preview/*.png). Iterate until the DOCX and PDF are visually clean, ATS-readable, and within the page budget, then record the review honestly:

    python3 resume-workflow/scripts/run_resume_workflow.py record-visual-inspection \
      --slug <slug> --status completed --performed-by "<agent or person>" --notes "<what you checked>"

    If no page images could be rendered, say that visual inspection was not possible instead of claiming it passed.

  11. Save the full application bundle without overwriting any master resume.

Output contract

For a slug such as acme-senior-business-system-analyst:

applications/<slug>/
|-- job-description.txt
|-- handoff.json
|-- tailored_resume.json
|-- tailoring-audit.json
|-- workflow-state.json
|-- <Name>_Resume_<Company>_<Role>.docx
|-- <Name>_Resume_<Company>_<Role>.pdf
`-- render-qa.json

tailoring-audit.json, workflow-state.json, and render-qa.json are private working artifacts. They are never part of the submitted resume.

Non-negotiable boundaries

  • Never overwrite a master resume or its structured source file.
  • Never create or strengthen metrics, scope, ownership, seniority, tools-in-use, employers, titles, dates, degrees, licenses, clearance, language fluency, or work authorization.
  • Never move a claim to a different employer or employment period.
  • Do not use ats-added skills anywhere in the submitted resume.
  • Do not hide an unmet hard gate with adjacent experience or a Skills entry.
  • Do not use historical tailored applications as factual sources unless the user explicitly names one.
  • Do not call the work complete until both DOCX and PDF exist, verify passes, and the page render was actually inspected.

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.