agentleFS
landedjobslandedjobs/ai-job-hunt-os/skills/resume-tailor/SKILL.md

resume-tailor

Skill3 starsChanged 4 months agoMITView on GitHub

Use when the user wants to tailor a resume to a job description, convert experience into quantified bullets, improve how a resume parses and scans, fix a resume that gets no responses, or prepare resume evidence for AI-company applications.

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

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 7

    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:

    Ask: "Tell me 2-3 things you actually did in that role that aren't on the resume, especially anything with a number attached (scale, …

    line 14
  2. Distinctive:

    Do not generate anything until you have at least items 1 and 2.

    line 16
  3. Distinctive:

    Gap: no evidence. Flag it; never fill it with wording.

    line 26
  4. Distinctive:

    Every bullet becomes evidence, not adjectives: use the XYZ pattern, "accomplished X, measured by Y, by doing Z." If Y is missing, ask for …

    line 30
  5. Distinctive:

    Read each rewritten bullet and ask: does this survive two follow-up questions about baselines, trade-offs, and what the user personally did?

    line 37
  6. Distinctive:

    Never invent employers, titles, dates, tools, metrics, or outcomes.

    line 48
  7. Distinctive:

    If the truthful resume does not clear the role's bar, say so plainly and point at the gap.

    line 49

“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

Rewrite resumes to match a specific job description without inventing anything. A resume must work in two modes: a fast human scan and structured retrieval inside an applicant-tracking system. Exact scan-time and ATS-adoption statistics vary by study and population, so do not repeat them as universal facts. The job is to make the resume parseable, make the first screen land, and make every line survive a follow-up question.

Before starting, collect

  1. The current resume.
  2. The full job description.
  3. Ask: "Tell me 2-3 things you actually did in that role that aren't on the resume, especially anything with a number attached (scale, latency, cost, users, revenue, time saved)." Most resumes undersell; the raw material lives in the person's head.

Do not generate anything until you have at least items 1 and 2.

Process

Step 1: Extract what the JD screens for

List in order of emphasis: hard requirements (named tools, domains; weight what appears early or repeats), the problem behind the role (visible in the responsibilities), and the JD's exact vocabulary. If they say "evals," never write "quality assessment."

Step 2: Map evidence into three buckets

  • Direct hit: they did exactly this. Leads the relevant section.
  • Adjacent: same muscle, different context. Reframe honestly.
  • Gap: no evidence. Flag it; never fill it with wording. Gaps are handled in the cover letter or interview, not by lying.

Step 3: Rewrite

  • Design the top third for a fast scan: target-matching title language, strongest company or project, domain fit, and proof links must be visible before any dense detail.
  • Every bullet becomes evidence, not adjectives: use the XYZ pattern, "accomplished X, measured by Y, by doing Z." If Y is missing, ask for it; estimates marked with "~" are fine, invented numbers are not.
  • Strip generic AI cadence: Phrases like "leveraged cutting-edge AI" get cut unless tied to a model, data, eval, or outcome the user actually touched. Tailoring must add relevant evidence, not synthetic polish.
  • Keep it database-readable: standard section headers, real dates, exact role nouns from the JD, no tables or graphics in the text flow.
  • For AI roles, surface proof links: GitHub, papers, demos, launches. Ask whether the linked repo shows tests, a clear README, and something deployed; a weak public repo is a risk, not an automatic plus.
  • Same length or shorter than the original. Tailoring adds relevance, not volume.

Step 4: Defensibility pass

Read each rewritten bullet and ask: does this survive two follow-up questions about baselines, trade-offs, and what the user personally did? If not, weaken it or cut it. At AI-native companies every resume line becomes an interview thread.

Output format

  1. The tailored resume, full text, ready to paste.
  2. Change log: what moved, what was rewritten, which JD requirement each change serves.
  3. Gap list: unmet requirements, each with a one-line plan (cover letter, pre-interview study, or ignore as wishlist).
  4. Resume-to-interview map: for each of the top 5 bullets, the most likely interview probe and what the user must be ready to say. This is where tailoring becomes interview prep.

Hard rules (apply at every step, no exceptions)

  • Never invent employers, titles, dates, tools, metrics, or outcomes. If the user cannot support a claim when you probe it, it does not go in. This mirrors what AI companies themselves ask of candidates: AI to sharpen true material, never to create experience.
  • If the truthful resume does not clear the role's bar, say so plainly and point at the gap. That is more useful than wording tricks.
  • One resume per JD. Generic resumes are what got the user here.

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.