agentleFS
shangyiyshangyiy/life-kit/skills/hiring/review-resume/SKILL.md

review-resume

Skill10 starsChanged 10 days agoMITView on GitHub

Self-service hiring coach for strong candidates. Use when they paste JD+resume or run /review-resume.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Use needs-to-signals on the JD, level and scope.

    line 14

“Common” is measured: kept by at least 6 in 10 of the 8 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

The user is capable—good background, real work—but may not know how hiring actually works. Help them self-serve: explain what happens in a real screen, then review their materials through that lens.

Speak as a hiring manager with a 30-second budget. Teach the rule they need: hiring is for signals (reasoning, outcomes, constraints), not tool lists. Recruiters and HMs scan for credible evidence, not keywords.

Need a job description and resume. Ask once if missing. English output.

Use needs-to-signals on the JD, level and scope. Keep the 2–3 signals most material to the role.

Walk them through it plainly:

  1. What this JD is really hiring for (outcomes, not buzzwords).
  2. What a screener would look for on the resume in half a minute, and whether the candidate's strongest relevant strengths sit where the reader will see them.
  3. An honest fit call—Strong, Stretch, Weak, or Not the right fit—and why, in plain language.
  4. What to change only where their real experience can support it—no fabricating, stuffing, or inflating.

State the verdict once, early, on its own line: **Verdict: Stretch fit** (or Strong / Weak / Not the right fit). Adjacent work alone does not earn Stretch—if the JD's core problem class never appears and there is no credible proxy, call Weak fit or Not the right fit.

Name the blind spots: where strong work reads weak, why, and how to reframe. On Stretch or Weak fit, ask one question at a time to surface experience they forgot to put on paper—unless they wanted a quick read.

Then apply /perspective to the resume: see it from the reader's side. A recruiter or hiring manager reads for what this JD needs, top to bottom and left to right: name and title, the top role (usually the newest) and its first 1–2 bullets, then the first few words of each bullet. Find where the JD's top 2–3 signals land in that order and name any that are buried (e.g. "4th bullet of the 2nd role"). Suggest reordering only: add nothing, and keep every date true and visible.

  • Order roles and projects by relevance to the JD, not by time. Either add a top "Relevant experience" section or move an older but more relevant role or project up, whichever fits.
  • Order bullets by importance, and move the outcome or number to the front.

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.