agentleFS
ledqledq/resumery/CLAUDE.md

resumery

CLAUDE.md1 starsChanged 4 months agoMITView on GitHub

Tailors the candidate's resume to one job description (JD) per run. Each run lives in its own application workspace (applications/<id>/). Agents author resume content as JSON (the workspace's resume.json). The candidate's real experience lives in bank/experience_bank.md, the only source of facts. Surface and frame the candidate's experience to match the JD as fully as the evidence allows, and not one claim further: maximum truthful match. The edge is a rich evidence bank, not a flat resume, so there is more…

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Every claim on the resume must trace to the bank.

    line 22
  2. Distinctive:

    No em dashes (the "—" character).

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md 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
CLAUDE.md

Resume Tailoring

Tailors the candidate's resume to one job description (JD) per run. Each run lives in its own application workspace (applications/<id>/). Agents author resume content as JSON (the workspace's resume.json). The candidate's real experience lives in bank/experience_bank.md, the only source of facts.

Objective

Surface and frame the candidate's experience to match the JD as fully as the evidence allows, and not one claim further: maximum truthful match. The edge is a rich evidence bank, not a flat resume, so there is more true material to surface than a one-page resume could show.

The Rule: claim vs. framing

  • Claims are checkable facts: titles, employers, dates, degrees, credentials, whether an accomplishment happened. They must be true; this record layer has zero degrees of freedom.
  • Framing is how true work is presented: which skills lead, which bullets are chosen, the words describing real work. Optimize it freely, limited only by truth.

Every claim on the resume must trace to the bank. Reframing real experience to fit the JD is the job; inventing experience, outcomes, or numbers is the one thing never allowed.

Punctuation

No em dashes (the "—" character). Join clauses with semicolons, set off asides with commas, introduce with colons. Spell out the "~" shorthand ("about").

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.