agentleFS
theraihanrakibbtheraihanrakibb/agent-skills/resume/SKILL.md

resume

Skill0 starsChanged 3 days agoMITView on GitHub

Resume review and optimization in one skill: diagnose quality (expression, structure, credibility, JD match, truthfulness, ATS parseability) and polish/improve an existing resume while preserving facts and, optionally, a designed PDF layout. Merged from resume-review + resume-polish. Triggers on: review my resume, rate my resume, check my resume, polish my resume, optimize my resume, improve this resume, rewrite for a job.

64 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use pause, status and 10 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.
  • kennethleungtySkill

    pause

    Pause — stop the music (alias for /stop)

    Also in 7 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 15 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 7 projects that use this

  • MicrosoftSkill

    config

    Show or change TokenEconomizer's settings: turn micro-skills, tool pruning or the loop guard on or off, or tune them, for this repository or (with --global) every repository. Use when the user asks to configure, enable or disable TokenEconomizer or one of its mechanisms.

    Also in 3 projects that use this

  • sahinSkill

    execute

    Also in 4 projects that use this

  • u9401066Skill

    bug-fix

    Structured bug fixing workflow with root cause analysis and regression prevention. Triggers: BF, 修 bug, fix bug, debug, 除錯, 錯誤, error, 問題, issue, 修復, fix, 故障, fault, 異常, exception, 失敗, failure, 不能用, broken, 壞掉.

    Also in 3 projects that use this

  • +2 more from microsoft

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 56 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    review = diagnosis only: Never rewrite, never restructure, never generate.

    line 33
  2. Very specific:

    polish = improve in place: Never fabricate numbers, tech stacks, hardware models, journal names, dates, or experiences.

    line 34
  3. Very specific:

    Preserve a designed PDF: If the user has a custom layout or sets preserveLayout, polish may NOT emit a full markdown resume — only a …

    line 35
  4. Very specific:

    Bilingual parity: If the resume is EN + 中文, every change is mirrored in both languages, not just the chosen language.

    line 36

“Common” is measured: kept by at least 6 in 10 of the 56 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 (merged: review + polish)

One skill that does both: review (diagnose, never edit) and polish (improve, never fabricate). It is the consolidation of the upstream resume-review and resume-polish skills, with additions:

  • ATS / parseability check (review): when you supply extracted PDF text (pdfText), it flags broken/split tokens, stray hyphens, ligature artifacts, and bilingual keyword duplication.
  • Internal number-consistency + Summary-to-body traceability (review): credibility now has two mandatory sub-checks.
  • Layout-preserving mode (polish): when the resume is a designed PDF you want kept intact, polish emits only before→after fragments, never a full rewrite.
  • Bilingual (EN + 中文) handling in both modes.

Which mode to run

User saysModeFull instructions
"review my resume", "rate this", "what's wrong"reviewreferences/review_SKILL.md (+ references/review_schema.json)
"polish my resume", "optimize", "improve", "rewrite for X"polishreferences/polish_SKILL.md (+ references/polish_schema.json)

Load the referenced file for the full workflow, dimensions, scoring, and output contract. This file is only the router.

Key rules (both modes)

  1. review = diagnosis only. Never rewrite, never restructure, never generate. Output JSON per references/review_schema.json.
  2. polish = improve in place. Never fabricate numbers, tech stacks, hardware models, journal names, dates, or experiences. Edits trace to the original or sourceTexts.
  3. Preserve a designed PDF. If the user has a custom layout or sets preserveLayout, polish may NOT emit a full markdown resume — only a compact before→after diff plus a note to apply edits in their source.
  4. Bilingual parity. If the resume is EN + 中文, every change is mirrored in both languages, not just the chosen language.
  5. ATS is advisory in polish. polish outputs Markdown, so it cannot fix PDF text-layer breaks; it must list any discovered text-layer issues in suggestions instead.
  6. Never submit or regenerate the PDF. These skills produce text/diffs only.

Typical loop

review → fix issues with polish (optionally preserveLayout to keep the PDF) → review again to confirm the score rose. Supply jd for targeted optimization, sourceTexts for anti-hallucination checks, and pdfText for the ATS check.

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.