agentleFS
thituongh699-hashthituongh699-hash/oriward/.agents/skills/resume-builder/SKILL.md

resume-builder

Skill2 starsChanged 7 days agoMITView on GitHub

Translate real career histories into complete, focused Markdown resumes, preserving sources and versions while delivering a full draft for user edits. Use for resume content, not external submission or invented qualifications.

27 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

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

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 4

    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:

    Use STAR-C to translate real work, business, study, projects and informal responsibilities into relevant value.

    line 8
  2. Distinctive:

    Import/input are optional source aids: check extraction against the original.

    line 10
  3. Distinctive:

    Follow resume-review; save through CLI and report receipt/path.

    line 15
  4. Distinctive:

    Use the decision contract for actual target/preparation recommendations.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 18 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 builder

Use STAR-C to translate real work, business, study, projects and informal responsibilities into relevant value. Clear self-report suffices; write confidently within its limits.

Import/input are optional source aids: check extraction against the original; imported text does not update the experience library. Diagnose is optional lint. Deliver a complete resume rewrite or resume compose draft under the composition contract.

  1. Reuse user requirements and saved career-mapping/search/analysis context. Read the primary JD first: its purpose, 2–4 deliverables and gates control the draft. Optional comparable JDs enrich interpretation without importing other employers' gates. Use resume tailor-packet --job-id <id> [--reference-job-ids <id> ...], then resume compose with matching target flags and --file <json>. Without a primary job, use references and optional --target-title for a direction draft; bind job-specific review/interview/application to a real job.
  2. Read the entire experience index, then selected details. Select evidence and necessary chronology anchors semantically; no automatic mapping, keyword scoring or restoration of unselected experiences. Expanded sections need model-written bullets; explicit bullets: [] permits a brief title/date anchor. Omit irrelevant school-period jobs lacking continuity value. Group only where dates/ownership remain clear; honour exclusions/gaps and invent no explanations.
  3. Present identity/contact and known availability in the header, personal strengths (skills/certificates as subsections) and education. Add work/projects/internships where useful. Categories: 工作经历, 项目经历, 实习经历, 教育经历; business maps to work, 其他经历 is invalid. Bind academic work to the matching degree with education_key. Save template choice: explicit template → profile.resume_preferences.template → reference; inherit a saved section_order where applicable.
  4. Follow resume-review; save through CLI and report receipt/path. Keep sources internal. Write the complete grounded draft without per-experience approval or exact quotes; ask only about material uncertainty.
  5. Read the actual draft with resume editorial-packet --resume-id <id> against JD/evidence. Check relevance, timeline, degree placement, STAR-C, template and factuality; save actual findings via resume editorial-review --file <json>. Compose requires this review: use revise for unresolved findings; reread corrections before ready. Saving is not readiness; never fabricate review. This is separate from hiring ratings and adds no user approval gate. Deliver the full draft for edits. Offer exact-version hiring review/interview practice for a primary job, respecting deferrals and saving only actual answers; these do not block writing/export. STAR-C clarifies true contribution, challenges and known results in natural prose; never invent metrics, seniority or impact. Full schema and examples are in the composition contract.
  6. For Word/PDF, use document-export. Inspect each rendered page for density, detached headings, links and breaks. Adjust content before shrinking type. Preserve versions; dry-run cleanup first.

Report local/unsubmitted status, version and paths; keep internal provenance out of candidate-facing content. Draft/export never authorizes sending.

Career Twin Core contract

  • Model guesses remain inferred, not user facts. Faithful professional synthesis of stated actions needs no separate factual approval.
  • Register useful preparation/learning follow-ups with action propose and suggestion_reason; market validation and learning support the new direction without blocking the current resume.
  • Use the decision contract for actual target/preparation recommendations. Shared privacy and external-action rules remain in AGENTS.md.

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.