agentleFS
Miracle-AlignerMiracle-Aligner/job-search-hq/.claude/skills/ingest-cv/SKILL.md

ingest-cv

Skill1 starsChanged 5 months agoMITView on GitHub

Use when the user wants to import a CV/résumé into Job Search HQ so it can drive scoring and CV-tailoring. Triggers: /ingest-cv, "ingest my CV", "parse my resume", "import my CV", "read my CV in profile/cv". Parses PDF/DOCX/Markdown CV files in profile/cv/ (gitignored) into structured CV data linked from profile/profile.json.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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:

    Keep a concise structured digest per variant (don't dump the whole CV) so assessment skills can reference concrete evidence (projects, …

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill 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
SKILL.md

ingest-cv

Turn a real CV file into structured data the assessment skills can use.

Input

CV files live in profile/cv/ (gitignored; only .gitkeep + example-cv.md are tracked). The user drops Backend-CV.pdf, Voice-CV.docx, etc. there. If the folder is empty, ask them to add a file (or point you at a path) first.

Parse

  • PDF → use the pdf skill to extract text (and OCR if scanned).
  • DOCX → use the docx skill.
  • Markdown / txt → read directly.

Extract: summary line, experience (company, title, dates, 2–4 impact bullets each), education, skills/stack, and anything that maps to a profile axis (years, seniority signals).

Link it

For each CV, add/update an entry in profile/profile.json cvVariants[]:

{ "key": "VOICE", "label": "ASR/TTS / voice-bot roles", "file": "profile/cv/Voice-CV.pdf" }

Keep a concise structured digest per variant (don't dump the whole CV) so assessment skills can reference concrete evidence (projects, metrics) when scoring tech/level and when tailoring.

How assessment uses it

/add-vacancy and /cover-letter read profile/candidate.md and the CV digests to:

  • score tech/level against real evidence, not just self-reported strengths;
  • pick the right CV variant and propose concrete, evidence-backed changes.

scripts/score.py stays pure rubric math — CV influence lives in the skill's judgement, not the script.

Finish

Save profile/profile.json (gitignored). Confirm which variants are now available.

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.