cv

name	cv
description	Generate, adapt, and update CVs from structured data stored in cv_data.json. Triggers: "cv" | "generate cv" | "generate my cv" | "adapt cv" | "update cv" | "tailor cv" | "make my resume" | "update my resume" | "write my cv" | "adapt my resume for" | "tailor my cv for".
version	0.1.0
allowed-tools	Read, Edit, Write, Bash, Glob, Grep

CV

Generate professional CVs from structured data. Adapt them for specific job postings. Update the master data file.

Let: V := ~/.roxabi-vault/cv/ — plugin data root D := V/cv_data.json — master CV data G := V/generated/ — generated CVs A := V/adapted/ — job-adapted CVs T := /templates/ — Jinja2 templates S := /scripts/generate_cv.py — generation script C := ~/.roxabi-vault/config/cv.json — plugin config

Self-Check

1. Verify D:

test -f ~/.roxabi-vault/cv/cv_data.json && echo "OK" || echo "MISSING"

¬D → "No cv_data.json found. Run /cv-init to set up the CV plugin." Halt.

2. Verify Jinja2:

python3 -c "import jinja2" 2>/dev/null && echo "OK" || echo "MISSING"

¬jinja2 → "Jinja2 is required. Install with: pip install jinja2". Halt.

Phase 1 — Determine Intent

Parse $ARGUMENTS:

Intent	Signal	Action
Generate	"generate", "create", "build", no args	Generate CV from D
Adapt	"adapt", "tailor", "for [job]", URL or job description	Adapt CV for role
Update	"update", "add", "change", "edit"	Modify D

Ambiguous → present choice Generate | Adapt | Update

Phase 2 — Generate

1. Read D. Determine format (md/html/all) and language (fr/en/all) from args or C. Default: C values.
2. Template: default cv_template; use cv_template_rich if D has experiences key with title/dates/sections fields, or user requests it.
3. Run:

python3 <plugin>/scripts/generate_cv.py --data ~/.roxabi-vault/cv/cv_data.json --lang <lang> --format <format> [--template cv_template_rich]

--lang all → one file per language (cv_fr.md, cv_en.md); --lang fr → cv.md (no suffix). --format all → md + html. Both experience/experiences keys accepted (aliased). Report output path(s).

Phase 3 — Adapt

1. Read D. Gather job posting from $ARGUMENTS (URL or text); → ask userif missing: "Provide the job posting URL or paste the job description."
2. Analyze posting: extract requirements, skills, keywords.
3. Adapt CV: reorder experience → relevant roles; emphasize matching skills; adjust summary → target role. ¬fabricate experience.
4. Write adapted data + generate (tempfile per ${CLAUDE_PLUGIN_ROOT}/../shared/references/tempfile-convention.md):

COMPANY_SAFE=$(echo "$COMPANY" | tr -c '[:alnum:]-' '-' | head -c 40)
TMPDIR=$(mktemp -d -t "cv-adapt-${COMPANY_SAFE}-XXXXXX")
trap 'rm -rf "$TMPDIR"' EXIT
ADAPTED="$TMPDIR/adapted.json"
# write adapted JSON → "$ADAPTED"
python3 <plugin>/scripts/generate_cv.py --data "$ADAPTED" --output ~/.roxabi-vault/cv/adapted/cv_<company>_<date>.<format> --format <format>

5. Report changes + output path.

Phase 4 — Update

Read D → present structure → present choice Experience | Skills | Education | Personal info → apply changes → validate JSON.

Vault Integration (Optional)

test -f ~/.roxabi-vault/vault.db && echo "VAULT_AVAILABLE" || echo "NO_VAULT"

VAULT_AVAILABLE → after generate/adapt: index output file with category=cv + type tag.

$ARGUMENTS