Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add leopu00/job-hunter-team --skill parse-cvgit clone --depth 1 https://github.com/leopu00/job-hunter-teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/leopu00/job-hunter-team/parse-cv)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/parse-cv"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/parse-cv/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/parse-cv"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/parse-cv.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00136 | $0.01719 |
| Opus 5 | $0.00068 | $0.00860 |
| Sonnet 5 | $0.00027 | $0.00344 |
| Haiku 4.5 | $0.00014 | $0.00172 |
Grade A, and why
parse-cv scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
parse-cv — text extraction da file caricato dall'utente
L'utente carica il suo CV via Telegram (o web drop-zone). L'Assistente
deve estrarre i dati strutturati (nome, ruolo, skill, esperienze) per
popolare $JHT_HOME/profile/candidate_profile.yml.
Senza pre-process: il LLM riceve il PDF binario via Read tool e fa il parsing direttamente. Funziona ma:
- Costa tanti token (un CV 2 pagine ≈ 3-5k token solo per il file)
- Risultati variabili su PDF scansionati / formati non-standard
- Errore silenzioso su .pages/.numbers (formati Apple non leggibili)
Con pre-process (questa skill): pdftotext/pandoc estraggono il testo plain in 50-200ms, il LLM riceve solo il testo (500-2000 token). Cinque-dieci volte meno token, parsing più affidabile.
Quando lanciarla
L'Assistente chiama parse-cv:
- Su ogni nuovo file in
$JHT_HOME/profile/sources/con estensione.pdf .docx .doc .odt .rtf .txt - NON sulle immagini (
.jpg .jpeg .png .heic .webp) — quelle le legge direttamente via vision multimodal del LLM - NON su file >5 MB (probabilmente non sono CV — l'Assistente chiede chiarimento)
Strumenti disponibili nel container
Già installati (verifica con command -v):
pdftotext(viapoppler-utils) — PDF → textpandoc— docx/odt/rtf/html → text/markdownfile— detect MIME type- NON disponibile:
tesseract(OCR),unrtf— per scansioni a bassa qualità il LLM cade su vision multimodal o chiede retry all'utente
Procedura
SRC="$1" # path al file in profile/sources/
[ -f "$SRC" ] || { echo "ERROR: file non trovato: $SRC"; exit 2; }
# 1. Detect MIME
MIME="$(file -b --mime-type "$SRC")"
# 2. Size check (5 MB limit)
SIZE=$(stat -c%s "$SRC" 2>/dev/null || stat -f%z "$SRC")
if [ "$SIZE" -gt 5242880 ]; then
echo "ERROR: file >5MB ($SIZE bytes), skip parse"
exit 3
fi
# 3. Estrazione per formato
case "$MIME" in
application/pdf)
# PDF: prova pdftotext (preserve layout per CV tabellari)
OUT="$(pdftotext -layout -nopgbrk "$SRC" - 2>/dev/null)"
if [ -z "$OUT" ] || [ "${#OUT}" -lt 50 ]; then
# Probabile PDF scansione (immagini, no text layer)
echo "ERROR: PDF text layer vuoto (probabile scansione). Usa vision multimodal o chiedi retry all'utente."
exit 4
fi
;;
application/vnd.openxmlformats-officedocument.wordprocessingml.document|\
application/msword|\
application/vnd.oasis.opendocument.text|\
application/rtf|\
text/rtf)
# Word/ODT/RTF: pandoc → plain text
OUT="$(pandoc -f auto -t plain --wrap=none "$SRC" 2>/dev/null)"
if [ -z "$OUT" ]; then
echo "ERROR: pandoc non riesce a estrarre testo da $SRC ($MIME)"
exit 5
fi
;;
text/plain|text/markdown)
OUT="$(cat "$SRC")"
;;
*)
echo "ERROR: MIME type non supportato: $MIME"
echo " Formati supportati: pdf, docx, doc, odt, rtf, txt, md"
echo " Per immagini usa vision multimodal direttamente."
exit 6
;;
esac
# 4. Print estratto
echo "$OUT"
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 140 lines · 136 tokens per session scan A f36bb8d60819
parse-cv is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 136 tokens to every session and 1,719 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
recipe-bulk-download-folder
List and download all files from a Google Drive folder.
markitdown
Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
cli-anything-wps
A command-line tool that controls WPS Office on Windows, including Writer, Calc, and Impress. It can also build presentations from structured JSON data and export them as PowerPoint and PDF files.
llm-document-extraction
Extract structured data from construction documents using LLMs. Process RFIs, submittals, contracts, specifications. Convert unstructured PDFs to structured JSON/Excel.
docutranslate
Use when translating documents locally via LLM — PDF, Word, Excel, Markdown, SRT subtitles with format preservation. DocuTranslate: LLM-powered multi-format local file translation tool with MCP server support.
freehire-tailor-cv
Use when reframing someone's CV toward a specific vacancy through freehire — reading the fit analysis for a tailored copy, fetching or editing the CV document by path, rendering the ATS PDF, or deciding what may and may not be written into a CV. Carries the evidence rule: anything stating what the candidate DID needs…