Menu
Extract plain UTF-8 text from local PDF files; pipeline input for summarize.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | PDF Extract |
| description | Extract plain UTF-8 text from local PDF files; pipeline input for summarize. |
| requires | {"bins":[],"env":[]} |
Use this skill whenever the user drops a PDF and wants its content read,
quoted, searched, or summarized. The extension decodes PDFs in pure Rust
(no pdftotext, no Python), returns plain text, and truncates to keep the
result within a safe LLM window.
summarize_textstatusNo arguments. Returns provider info, file-size limit, default char cap.
extract_textpath (string, required) — absolute or relative path to the PDF (≤ 25 MB)max_chars (integer, optional, 1..=1 000 000, default 200 000) — truncates outputReturns:
{
"path": "...",
"bytes": 12345,
"max_chars": 200000,
"truncated": false,
"char_count": 1200,
"total_char_count": 1200,
"text": "..."
}
max_chars: 50000 when chaining into summarize_text (summarize
rejects inputs > 60 000 chars).truncated: true, warn the user the summary is based on the first N
chars; offer to do a second pass on later pages with a different
max_chars + byte offset (not yet supported).-32602 on bad path → ask the user to confirm the absolute path.-32006 on extraction failure → likely a scanned PDF with no text
layer, or a corrupted file. Suggest an OCR tool (out of scope).Bounded auto-iteration for a prompt with explicit stop predicates.
Memory hygiene workflow to classify, deduplicate, and promote durable knowledge across local memory layers.
Bounded simplification pass for a file or hunk that preserves behavior while reducing complexity.
Turn a repeatable workflow into a reusable local SKILL.md with explicit steps, criteria, and safe defaults.
Bounded auto-debug loop for failing build/test commands with evidence-first diagnosis.
Safely update Nexo config files with read-before-write merges, schema-aware mapping, and reload/restart awareness.