XLSX
rvdbreemen/OTGW-firmware
Use this skill any time a spreadsheet file is the primary input or output.
Document intelligence: categorize, autofill forms, analyze contracts, scan receipts/invoices, analyze bank statements, parse resumes/CVs, scan IDs/passports (MRZ), summarize medical records, redact…
Install Doc Process
$ npx skills add LeoYeAI/openclaw-master-skills --skill doc-process -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills doc-process --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/doc-process .claude/skills/doc-process && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "doc-process" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/doc-process into .claude/skills/doc-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-process", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/doc-processType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill doc-process -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills doc-process --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/doc-process .agents/skills/doc-process && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "doc-process" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/doc-process into .agents/skills/doc-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-process", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill doc-process -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills doc-process --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/doc-process .cursor/skills/doc-process && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "doc-process" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/doc-process into .cursor/skills/doc-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-process", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/doc-process--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill doc-process -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills doc-process --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/doc-process .gemini/skills/doc-process && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "doc-process" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/doc-process into .gemini/skills/doc-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-process", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills doc-processInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill doc-process -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/doc-process .github/skills/doc-process && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "doc-process" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/doc-process into .github/skills/doc-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-process", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill doc-process -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills doc-process --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/doc-process .opencode/skills/doc-process && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "doc-process" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/doc-process into .opencode/skills/doc-process/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-process", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
doc-process- GitHub stars
- 2.2k
- Token cost
- ~5.2k tokens
- SKILL.md length
- 2,302 words
- Files
- 30 (incl. scripts, references)
- Skills in repo
- 1,215
- Repo updated
- First seen
- Licence
- MIT
At a glance
Document intelligence: categorize, autofill forms, analyze contracts, scan receipts/invoices, analyze bank statements, parse resumes/CVs, scan IDs/passports (MRZ), summarize medical records, redact…
- Works in 8 steps: Auto-Setup (run once on first use) → Identify the Mode → Read the Document → …
- Tasks that involve Forms and invoices
- SKILL.md covers Step 0 — Auto-Setup (run once…, Overview, How Features Are Implemented and Dependencies & Installation, plus 11 more sections
- Calls python, pip and bash
What it does
Doc Process is an agent skill from LeoYeAI/openclaw-master-skills. Document intelligence: categorize, autofill forms, analyze contracts, scan receipts/invoices, analyze bank statements, parse resumes/CVs, scan IDs/passports (MRZ), summarize medical records, redact PII (light/standard/full, 50+ rule types, global coverage), extract meeting minutes/action items, extract tables to CSV/JSON, translate documents, scan/dewarp document photos (edge detection, perspective correction, scan-quality output). Trigger: fill this form, autofill, review contract, red flags, scan receipt, log…
Its SKILL.md is about 5.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 31 other files, including scripts and reference files (for example `_meta.json`, `evals/evals.json` and `references/bank-statement-analyzer.md`).
It sits in Documents & Office, covering Forms and invoices, Contract review and Meeting notes and agendas. It works with Azure AI Document Intelligence and Python. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
When your agent uses it
- Tasks that involve Forms and invoices
- Tasks that involve Contract review
- Tasks that involve Meeting notes and agendas
Example prompts
- “/doc-process”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Glob
Workflow steps
8 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditBashGlob
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
pythonpipbashbrewapt
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Doc Process loads about 5.2k tokens when it runs, and up to ~43k if it reads all its reference files. Until then it costs about 201 tokens; SKILL.md has 2,302 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Read, Write, Edit, Bash, Glob
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 2,302 words, ~5,217 tokens.
Download SKILL.mdSave it as
.claude/skills/doc-process/SKILL.md (or your agent's skills folder). This skill also uses 29 other files; get the full folder from GitHub.- name
- doc-process
- description
- Document intelligence: categorize, autofill forms, analyze contracts, scan receipts/invoices, analyze bank statements, parse resumes/CVs, scan IDs/passports (MRZ), summarize medical records, redact PII (light/standard/full, 50+ rule types, global coverage), extract meeting minutes/action items, extract tables to CSV/JSON, translate documents, scan/dewarp document photos (edge detection, perspective correction, scan-quality output). Trigger: fill this form, autofill, review contract, red flags, scan receipt, log expense, bank statement, subscriptions, parse resume, scan passport, read id, lab report, redact, remove pii, anonymize, meeting minutes, action items, extract table, table to csv, translate, scan photo, make scanned, dewarp, correct perspective, what is this, analyze this.
- allowed-tools
- Read, Write, Edit, Bash, Glob
Doc-Process — Document Intelligence Skill
Step 0 — Auto-Setup (run once on first use)
Before invoking any script for the first time in a session, check whether the script dependencies are available. If any are missing, run the setup script automatically — no prompting needed:
bash skills/doc-process/setup.shThis installs all Python packages (pymupdf, Pillow, pytesseract, opencv-python-headless, numpy, img2pdf, pdfplumber, openai-whisper) and attempts to install system binaries (tesseract, ffmpeg) via brew or apt depending on the platform.
When to run Step 0:
- First time any script-assisted mode is used in a session
- After a fresh
clawhub install piyush-zinc/doc-process - If a script fails with
ModuleNotFoundErrororImportError
To install Python packages only (no system packages):
bash skills/doc-process/setup.sh --lightOr install directly from the skill's requirements file:
pip install -r skills/doc-process/requirements.txtNote:
openai-whisperdownloads its model (~140 MB) on first audio transcription — not at install time.
Overview
This skill handles all document-related tasks using Claude's native vision/language capabilities for reading and analysis, and Python scripts for file-output operations. Most modes require no installation — only the file-output scripts need third-party libraries.
How Features Are Implemented
| Feature | Implementation | External libraries |
|---|---|---|
| OCR / reading images | Claude built-in vision | None |
| MRZ decoding (passport/ID) | Claude reads MRZ visually, applies ICAO algorithm | None |
| PDF reading | Claude reads PDF text layer or visually | None |
| Form autofill | Claude reads form fields, outputs fill table | None |
| Contract analysis | Claude applies reference rule set | None |
| Receipt / invoice scanning | Claude reads image or PDF | None |
| Bank statement (PDF) | Claude reads PDF pages | None |
| Bank statement (CSV) | statement_parser.py — pure stdlib | None |
| Expense logging | expense_logger.py — pure stdlib | None |
| Bank report generation | report_generator.py — pure stdlib | None |
| Resume / CV parsing | Claude reads document | None |
| Medical summarizer | Claude reads document | None |
| Legal redaction (display) | Claude marks up output | None |
| Legal redaction (file output) | redactor.py | pymupdf (PDF); Pillow + pytesseract (image) |
| Meeting minutes (text/PDF) | Claude reads document | None |
| Translation | Claude's multilingual capabilities | None |
| Document categorizer | Claude reads first 1–2 pages (with consent gate) | None |
| Timeline logging | timeline_manager.py — pure stdlib | None |
| Table extraction (PDF) | table_extractor.py | pdfplumber |
| Audio transcription | audio_transcriber.py | openai-whisper + ffmpeg |
| Doc scan / perspective correction | doc_scanner.py | opencv-python-headless, numpy, Pillow; img2pdf optional |
Dependencies & Installation
No installation required for core functionality
Reading, analysis, form filling, contract review, receipt scanning, bank statement analysis (PDF), resume parsing, ID scanning, medical summarising, redaction markup, meeting minutes, and translation all run on Claude's built-in capabilities.
Optional — install only for file-output scripts
# PII redaction to PDF/image files (redactor.py)
pip install pymupdf>=1.23 # required for PDF redaction
pip install Pillow>=10.0 # required for image redaction
pip install pytesseract>=0.3 # required for image redaction (also: brew install tesseract)
# Document scanning / perspective correction (doc_scanner.py)
pip install opencv-python-headless>=4.9 numpy>=1.24 Pillow>=10.0
pip install img2pdf>=0.5 # optional — for PDF output; Pillow fallback used if absent
# Table extraction from PDFs (table_extractor.py)
pip install pdfplumber>=0.11
# Audio transcription (audio_transcriber.py)
# Also requires ffmpeg binary: brew install ffmpeg / apt install ffmpeg
pip install openai-whisper>=20231117All dependencies are also listed in requirements.txt at the repository root.
Binary dependencies
| Binary | Required by | Install |
|---|---|---|
tesseract | redactor.py (image mode) | brew install tesseract / apt install tesseract-ocr |
ffmpeg | audio_transcriber.py | brew install ffmpeg / apt install ffmpeg |
Network access
openai-whisper downloads model files (~140 MB) from OpenAI/HuggingFace servers on first run only. Cached at ~/.cache/whisper/. All other scripts are fully local after installation.
Script Reference
| Script | Dependencies | Purpose | Example |
|---|---|---|---|
redactor.py | pymupdf; Pillow + pytesseract (image mode) | PII redaction to file (PDF/image/text) | python scripts/redactor.py --file doc.pdf --mode full --log |
doc_scanner.py | opencv-python-headless, numpy, Pillow; img2pdf optional | Document scanning: edge detection, perspective correction, scan-quality output | python scripts/doc_scanner.py --input photo.jpg --output scanned.png --mode bw |
expense_logger.py | None | Add/list/edit/delete expense entries in CSV | python scripts/expense_logger.py add --date 2024-03-15 --merchant "Starbucks" --amount 13.12 --file expenses.csv |
statement_parser.py | None | Parse bank CSV export, categorize transactions | python scripts/statement_parser.py --file statement.csv --output categorized.json |
report_generator.py | None | Format categorized JSON into a markdown report | python scripts/report_generator.py --file categorized.json --type bank |
timeline_manager.py | None | Manage opt-in document processing timeline | python scripts/timeline_manager.py show |
audio_transcriber.py | openai-whisper, ffmpeg | Transcribe audio files to text | python scripts/audio_transcriber.py --file meeting.mp3 --output transcript.txt |
table_extractor.py | pdfplumber | Extract tables from PDFs to CSV or JSON | python scripts/table_extractor.py --file document.pdf --output data.csv |
All scripts import only what they declare. Scripts with no declared deps use Python stdlib only. You can verify any script: "show me the source of [script name]".
Script Import Verification
| Script | Stdlib imports | Third-party | Network |
|---|---|---|---|
timeline_manager.py | argparse, json, sys, datetime, pathlib, uuid, collections | None | Never |
redactor.py | argparse, re, sys, pathlib, dataclasses | pymupdf (PDF); Pillow + pytesseract (image) | Never |
doc_scanner.py | argparse, json, sys, time, pathlib | opencv-python-headless, numpy, Pillow; img2pdf optional | Never |
expense_logger.py | argparse, csv, json, sys, pathlib | None | Never |
statement_parser.py | argparse, csv, json, re, sys, collections, datetime, pathlib | None | Never |
report_generator.py | argparse, json, sys, collections, pathlib | None | Never |
utils.py | re, unicodedata, datetime, pathlib | None | Never |
audio_transcriber.py | argparse, sys, pathlib | openai-whisper | First-run model download only |
table_extractor.py | argparse, csv, io, json, sys, pathlib | pdfplumber | Never |
Privacy & Data Handling
| Aspect | Policy |
|---|---|
| Document content | Read locally within this session only. Not stored, indexed, or transmitted. |
| Personal data for form autofill | Used only to complete the current form. Not written to any file. Not retained after session. |
| Timeline log | Opt-in only. Confirmed by user before any entry is written. Contains no raw document content — only category-level summaries. |
| Redacted output files | Written only to a path the user explicitly confirms. |
| Audio transcripts | Written to a local file the user specifies. Model download on first Whisper use only. |
| No telemetry | This skill has no analytics, usage reporting, or network calls beyond what is listed above. |
Step 1 — Identify the Mode
Explicit intent → go directly to the matching mode
| Mode | User intent signals | Typical file types |
|---|---|---|
| Document Categorizer | "process this", "what is this?", "analyze this", "help with this", no clear intent | Any |
| Form Autofill | fill, autofill, fill out, complete this form | PDF form, image, screenshot |
| Contract Analyzer | review, summarize, contract, agreement, risks, red flags, NDA, lease | PDF, text |
| Receipt Scanner | receipt, invoice, log expense, scan this bill | Photo, image, PDF |
| Bank Statement Analyzer | bank statement, transactions, subscriptions, categorize spending | PDF, CSV |
| Resume / CV Parser | parse resume, extract cv, what's on this resume, scan resume | PDF, image, text |
| ID & Passport Scanner | scan id, read passport, extract from id card, scan my passport | Photo, image, PDF |
| Medical Summarizer | lab report, blood test, prescription, discharge summary, medical results | PDF, image, text |
| Legal Redactor | redact, remove pii, anonymize, censor sensitive info | PDF, text, image |
| Meeting Minutes | meeting minutes, action items, summarize meeting, transcribe meeting | Text, PDF, image, audio |
| Table Extractor | extract table, table to csv, get data from pdf, table to json | PDF, image, text |
| Document Translator | translate this, translate to [language], document translation | Any |
| Document Timeline | show my timeline, document history, what have I processed, save timeline | — |
| Doc Scan | scan this photo, make this look scanned, correct perspective, dewarp, clean this photo, digitize this, straighten this | Photo, image |
Ambiguous intent → Document Categorizer (with consent gate)
If the user uploads a file without a clear mode signal, do not read it yet. Ask:
"I can classify this document automatically to suggest the best mode — that requires me to read the first 1–2 pages. Or you can choose directly:
Option Best for Form Autofill Forms with fill-in fields Contract Analyzer Agreements, NDAs, leases Receipt Scanner Receipts, invoices Bank Statement Analyzer Bank/credit card statements Resume Parser CVs, resumes ID Scanner Passports, IDs, driver's licenses Medical Summarizer Lab reports, prescriptions Legal Redactor Any document with PII to remove Meeting Minutes Notes or recordings Table Extractor Documents with data tables Translator Non-English documents Doc Scan Document photo needing perspective correction Shall I classify it, or which mode would you like?"
Only read the document after the user confirms.
Step 2 — Read the Document
Use the Read tool on the uploaded file. For images, read them visually. For PDFs over 10 pages, read in page ranges.
For audio files (Meeting Minutes mode only): confirm before running — this requires openai-whisper and downloads a model on first run:
"Transcribing this audio requires the
openai-whisperlibrary. On first use it downloads a model file (~140 MB). Is that OK?"
If yes:
python skills/doc-process/scripts/audio_transcriber.py --file <path> --output transcript.txtIf no: ask if the user can provide a text transcript.
For document photos (Doc Scan mode): read the image visually first to assess quality and detect the document type before running the scanner script.
Step 3 — Execute the Mode
Load and follow the matching reference file in full:
| Mode | Reference file |
|---|---|
| Document Categorizer | references/document-categorizer.md |
| Form Autofill | references/form-autofill.md |
| Contract Analyzer | references/contract-analyzer.md |
| Receipt Scanner | references/receipt-scanner.md |
| Bank Statement Analyzer | references/bank-statement-analyzer.md |
| Resume / CV Parser | references/resume-parser.md |
| ID & Passport Scanner | references/id-scanner.md |
| Medical Summarizer | references/medical-summarizer.md |
| Legal Redactor | references/legal-redactor.md |
| Meeting Minutes | references/meeting-minutes.md |
| Table Extractor | references/table-extractor.md |
| Document Translator | references/document-translator.md |
| Document Timeline | references/document-timeline.md |
| Doc Scan | references/doc-scan.md |
Show full SKILL.md (981 more words)Show less
Step 4 — Redactor: PII Rule Coverage
The redactor.py script covers the following PII categories across 50+ rule types for global document types (bank statements, contracts, medical records, invoices, share-purchase agreements, government forms, and more).
Category 1 — Personal Identifiers (standard + light mode)
| Rule | Examples |
|---|---|
| SSN (US) | 123-45-6789 |
| SIN (Canada) | 123-456-789 |
| UK National Insurance Number | AB 12 34 56 C |
| Australian TFN | 123 456 789 |
| Australian Medicare number | 1234 56789 1 |
| Indian Aadhaar | 1234 5678 9012 |
| Passport number | A12345678 |
| Driver's license | keyword-anchored |
| UK NHS number | 943 476 5919 |
| National / voter ID | keyword-anchored |
| Vehicle VIN | keyword-anchored 17-char code |
| NRIC (Singapore) | S1234567A |
| Medical record (MRN) | keyword-anchored |
| Indian PAN | AABCW6386P |
| Email address | any@domain.com |
| Phone number | all international formats; date/reference false-positives suppressed |
| Street address | BLK/BLOCK/FLAT/UNIT/APT prefix + number + street name + type (Street, Ave, Rd, Hill, Close, Quay, Park, etc.) |
| Unit / apartment number | #02-01, Unit 3B, Apt 4C, Flat 12 |
| P.O. Box | PO Box 1234 |
| US ZIP / CA postal | 10001, M5V 3A8 |
| UK postcode | SW1A 2AA |
| International 6-digit postal | Singapore 229572, Bangalore 560067 |
| IPv4 address | 192.168.1.1 |
| MAC address | AA:BB:CC:DD:EE:FF |
| Date of birth | keyword + numeric/month-name formats |
| Age | "Age: 34" |
| Labeled name (50+ field keywords) | Bill To, Shipper, Attention, Buyer, Seller, Patient, Employee, Plaintiff, Trustee, Shareholder, Director, Tenant, Lender, Beneficiary, etc. |
| Honorific prefix + name | Mr./Mrs./Ms./Dr./Prof./Rev./Hon./Mx. + name |
Category 2 — Financial Data (standard + full mode)
| Rule | Examples |
|---|---|
| Credit / debit card number | 4111 1111 1111 1111 |
| Card CVV | CVV: 123 |
| Card expiry | 03/26 |
| Bank account number | keyword-anchored |
| IBAN | IBAN country-code validated (GB, DE, FR, etc.) |
| ABA / routing number | "Routing No." and "ABA No." |
| UK Sort code | 20-00-00 |
| Australian BSB | 063-000 |
| Indian IFSC code | HDFC0000001 |
| SWIFT / BIC code | allows space in code (e.g. CHAS US33) |
| Salary / compensation | salary, CTC, gross/net pay, take-home, remuneration |
| Credit score | keyword-anchored |
| Loan / mortgage amount | keyword-anchored |
| Tax figures | AGI, taxable income, tax paid |
| Net worth / total assets | keyword-anchored |
| Cryptocurrency wallet | Bitcoin, Ethereum |
Category 3 — Sensitive / Protected (full mode only)
HIV/AIDS status, blood type, mental health diagnoses (expanded), reproductive health, substance use history, sexual orientation / gender identity, disability, criminal record, genetic information, immigration status, minor's name, attorney–client privilege, trade secrets.
Redaction modes
| Flag | Categories | Use case |
|---|---|---|
--mode light | Cat 1 only | Sharing docs where financial details can remain |
--mode standard | Cat 1 + 2 (default) | General privacy protection |
--mode full | Cat 1 + 2 + 3 | Legal filings, healthcare, immigration, HR |
--custom REGEX | Cat 0 + selected mode | Domain-specific or proprietary terms |
How PDF redaction works
- Word bounding boxes are extracted from the PDF layout engine
- PII is detected using a single-pass, non-overlapping regex engine
- Matched spans are mapped back to word bounding boxes
- PyMuPDF redaction annotations (solid black fill) are placed on the exact word rects
apply_redactions()burns the black fills in and removes the underlying text data from the content stream — redacted text cannot be copy-pasted or extracted- The file is saved incrementally — every non-redacted element (fonts, images, vector graphics, metadata) is left completely untouched
- The original file is never modified; output is always a separate copy
Step 5 — Doc Scan: How It Works
The doc_scanner.py script converts a document photo into a professional scan in 7 steps:
- Multi-strategy edge detection — tries three approaches in order: (A) Canny on greyscale; (B) Morphological gradient; (C) Colour/brightness threshold. Stops at first success.
- Sub-pixel corner refinement —
cv2.cornerSubPixmakes the four corner points accurate to sub-pixel level for the most precise warp. - Perspective warp — four-point transform using Lanczos interpolation flattens the document to a perfect rectangle.
- Shadow removal — per-channel background estimation + normalisation removes cast shadows and uneven lighting without affecting text.
- Scan-quality enhancement — mode-specific: BW = adaptive threshold (block size auto-scaled to resolution) + stroke repair + denoising; Gray = auto-levels + CLAHE + unsharp mask; Color = white-balance + CLAHE + sharpening.
- Scanner border — 8 px white border simulates scanner bed edge.
- DPI-tagged output — saved with embedded DPI metadata (default 300 DPI, print quality).
When auto-detection fails
If the script reports "corners_detected": false:
- Offer manual corner hints: ask the user where the four corners of the document are approximately
- Use
--no-warpto at least apply enhancement without perspective correction - Provide photography tips (see
references/doc-scan.mdStep 8)
Step 6 — Document Timeline (Opt-In)
Off by default. After completing the first document task in a session, ask once:
"Would you like me to keep a processing log for this session? It records document type, filename, and a category-level summary (no raw content, no personal data) to
~/.doc-process-timeline.jsonon your local machine. Entirely optional — yes or no."
- Yes → confirm "Timeline logging is on." Log current and subsequent documents. Announce each with "Logged to your timeline."
- No → confirm "No log will be kept." Do not run any timeline script. Do not ask again this session.
- No response / unsure → treat as No.
Summary rules (strictly enforced): the --summary argument must never contain names, ID numbers, dates of birth, addresses, account numbers, card numbers, medical values, or any data that could identify a person. Category-level descriptions only.
Step 7 — Deliver Output
Present output in clean tables with section headers as specified in each reference file. Always end with an action prompt relevant to the mode. For Doc Scan, always offer to continue processing the scanned output.
General Principles
- Never hallucinate field values. Unknown values →
[MISSING]or[UNREADABLE]. - Flag risks conservatively — when in doubt, include it.
- Keep summaries scannable with tables and bullets.
- Do not echo sensitive data beyond what is necessary for the immediate task.
- Always include relevant disclaimers (medical, legal, privacy) where required by the reference guide.
- Timeline is opt-in per session. Never log without confirmed consent.
- Personal data for form autofill is session-only. Never write it to a file.
- Before running any script with third-party deps, run
bash skills/doc-process/setup.shautomatically if deps are not yet installed (see Step 0). No need to ask — the setup script is safe and idempotent. - Categorize before asking — but only after confirming the user wants auto-classification.
- For Doc Scan: always assess the image visually first; never process non-document images.
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 29 other files (scripts, references) in skills/doc-process of LeoYeAI/openclaw-master-skills.
- SKILL.md
- _meta.json
- evals/evals.json
- references/bank-statement-analyzer.md
- references/contract-analyzer.md
- references/doc-scan.md
- references/document-categorizer.md
- references/document-timeline.md
- references/document-translator.md
- references/form-autofill.md
- references/id-scanner.md
- references/legal-redactor.md
- references/medical-summarizer.md
- references/meeting-minutes.md
- references/receipt-scanner.md
- references/resume-parser.md
- references/table-extractor.md
- requirements.txt
- scripts
- … and 11 more
Open the folder on GitHubat commit e5199b5
Compare with similar skills
Doc Process next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Doc Process this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.2k | Automated safety check: Notes | MIT | |
| XLSXrvdbreemen/OTGW-firmware | 207 | 35 repos | ~2.9k | Automated safety check: Pass | Proprietary | |
| PDF ToolkitXiaomiMiMo/MiMo-Code | 14k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| PDF Generation, Forms and Extractionpipeshub-ai/pipeshub-ai | 3.8k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Markdown Exporterbowenliang123/markdown-exporter | 271 | 1 repos | ~5.3k | Automated safety check: Pass | Apache-2.0 | |
| Nsight Graphics AnalyzerLuna5ama/Alpha-Piscium | 156 | — | ~4.7k | Automated safety check: Pass | GPL-3.0 |
Similar skills
PDF Toolkit
XiaomiMiMo/MiMo-Code
Reads, transforms, composes and fills PDFs with Python scripts for extraction, merging, watermarking, encryption, OCR and form filling.
PDF Generation, Forms and Extraction
pipeshub-ai/pipeshub-ai
Picks the right library for generating a new PDF, filling an existing PDF form, or extracting text and tables, defaulting to Node where possible.
Markdown Exporter
bowenliang123/markdown-exporter
Convert Markdown text to DOCX, PPTX, XLSX, PDF, PNG, SVG, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files.
Nsight Graphics Analyzer
Luna5ama/Alpha-Piscium
Drive NVIDIA Nsight Graphics 2026.1+ from the command line for GPU performance analysis, frame capture, frame trace inspection, draw-call inspection, NVTX/D3DPERF stage timing, replay metadata…
Kimi PDF
thvroyal/kimi-skills
Professional PDF solution. An agent skill from thvroyal/kimi-skills.
More from LeoYeAI/openclaw-master-skills
All 1,215 skills in this repoDevOps Pipeline Management
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
Feishu Document Collaboration
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
Files Memory System
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
GEO-Claw AI Visibility Agent
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
Google Workspace CLI
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
HealthFit Health Advisors
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Related
Works with
Categories
Questions about Doc Process
What does Doc Process do?
Document intelligence: categorize, autofill forms, analyze contracts, scan receipts/invoices, analyze bank statements, parse resumes/CVs, scan IDs/passports (MRZ), summarize medical records, redact…. Doc Process is an agent skill from LeoYeAI/openclaw-master-skills. Document intelligence: categorize, autofill forms, analyze contracts, scan receipts/invoices, analyze bank statements, parse resumes/CVs, scan IDs/passports (MRZ), summarize medical records, redact PII (light/standard/full, 50+ rule types, global coverage), extract meeting minutes/action items, extract tables to CSV/JSON, translate documents, scan/dewarp document photos (edge detection, perspective correction, scan-quality output).
When should I use Doc Process?
Doc Process fits situations like: tasks that involve Forms and invoices; tasks that involve Contract review; tasks that involve Meeting notes and agendas.
How do I install Doc Process in Claude Code?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill doc-process -a claude-code`. Or copy the skill folder (skills/doc-process in LeoYeAI/openclaw-master-skills) into .claude/skills/doc-process in your project. Claude Code loads it when a task matches its description.
How do I install Doc Process in Codex?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill doc-process -a codex`. Or copy the skill folder (skills/doc-process in LeoYeAI/openclaw-master-skills) into .agents/skills/doc-process in your project. Codex loads it when a task matches its description.
Can I use Doc Process in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill doc-process -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/doc-process, .gemini/skills/doc-process, .github/skills/doc-process and .opencode/skills/doc-process in your project.
What does Doc Process need to run?
Going by SKILL.md and its folder, Doc Process needs the command-line tools its instructions call (python, pip, bash, brew and apt). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Glob.
Does Doc Process access the network?
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Doc Process safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Doc Process use?
Doc Process is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Doc Process use?
About 5.2k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 38k tokens, read only when the agent opens those files.
What are the alternatives to Doc Process?
Skills that share tags, products or a category with Doc Process: XLSX (rvdbreemen/OTGW-firmware, 207 stars), PDF Toolkit (XiaomiMiMo/MiMo-Code, 14k stars), PDF Generation, Forms and Extraction (pipeshub-ai/pipeshub-ai, 3.8k stars) and Markdown Exporter (bowenliang123/markdown-exporter, 271 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Doc Process?
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,158 GitHub stars. The repository holds 1,215 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.