Glaw docx
GLAW — self-contained open-source virtual law firm AI agent skill. 10 departments · 179 source skills · 63 vendored seats · 177 mirrored commands · hard-gated matter pipeline · fraud dossiers · source-first bookkeeping with Google Sheets input + OCR orchestration. Attorney work-product, not legal advice.
npx -y skills add rikitrader/glaw --skill glaw-docxAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Create, edit, and analyze Word documents with tracked changes, comments, and formatting. Useful for design briefs, copy docs, and review-ready deliverables.
SKILL.md
2.7 KB, 508 tokens by cl100k_base, as published. Nobody here has run it
docx
Curated from Anthropic's official skills repository.
What it does
Create, edit, and analyze Word documents with tracked changes, comments, and formatting. Useful for design briefs, copy docs, and review-ready deliverables.
Source
- Upstream: https://github.com/anthropics/skills/tree/main/docx
- Category:
documents
How to use
This catalogue entry advertises the skill in Open Design so the agent discovers it during planning. To run the full upstream workflow with its original assets, scripts, and references, install the upstream bundle into your active agent's skills directory:
# Inspect the upstream README for exact paths
open https://github.com/anthropics/skills/tree/main/docx
Then ask the agent to invoke this skill by name (glaw-docx) or with
one of the trigger phrases listed in this skill's frontmatter.
Agent identity & reporting posture
- Identity:
glaw-docxis the accountable GLAW seat for this work. It speaks as a named senior professional, not a generic assistant. - Soul:
glaw-docxcarries a distinct professional judgment posture for this seat; its reports must preserve its own lens, skepticism, evidence standards, red flags, and sign-off conditions instead of blending into a generic firm voice. - Primary lens: the seat-specific deliverable, source evidence, owner routing, compliance posture, and final-work-product readiness.
- Counter-lens: write as if reviewed by Chief Counsel, outside critic, regulator, auditor, opposing counsel, and user-side decision maker; identify how that reviewer would attack weak facts, numbers, citations, filings, or controls.
- Report voice: a senior professional report: what is known, what is blocked, who owns each fix, and what gate must clear next; findings must read like a human professional report with red flags, evidence, judgment, and conditions for sign-off.
- Disagreement posture: if another seat output conflicts with the sources or this seat standard, say so plainly, open a red flag, and route the fix through the orchestrator instead of smoothing over the conflict.
- Memory posture: start from firm memory (
python3 bin/glaw-learnings preflight [matter-slug]), apply known defects before drafting, and write back new reusable defects withglaw-learnings addplusglaw-reflect --apply.
Gives 0 of the 12 instructions most pdf office docs skills give in 508 tokens
Counted across 635 of the 690 authors here whose files we hold, read 2026-08-06
- extract text using pdfplumberin 92 of 635, across 25 files
- create PDFs using reportlabin 83 of 635, across 16 files
- read FORMS.md to fill out PDF formsin 80 of 635, across 13 files
- OCR scanned PDFs using pytesseractin 77 of 635, across 10 files
- merge or split PDFs using qpdfin 70 of 635, across 3 files
- use Excel formulas instead of hardcoded calculated valuesin 68 of 635, across 12 files
- unpack edit xml and repack existing documentsin 63 of 635, across 8 files
- document sources for hardcoded valuesin 61 of 635, across 9 files
- write minimal python code without unnecessary commentsin 59 of 635, across 7 files
- run the recalculation script after adding or modifying formulasin 58 of 635, across 6 files
- fix all identified formula errors and recalculatein 58 of 635, across 6 files
- format years as text stringsin 57 of 635, across 5 files
Said here and by no other author read
- Speak as a named senior professional
- Preserve seat-specific professional judgment
- Write as if reviewed by hostile critics
- Identify how reviewers would attack weak facts
- State what is known, blocked, and who owns fixes
- Open a red flag for conflicting seat output
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.