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 evoelsewhere/evoflux --skill docx-officialgit clone --depth 1 https://github.com/evoelsewhere/evofluxWrote 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/evoelsewhere/evoflux/docx-official)<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/docx-official"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/docx-official/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/evoelsewhere/evoflux/docx-official"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/docx-official.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 | $0.00124 | $0.02835 |
| Opus 5.5 | $0.00050 | $0.01134 |
| Sonnet 5.5 | $0.00025 | $0.00567 |
| Haiku 4.5 | $0.00012 | $0.00283 |
Grade A, and why
docx-official 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 22d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DOCX Skill
An Apache-2.0 toolkit for producing, editing, and reading Microsoft Word (.docx) files, written against the public ECMA-376 / ISO/IEC 29500 specification. Runtime libraries: python-docx (MIT) and lxml (BSD-3-Clause). LibreOffice (soffice) is an optional external binary.
Pipeline
Run these phases in order. Two are gates: do not pass a gate on your own judgement.
Phase 0 Read the source and the workspace
Phase 1 Settle the brief <- ask once, bounded
Phase 2 Heading tree + style <- GATE: user approves before drafting
Phase 3 Draft
Phase 4 Verify and repair <- loop until it passes
Phase 5 Hand off
Phase 0 — Read. Read the source, and look for a template, an earlier document of the same kind, or a style guide in the workspace. That reading is what tells you which questions are still open.
Phase 1 — Settle the brief. Reader, purpose, length, and register decide
what the document is. Take from context whatever context answers, then ask
about the rest in one ask_user call — at most three questions, options with
a marked recommendation. Skip this phase for an edit, a template fill, or an
explicit brief. Read interview.md for what to ask, what to
answer yourself, and what the Phase 2 plan must contain.
Phase 2 — Heading tree and style, then stop. Write the heading tree, one line per section stating what it must establish, the style basis, your assumptions, and every fact the material does not support. Put it in front of the user and wait. Rewriting an outline costs a sentence.
Phase 3 — Draft. Write inside the approved tree using named styles, not direct formatting. Do not add sections the plan does not contain.
Phase 4 — Verify and repair. Run the QA checklist and document_preview,
fix what they report, run them again.
Phase 5 — Hand off. File path, style basis, the checks that actually ran, and every placeholder still open.
What ships with it
13 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.
- create.md 16 KB
- edit.md 11 KB
- interview.md 3.0 KB
- LICENSE 1.3 KB
- read.md 9.0 KB
- scripts/annotate.py 10 KB runs code
- scripts/assemble.py 5.4 KB runs code
- scripts/audit.py 5.7 KB runs code
- scripts/explode.py 4.4 KB runs code
- scripts/extract_text.py 7.2 KB runs code
- scripts/render_pdf.py 3.2 KB runs code
- scripts/resolve_revisions.py 6.6 KB runs code
- scripts/transcode.py 9.0 KB runs code
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.
- 22d ago Changed · +3 lines · +24 tokens per session 3ac827cecfeb
- 1mo ago First seen · 193 lines · 100 tokens per session scan A 500a11cc860e
docx-official is a skill published in the GitHub repository evoelsewhere/evoflux (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 124 tokens to every session and 2,835 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-06.
Other skills, from other repositories
tdoc-orchestrator
A workflow coordinator for creating and formatting documents, then converting HTML documents into Word files. It identifies the user's document task and sends each stage to the appropriate specialist.
Spreadsheets
Create, edit, analyze, and verify standalone spreadsheet files or Google Sheets-ready workbooks, including .xlsx, .xls, .csv, and .tsv. Do not use for live controlling Microsoft Excel app or a live Excel session.
tencent-docs-sheet-generation
A tool for creating a new Excel workbook (.xlsx) from written requirements or reference PDF, Word, or presentation files. It is for starting without an existing spreadsheet file.
doc-typeset
A document formatter that turns text and design settings into complete, styled HTML. It includes templates for contracts, academic papers, official documents, business reports, meeting notes, research reports, and annual reports.
html-to-docx
A converter that turns HTML into an editable Microsoft Word document (.docx). It maps common HTML structure and styles, and can include images, tables, a table of contents, headers, and footers.
tencent-local-office-edit
A local editing skill for opening, changing, creating, and saving Microsoft Office and WPS documents, spreadsheets, and presentations through a local editor service. It supports specified document formats but does not execute macros or edit PDFs.