Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TasiTech/tasi-harnessnpx agentmods add skills/tasitech/tasi-harness/docxWrote 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/tasitech/tasi-harness/docx)<a href="https://agentmods.dev/skills/tasitech/tasi-harness/docx"><img src="https://agentmods.dev/badge/skills/tasitech/tasi-harness/docx.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00077 | $0.04020 |
| Opus 5 | $0.00039 | $0.02010 |
| Sonnet 5 | $0.00015 | $0.00804 |
| Haiku 4.5 | $0.00008 | $0.00402 |
Grade B, and why
docx scanned grade B with 1 finding 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **pandoc**: `sudo apt-get install pandoc` (for text extraction) How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DOCX creation, editing, and analysis
Overview
A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.
Content Quality Defaults (Critical)
When the user asks to create or rewrite document content and does not explicitly ask for brevity, generate a substantive first draft instead of skeletal outlines.
Required defaults:
- Prefer complete prose over bullet-only stubs.
- Each major section should contain at least 2-4 developed paragraphs unless the user requests a short memo format.
- Paragraphs should include concrete details: context, rationale, implications, and next actions (not generic filler).
- Add specific examples, scenarios, or mini case-style illustrations where appropriate.
- Use domain-appropriate terminology and define key concepts the first time they appear.
- If requirements are ambiguous, state reasonable assumptions in the document and continue with a complete draft.
Anti-patterns to avoid:
- One-line section placeholders (for example: "TBD", "待补充", "略").
- Repeating high-level statements without evidence, explanation, or actionable detail.
- Ending after a high-level outline when the user asked for "write/generate/draft".
Length guidance (default baseline unless user specifies otherwise):
- Short practical document: 800-1200 Chinese characters (or 500-900 English words).
- Standard report/proposal: 1500-3000 Chinese characters (or 1000-2000 English words).
- For multi-section documents, keep section depth balanced; avoid one oversized section plus many thin sections.
Workflow Decision Tree
Reading/Analyzing Content
Use "Text extraction" or "Raw XML access" sections below
Creating New Document
Use "Creating a new Word document" workflow
Editing Existing Document
- Your own document + simple changes Use "Basic OOXML editing" workflow
What ships with it
60 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.
- docx-js.md 21 KB
- LICENSE.txt 1.4 KB
- ooxml.md 23 KB
- ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd 1.9 KB
- ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd 2.5 KB
- ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd 2.8 KB
- ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd 1.3 KB
- ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd 73 KB
- ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd 6.8 KB
- ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd 50 KB
- ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd 624 B
- ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd 148 KB
- ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd 1.2 KB
- ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd 8.7 KB
- ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd 14 KB
- ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd 82 KB
- ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd 1.2 KB
- ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd 7.2 KB
- ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd 6.2 KB
- ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd 1.2 KB
- ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd 880 B
- ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd 2.5 KB
- ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd 3.4 KB
- ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd 7.3 KB
- ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd 23 KB
- ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd 1.3 KB
- ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd 237 KB
- ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd 26 KB
- ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd 25 KB
- ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd 535 B
- ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd 5.6 KB
- ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd 3.9 KB
- ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd 167 KB
- ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd 4.5 KB
- ooxml/schemas/mce/mc.xsd 3.1 KB
- ooxml/schemas/microsoft/wml-2010.xsd 26 KB
- ooxml/schemas/microsoft/wml-2012.xsd 3.7 KB
- ooxml/schemas/microsoft/wml-2018.xsd 901 B
- ooxml/schemas/microsoft/wml-cex-2018.xsd 1.7 KB
- ooxml/schemas/microsoft/wml-cid-2016.xsd 1002 B
- ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd 600 B
- ooxml/schemas/microsoft/wml-symex-2015.xsd 745 B
- ooxml/scripts/__pycache__/pack.cpython-310.pyc 4.4 KB
- ooxml/scripts/__pycache__/pack.cpython-312.pyc 7.3 KB
- ooxml/scripts/__pycache__/unpack.cpython-310.pyc 1.1 KB
- ooxml/scripts/__pycache__/unpack.cpython-312.pyc 1.8 KB
- ooxml/scripts/__pycache__/validate.cpython-310.pyc 1.7 KB
- ooxml/scripts/__pycache__/validate.cpython-312.pyc 2.6 KB
- ooxml/scripts/pack.py 5.5 KB runs code
- ooxml/scripts/unpack.py 1.0 KB runs code
- ooxml/scripts/validate.py 1.9 KB runs code
- ooxml/scripts/validation/__init__.py 336 B runs code
- ooxml/scripts/validation/__pycache__/__init__.cpython-310.pyc 500 B
- ooxml/scripts/validation/__pycache__/__init__.cpython-312.pyc 516 B
- ooxml/scripts/validation/__pycache__/base.cpython-310.pyc 21 KB
- ooxml/scripts/validation/__pycache__/base.cpython-312.pyc 37 KB
- ooxml/scripts/validation/__pycache__/docx.cpython-310.pyc 6.3 KB
- ooxml/scripts/validation/__pycache__/docx.cpython-312.pyc 11 KB
- ooxml/scripts/validation/__pycache__/pptx.cpython-310.pyc 7.6 KB
- ooxml/scripts/validation/__pycache__/pptx.cpython-312.pyc 13 KB
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.
- 8d ago First seen · 279 lines · 77 tokens per session scan B cb4fcabf4d4c
docx is a skill published in the GitHub repository TasiTech/tasi-harness (11 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 4,020 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sn-da-excel-workflow
A step-by-step workflow for analysing Excel workbooks with multiple sheets. It covers reading data, cleaning it, filtering and combining results, and exporting reports, with a separate strategy for large files.
sn-da-large-file-analysis
A workflow for analyzing very large Excel datasets, especially files with at least 10,000 rows. It uses lower-memory reading, streaming through rows, splitting work into chunks, and converting data to Parquet, a column-based data format suited to repeated analysis.
sn-ppt-creative
Creative-mode PPT pipeline. One full-page 16:9 PNG per slide. LLM / VLM calls go through sn-ppt-standard/lib/modelclient.py (shared thin client). Text-to-image (the actual png rendering) goes through sn-image-base/scripts/snagentrunner.py. Falls back to web image search when T2I generation fails. Expects taskpack.json…
sn-ppt-entry
Entry point for PPT generation. Asks the user to choose a mode (fast, standard, or creative), then collects role / audience / scene / pagecount as needed. For standard mode, also asks how images should be sourced (AI generation, web search, or none), whether charts should use AI-generated infographics or ECharts, and…
pdf-analysis
A PDF analysis method for reading both normal PDFs with selectable text and scanned PDFs made from page images.
ppt-analysis
A parser for PowerPoint presentations in .pptx or older .ppt format that extracts their contents and flags slides needing image-based inspection.