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 Sven-LI-sankyuu/presentation-skills --skill word-polished-doc-collabgit clone --depth 1 https://github.com/Sven-LI-sankyuu/presentation-skillsWrote 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/sven-li-sankyuu/presentation-skills/word-polished-doc-collab)<a href="https://agentmods.dev/skills/sven-li-sankyuu/presentation-skills/word-polished-doc-collab"><img src="https://agentmods.dev/badge/skills/sven-li-sankyuu/presentation-skills/word-polished-doc-collab/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/sven-li-sankyuu/presentation-skills/word-polished-doc-collab"><img src="https://agentmods.dev/badge/skills/sven-li-sankyuu/presentation-skills/word-polished-doc-collab.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00081 | $0.03900 |
| Opus 5 | $0.00041 | $0.01950 |
| Sonnet 5 | $0.00016 | $0.00780 |
| Haiku 4.5 | $0.00008 | $0.00390 |
Grade A, and why
word-polished-doc-collab 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 12d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- agents/openai.yaml 539 B
- references/build_routes.md 3.0 KB
- references/doc_workflow.md 7.7 KB
- references/lightweight_mode.md 4.8 KB
- references/local_pipeline_case_study.md 2.8 KB
- references/office_chart_support.md 3.2 KB
- references/preset_style_guides.md 23 KB
- references/principles.md 7.7 KB
- references/python_figure_support.md 2.4 KB
- references/quality_gates.md 4.4 KB
- references/technical_support.md 5.0 KB
- references/typography_profiles.md 6.7 KB
- scripts/agent_qc_reminders/__init__.py 749 B runs code
- scripts/agent_qc_reminders/core.py 72 KB runs code
- scripts/build_docx.py 3.2 KB runs code
- scripts/check_word_environment.py 5.4 KB runs code
- scripts/export_docx_preview.py 2.7 KB runs code
- scripts/init_doc_workspace.py 9.9 KB runs code
- scripts/lint_doc_markdown.py 5.7 KB runs code
- scripts/run_docx_qa.py 6.3 KB runs code
- scripts/word_skill_tools.py 102 KB runs code
- vendor/docx/__init__.py 1.8 KB runs code
- vendor/docx/api.py 1.3 KB runs code
- vendor/docx/blkcntnr.py 3.4 KB runs code
- vendor/docx/comments.py 6.2 KB runs code
- vendor/docx/dml/__init__.py 0 B runs code
- vendor/docx/dml/color.py 4.3 KB runs code
- vendor/docx/document.py 11 KB runs code
- vendor/docx/drawing/__init__.py 2.2 KB runs code
- vendor/docx/enum/__init__.py 0 B runs code
- vendor/docx/enum/base.py 5.0 KB runs code
- vendor/docx/enum/dml.py 3.3 KB runs code
- vendor/docx/enum/section.py 2.3 KB runs code
- vendor/docx/enum/shape.py 396 B runs code
- vendor/docx/enum/style.py 9.9 KB runs code
- vendor/docx/enum/table.py 3.9 KB runs code
- vendor/docx/enum/text.py 10 KB runs code
- vendor/docx/exceptions.py 454 B runs code
- vendor/docx/image/__init__.py 664 B runs code
- vendor/docx/image/bmp.py 1.3 KB runs code
- vendor/docx/image/constants.py 3.4 KB runs code
- vendor/docx/image/exceptions.py 383 B runs code
- vendor/docx/image/gif.py 1.1 KB runs code
- vendor/docx/image/helpers.py 3.0 KB runs code
- vendor/docx/image/image.py 7.8 KB runs code
- vendor/docx/image/jpeg.py 15 KB runs code
- vendor/docx/image/png.py 8.0 KB runs code
- vendor/docx/image/tiff.py 10 KB runs code
- vendor/docx/opc/__init__.py 0 B runs code
- vendor/docx/opc/constants.py 17 KB runs code
- vendor/docx/opc/coreprops.py 3.4 KB runs code
- vendor/docx/opc/exceptions.py 264 B runs code
- vendor/docx/opc/oxml.py 8.1 KB runs code
- vendor/docx/opc/package.py 8.5 KB runs code
- vendor/docx/opc/packuri.py 3.6 KB runs code
- vendor/docx/opc/part.py 8.8 KB runs code
- vendor/docx/opc/parts/__init__.py 0 B runs code
- vendor/docx/opc/parts/coreprops.py 1.7 KB runs code
- vendor/docx/opc/phys_pkg.py 3.9 KB runs code
- vendor/docx/opc/pkgreader.py 9.4 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.
- 12d ago First seen · 172 lines · 81 tokens per session scan A acc2d6395953
word-polished-doc-collab is a skill published in the GitHub repository Sven-LI-sankyuu/presentation-skills (171 stars, last pushed 1mo ago), with no licence file. It adds 81 tokens to every session and 3,900 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
pm-preview
A tool that previews Markdown product documents in a web browser and refreshes the view when the documents change. Markdown is a plain-text format commonly used for project documentation.
agent-browser
A command-line tool for controlling a web browser without a visible window. It can open pages, inspect their accessibility structure, interact with forms, take screenshots, create PDFs, and run JavaScript.
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI.
feishu-drive
A skill for managing files and folders in Feishu Drive, Feishu’s cloud storage service. It covers common file-management actions.
feishu-perm
Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.
feishu-doc
Fetch content from Feishu (Lark) Wiki, Docs, Sheets, and Bitable. Automatically resolves Wiki URLs to real entities and converts content to Markdown.