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 gxgeek-n/wenqu-mem --skill thesis-docxgit clone --depth 1 https://github.com/gxgeek-n/wenqu-memWrote 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/gxgeek-n/wenqu-mem/thesis-docx)<a href="https://agentmods.dev/skills/gxgeek-n/wenqu-mem/thesis-docx"><img src="https://agentmods.dev/badge/skills/gxgeek-n/wenqu-mem/thesis-docx/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/gxgeek-n/wenqu-mem/thesis-docx"><img src="https://agentmods.dev/badge/skills/gxgeek-n/wenqu-mem/thesis-docx.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 | $0.00130 | $0.07019 |
| Opus 5 | $0.00065 | $0.03510 |
| Sonnet 5 | $0.00026 | $0.01404 |
| Haiku 4.5 | $0.00013 | $0.00702 |
Grade A, and why
thesis-docx 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
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- assets/gb7714-2015-numeric.csl 15 KB
- assets/zju-mem-frontmatter-master.docx 541 KB
- assets/zju-reference.docx 12 KB
- assets/浙江大学工程管理硕士学位论文规范要求-2024.docx 682 KB
- README.md 6.8 KB
- references/conversion-rules.md 9.1 KB
- references/draft-normalizer.md 3.1 KB
- references/official-format-requirements.md 3.1 KB
- references/visual-qa-checklist.md 5.7 KB
- scripts/mem_docx.py 9.8 KB runs code
- scripts/pyproject.toml 4.3 KB
- scripts/test_abstract_extraction_edge.py 7.6 KB runs code
- scripts/test_bibliography_split.py 2.8 KB runs code
- scripts/test_blind_frontmatter.py 5.7 KB runs code
- scripts/test_citation_links.py 2.6 KB runs code
- scripts/test_comments_export.py 16 KB runs code
- scripts/test_crossref_numbering.py 6.2 KB runs code
- scripts/test_doc_hygiene.py 14 KB runs code
- scripts/test_docx_semantics.py 6.5 KB runs code
- scripts/test_draft_normalizer.py 5.0 KB runs code
- scripts/test_equation_layout.py 18 KB runs code
- scripts/test_figure_ref_links.py 5.3 KB runs code
- scripts/test_mem_docx_cli.py 11 KB runs code
- scripts/test_redline.py 13 KB runs code
- scripts/test_review_fixes.py 4.9 KB runs code
- scripts/test_schema_check.py 14 KB runs code
- scripts/test_seq_captions.py 8.7 KB runs code
- scripts/test_visual_regress.py 7.5 KB runs code
- scripts/thesis_docx/__init__.py 61 B runs code
- scripts/thesis_docx/cli/__init__.py 58 B runs code
- scripts/thesis_docx/cli/native.py 14 KB runs code
- scripts/thesis_docx/domain/__init__.py 60 B runs code
- scripts/thesis_docx/domain/abstracts.py 8.1 KB runs code
- scripts/thesis_docx/domain/draft.py 18 KB runs code
- scripts/thesis_docx/importers/__init__.py 70 B runs code
- scripts/thesis_docx/importers/docx.py 4.4 KB runs code
- scripts/thesis_docx/ooxml/__init__.py 53 B runs code
- scripts/thesis_docx/ooxml/contract.py 8.3 KB runs code
- scripts/thesis_docx/ooxml/equations.py 14 KB runs code
- scripts/thesis_docx/ooxml/field_dsl.py 2.3 KB runs code
- scripts/thesis_docx/ooxml/fields.py 2.4 KB runs code
- scripts/thesis_docx/ooxml/fonts.py 9.5 KB runs code
- scripts/thesis_docx/ooxml/hygiene.py 9.9 KB runs code
- scripts/thesis_docx/ooxml/package.py 11 KB runs code
- scripts/thesis_docx/ooxml/postprocess_links.py 14 KB runs code
- scripts/thesis_docx/ooxml/postprocess.py 11 KB runs code
- scripts/thesis_docx/ooxml/seq_captions.py 9.4 KB runs code
- scripts/thesis_docx/ooxml/styles.py 14 KB runs code
- scripts/thesis_docx/ooxml/table_checks.py 3.1 KB runs code
- scripts/thesis_docx/ooxml/table_reports.py 6.1 KB runs code
- scripts/thesis_docx/ooxml/tables.py 18 KB runs code
- scripts/thesis_docx/pipeline/__init__.py 63 B runs code
- scripts/thesis_docx/pipeline/body_latex.py 14 KB runs code
- scripts/thesis_docx/pipeline/body_postprocess.py 6.0 KB runs code
- scripts/thesis_docx/pipeline/body_report.py 2.1 KB runs code
- scripts/thesis_docx/pipeline/body.py 16 KB runs code
- scripts/thesis_docx/pipeline/draft_format.py 8.6 KB runs code
- scripts/thesis_docx/pipeline/frontmatter.py 11 KB runs code
- scripts/thesis_docx/pipeline/merge_sections.py 11 KB runs code
- scripts/thesis_docx/pipeline/merge.py 17 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 · 382 lines · 130 tokens per session scan A b713fbf86a8e
thesis-docx is a skill published in the GitHub repository gxgeek-n/wenqu-mem (3 stars, last pushed 1mo ago), with no licence file. It adds 130 tokens to every session and 7,019 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
academic-citation
An academic reference manager and checker for organizing sources used in research papers. It supports styles such as GB/T 7714, APA, IEEE, and Nature, and works with formats including BibTeX and RIS.
paper-typeset
A document-conversion tool for turning Markdown—the plain-text writing format—into LaTeX, Word, or PDF files. It can format references using GB/T 7714-2015, the Chinese national citation standard.
patent-application
A patent-application document workflow that turns supplied invention materials into claims, a description, an abstract, and black-and-white drawings. It can also produce Markdown and Word files.
data-management-plan
Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data…
new-diagram
Scaffold a new TikZ diagram from the snippet gallery with prevention rules pre-applied (explicit node dimensions, coordinate map, directional edge labels). Compiles standalone, invokes tikz-reviewer with citations from tikz-measurement.md, and loops on revisions until APPROVED.
compile-latex
Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides", "rebuild the PDF", "run latex", "render the tex", or asks why a .tex file isn't producing a PDF. Operates on Slides/.tex.