Weak Agent Test
kklimuk/docx-cli
Run the weak-agent adversarial test harness against docx-cli.
Create, read, edit, review, redline, comment on, merge, audit, render, and verify .docx Word documents, including layout-sensitive and OOXML-level work.
Install DOCX
$ npx skills add MemTensor/memmy-agent --skill docx -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MemTensor/memmy-agent docx --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/MemTensor/memmy-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/App/memmy-agent/src/skills/docx .claude/skills/docx && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "docx" agent skill from https://github.com/MemTensor/memmy-agent/tree/main/App/memmy-agent/src/skills/docx into .claude/skills/docx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/MemTensor/memmy-agent/tree/main/App/memmy-agent/src/skills/docxType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add MemTensor/memmy-agent --skill docx -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MemTensor/memmy-agent docx --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemTensor/memmy-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/App/memmy-agent/src/skills/docx .agents/skills/docx && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "docx" agent skill from https://github.com/MemTensor/memmy-agent/tree/main/App/memmy-agent/src/skills/docx into .agents/skills/docx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MemTensor/memmy-agent --skill docx -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MemTensor/memmy-agent docx --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemTensor/memmy-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/App/memmy-agent/src/skills/docx .cursor/skills/docx && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "docx" agent skill from https://github.com/MemTensor/memmy-agent/tree/main/App/memmy-agent/src/skills/docx into .cursor/skills/docx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/MemTensor/memmy-agent.git --path App/memmy-agent/src/skills/docx--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add MemTensor/memmy-agent --skill docx -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MemTensor/memmy-agent docx --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemTensor/memmy-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/App/memmy-agent/src/skills/docx .gemini/skills/docx && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "docx" agent skill from https://github.com/MemTensor/memmy-agent/tree/main/App/memmy-agent/src/skills/docx into .gemini/skills/docx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install MemTensor/memmy-agent docxInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add MemTensor/memmy-agent --skill docx -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MemTensor/memmy-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/App/memmy-agent/src/skills/docx .github/skills/docx && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "docx" agent skill from https://github.com/MemTensor/memmy-agent/tree/main/App/memmy-agent/src/skills/docx into .github/skills/docx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MemTensor/memmy-agent --skill docx -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MemTensor/memmy-agent docx --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemTensor/memmy-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/App/memmy-agent/src/skills/docx .opencode/skills/docx && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "docx" agent skill from https://github.com/MemTensor/memmy-agent/tree/main/App/memmy-agent/src/skills/docx into .opencode/skills/docx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docx", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
docx- GitHub stars
- 2.1k
- Token cost
- ~1.9k tokens
- SKILL.md length
- 748 words
- Files
- 77 (incl. scripts, references)
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
Create, read, edit, review, redline, comment on, merge, audit, render, and verify .docx Word documents, including layout-sensitive and OOXML-level work.
- Works in 5 steps: Identify the operation: read/review,… → Keep the source document unchanged for… → Use Node OOXML for ordinary paragraphs,… → …
- Tasks that involve Word documents
- SKILL.md covers Core workflow, Route to the relevant guide, Rendering and visual QA and New documents and major rewrites, plus 3 more sections
- Calls node
What it does
DOCX is an agent skill from MemTensor/memmy-agent. Create, read, edit, review, redline, comment on, merge, audit, render, and verify .docx Word documents, including layout-sensitive and OOXML-level work.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 80 other files, including scripts and reference files (for example `references/design_presets.md`, `references/examples/end_to_end_smoke_test.md` and `references/header_templates.md`).
It sits in Documents & Office, covering Word documents and Contract review. It works with Microsoft Word and OpenAI. The repository describes itself as: 🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now… The licence is MIT.
When your agent uses it
- Tasks that involve Word documents
- Tasks that involve Contract review
Example prompts
- “/docx”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Identify the operation: read/review, create/edit, template following,
- Keep the source document unchanged for review and template-distillation
- Use Node OOXML for ordinary paragraphs, runs, styles, tables,
- After every meaningful create or edit batch, render the document with
- Deliver only the requested final document. Keep rendered PNGs, temporary
What it can do on your machine
Read from SKILL.md and the folder at commit ee0ed02. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
node
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
DOCX loads about 1.9k tokens when it runs, and up to ~26k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 748 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from MemTensor/memmy-agent at commit ee0ed02, republished under its MIT licence (© MemTensor). 748 words, ~1,850 tokens.
Download SKILL.mdSave it as
.claude/skills/docx/SKILL.md (or your agent's skills folder). This skill also uses 76 other files; get the full folder from GitHub.- name
- docx
- description
- Create, read, edit, review, redline, comment on, merge, audit, render, and verify .docx Word documents, including layout-sensitive and OOXML-level work.
DOCX Skill
Use this skill when a task involves a Word .docx document and correctness
depends on document structure, formatting, tracked changes, comments, fields,
tables, forms, or rendered layout.
Core workflow
- Identify the operation: read/review, create/edit, template following, redlining/comments, conversion, or final verification.
- Keep the source document unchanged for review and template-distillation work. Write outputs and intermediate files to a task-specific writable directory.
- Use
Node OOXMLfor ordinary paragraphs, runs, styles, tables, headers/footers, and page setup. Use the bundled helpers underscripts/for deterministic audits and OOXML operations. - After every meaningful create or edit batch, render the document with
render_docx.mjs, inspect every generated page image, and iterate until the layout is clean. - Deliver only the requested final document. Keep rendered PNGs, temporary PDFs, audit JSON, and diff images as internal QA artifacts unless requested.
Route to the relevant guide
Read only the supporting guide needed for the current operation:
- Existing-document reading or review: references/tasks/read_review.md
- Creating or editing a document: references/tasks/create_edit.md
- Render and visual verification: references/tasks/verify_render.md
- Accessibility and document structure: references/tasks/accessibility_a11y.md
- Styles and formatting cleanup: references/tasks/style_lint_normalize.md
- Templates and style packs: references/tasks/templates_style_packs.md
- Template distillation and creation: references/template-distill.md and references/template-create.md
- Tables and spreadsheet-to-document conversion: references/tasks/tables_spreadsheets.md
- Forms/content controls: references/tasks/forms_content_controls.md
- Captions and cross-references: references/tasks/captions_crossrefs.md
- Fields and field display text: references/tasks/fields_update.md
- Navigation and table of contents: references/tasks/navigation_internal_links.md and references/tasks/toc_workflow.md
- Tracked changes: references/tasks/clean_tracked_changes.md and references/ooxml/tracked_changes.md
- Comments: references/tasks/comments_manage.md and references/ooxml/comments.md
- Hyperlinks, fields, headers, and page numbers: references/ooxml/hyperlinks_and_fields.md
- Package relationships and content types: references/ooxml/rels_and_content_types.md
- Redaction, privacy, protection, watermarks, footnotes, merging, or sections:
use the matching file under
references/tasks/.
Rendering and visual QA
The canonical renderer converts DOCX to PDF internally and rasterizes each page
to page-<N>.png:
node scripts/render_docx.mjs input.docx --output_dir /path/to/qaUse --emit_pdf only when an intermediate PDF is useful for diagnosis. Use
--verbose when LibreOffice conversion needs debugging. Inspect every page at
full resolution for clipped or overlapping text, missing glyphs, broken tables,
unexpected page breaks, and header/footer drift. Text extraction or XML checks
alone cannot prove visual correctness.
If LibreOffice is unavailable, complete structural checks with the relevant audits and state that visual QA could not be performed. If conversion fails for another reason, diagnose the renderer/profile problem before judging the DOCX.
For repeated comparisons, use scripts/render_and_diff.mjs. For a quick
structural pass, use the audits for sections, headings, images, fields,
footnotes, comments, tables, styles, watermarks, accessibility, or content
controls as applicable.
Show full SKILL.md (364 more words)Show less
New documents and major rewrites
When no supplied template controls the design, choose exactly one preset from references/design_presets.md:
standard_business_brieffor formal memos and executive briefscompact_reference_guidefor checklists, launch guides, and dense referencesnarrative_proposalfor proposals and longer persuasive documents- an archetype alias defined by the reference when it is a closer fit
Resolve the preset into explicit page, margin, typography, spacing, list, table, color, header, and footer tokens before drafting. Use real Word styles, numbering definitions, and fixed DXA table geometry; do not depend on inherited defaults or visual approximations. Read references/header_templates.md when a new first-page header, cover, or title block is needed.
Use the lightest form factor that matches the content: prose for explanation, bullets for unordered considerations, numbered steps for procedures, checklists for acceptance criteria, callouts for warnings, and tables only for genuinely tabular data. Avoid using tables as layout containers or turning cells into long prose blocks.
Editing, redlining, and OOXML
For an existing document, preserve the original structure and make the smallest local change that satisfies the request. Do not rewrite unrelated paragraphs or styles. Real tracked changes and Word comments require OOXML patching; use the corresponding helpers and perform another render plus structural check after any package-level change.
Use scripts/privacy_scrub.mjs before publication when personal metadata or
rsid values should be removed. Use scripts/redact_docx.mjs for explicit
redaction/anonymization requests and verify the result structurally and
visually. Use scripts/set_protection.mjs only when the requested output needs
editing restrictions.
File and command conventions
- Refer to inputs and outputs by absolute paths when reporting results.
- Keep temporary work in a unique writable directory; never modify a retained reference document during inspection.
- Prefer the bundled Node/MJS helpers and the renderer bundled with the application. Check the renderer bundle before relying on an optional operation.
- Do not claim a render or audit passed unless its output was actually checked.
- Keep citation text human-readable; do not place internal tool tokens in the document.
Bundled resources
The package includes the canonical renderer, OOXML notes, task playbooks,
design references, examples, and reusable scripts. references/manifest.txt lists the
bundled paths. Scripts are intended to be run from a writable working
directory, while this skill directory remains the source of reusable helpers.
© MemTensor, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 76 other files (scripts, references) in App/memmy-agent/src/skills/docx of MemTensor/memmy-agent.
- SKILL.md
- references/design_presets.md
- references/examples/end_to_end_smoke_test.md
- references/header_templates.md
- references/manifest.txt
- references/ooxml/comments.md
- references/ooxml/hyperlinks_and_fields.md
- references/ooxml/rels_and_content_types.md
- references/ooxml/tracked_changes.md
- references/tasks/accessibility_a11y.md
- references/tasks/captions_crossrefs.md
- references/tasks/clean_tracked_changes.md
- references/tasks/comments_manage.md
- references/tasks/compare_diff.md
- references/tasks/create_edit.md
- references/tasks/fields_update.md
- references/tasks/fixtures_edge_cases.md
- … and 60 more
Open the folder on GitHubat commit ee0ed02
Compare with similar skills
DOCX next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| DOCX this skillMemTensor/memmy-agent | 2.1k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Weak Agent Testkklimuk/docx-cli | 215 | — | ~6.1k | Automated safety check: Notes | MIT | |
| WordIgorWarzocha/Opencode-Workflows | 122 | — | ~647 | Automated safety check: Pass | None | |
| Contract Output Formatterinfometa/workbuddyskills | 342 | — | ~1.6k | Automated safety check: Pass | None | |
| Adeu Redliningdealfluence/adeu | 165 | — | ~2.4k | Automated safety check: Pass | MIT | |
| DOCX Processing Openailawve-ai/awesome-legal-skills | 826 | — | ~810 | Automated safety check: Notes | Apache-2.0 |
Similar skills
Word
IgorWarzocha/Opencode-Workflows
Handle Word document (.docx) creation, editing, and analysis with high-fidelity visual review.
Contract Output Formatter
infometa/workbuddyskills
Format contract work products into the delivery shape that best matches the hit scenario (C1-C9) and the reading audience.
Adeu Redlining
dealfluence/adeu
A skill your agent uses when reviewing, editing, redlining, or negotiating an existing Microsoft Word document (.docx) — including proposing edits as tracked changes, accepting or rejecting existing…
DOCX Processing Openai
lawve-ai/awesome-legal-skills
Toolkit for comprehensive document reading, editing, and creation with visual quality control.
Doc
nexu-io/open-design
Read, create, and edit .docx documents with formatting and layout fidelity via OpenAI's document skill.
More from MemTensor/memmy-agent
All 10 skills in this repoSkill Creator
MemTensor/memmy-agent
Create, edit, improve, tidy, review, audit, or restructure memmy-agent skills and SKILL.md files.
Update Setup
MemTensor/memmy-agent
One-time setup wizard for the memmy upgrade skill. An agent skill from MemTensor/memmy-agent.
Agent Memory Onboarding
MemTensor/memmy-agent
On-demand provisioning guide for a Memmy GUI task that fully connects an explicitly named local Agent: discover its active history store, install or remove its rendered Memmy Skill, bootstrap a scan…
PPTX
MemTensor/memmy-agent
Create, inspect, edit, validate, render, and deliver PowerPoint presentations and templates while preserving OOXML structure and user metadata.
Computer History
MemTensor/memmy-agent
Answer questions about what the user recently did on their computer — who contacted them, what they were working on, where they left off — by reading the local Computer History summaries and raw…
Image Generation
MemTensor/memmy-agent
Generate images and iteratively edit saved image artifacts. An agent skill from MemTensor/memmy-agent.
Related
Works with
Categories
Questions about DOCX
What does DOCX do?
Create, read, edit, review, redline, comment on, merge, audit, render, and verify .docx Word documents, including layout-sensitive and OOXML-level work. DOCX is an agent skill from MemTensor/memmy-agent.docx Word documents, including layout-sensitive and OOXML-level work.
When should I use DOCX?
DOCX fits situations like: tasks that involve Word documents; tasks that involve Contract review.
How do I install DOCX in Claude Code?
Run `npx skills add MemTensor/memmy-agent --skill docx -a claude-code`. Or copy the skill folder (App/memmy-agent/src/skills/docx in MemTensor/memmy-agent) into .claude/skills/docx in your project. Claude Code loads it when a task matches its description.
How do I install DOCX in Codex?
Run `npx skills add MemTensor/memmy-agent --skill docx -a codex`. Or copy the skill folder (App/memmy-agent/src/skills/docx in MemTensor/memmy-agent) into .agents/skills/docx in your project. Codex loads it when a task matches its description.
Can I use DOCX in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MemTensor/memmy-agent --skill docx -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/docx, .gemini/skills/docx, .github/skills/docx and .opencode/skills/docx in your project.
What does DOCX need to run?
Going by SKILL.md and its folder, DOCX needs the command-line tools its instructions call (node).
Does DOCX access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is DOCX safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does DOCX use?
DOCX is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does DOCX use?
About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 24k tokens, read only when the agent opens those files.
What are the alternatives to DOCX?
Skills that share tags, products or a category with DOCX: Weak Agent Test (kklimuk/docx-cli, 215 stars), Word (IgorWarzocha/Opencode-Workflows, 122 stars), Contract Output Formatter (infometa/workbuddyskills, 342 stars) and Adeu Redlining (dealfluence/adeu, 165 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains DOCX?
MemTensor (a GitHub organization) maintains it in MemTensor/memmy-agent, which has 2,064 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 30, 2026.
Source: MemTensor/memmy-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.