What does this skill do, and when should you use it?
This is a scene-specific skill bundled in the OfficeCLI repository for building academic-style .docx output. It supports APA, Chicago, IEEE, MLA citation styles, numbered equations, figure/table cross-references, footnotes/endnotes, hanging-indent bibliographies, and multi-column journal layouts. It inherits rules from the base docx skill and depends on the OfficeCLI command-line tool.
Reads venue specifications, plans sections, sets up styles, builds documents paragraph by paragraph via officecli commands, adds equations, SEQ/PAGEREF fields, footnotes, endnotes, multi-column sections, and runs delivery gate checks for validation.
- A graduate student writing a thesis with APA formatting and a reference list.
- An engineer preparing an IEEE conference paper with two-column layout and Roman-numeral section headings.
- A humanities scholar needing Chicago notes-bibliography footnotes and bibliography.
- A literature researcher requiring MLA Works Cited format.
- A researcher generating manuscripts with cross-references and numbered equations.
How do you install this skill?
- Installation script (curl | bash) poses supply-chain risk; users should review script content and verify integrity.
- Skill depends on external services (d.officecli.ai, github.com) which may be unreachable from mainland China; consider alternative installation methods or proxies.
- Skill does not provide versioning or changelog; follow official releases for updates.
- Skill references other files (docx v2) not available during assessment; ensure they exist when using.
- Shell / CLI
- Network access
- Local filesystem
officecli binary
Install the officecli binary first: macOS/Linux: curl -fsSL https://d.officecli.ai/install.sh | bash, Windows PowerShell: irm https://d.officecli.ai/install.ps1 | iex. Then obtain the skill file via curl -fsSL https://officecli.ai/SKILL.md or from the repo's skills/officecli-academic-paper/SKILL.md.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/iOfficeAI/OfficeCLI.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/officecli-academic-paper" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Follow the workflow in SKILL.md: read venue spec, plan sections, set styles, add headings/paragraphs/equations/figures/tables/references with officecli add commands, then run officecli validate and delivery gate checks. Example: officecli create paper.docx; officecli add paper.docx /body --type paragraph --prop text="Abstract".
What are this skill's strengths and limitations?
- Zero-dependency binary, no Office installation needed to generate formatted docx.
- Detailed style-specific guides for APA/Chicago/IEEE/MLA, including paragraph indents, citation formats, and more.
- Automatic numbering for equations and SEQ/PAGEREF cross-references, ensuring accurate references.
- Built-in delivery gate checks for citation round-trip, SEQ presence, and visual QA.
- Requires learning the officecli CLI syntax, with a learning curve.
- Skill documentation is long and may be overwhelming.
- Some features like IEEE table Roman numerals need manual patching.
- Only outputs docx; no PDF export or other formats.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| OfficeCLI Academic Paper Skill this page | 51 · Use with care | ★ 32k | 5d ago | Apache-2.0 |
| Academic Paper Writing Expert Team | 0 · Not recommended | ★ 51k | 8d ago | NOASSERTION |
| Paper to Chinese Patent Draft | 56 · Use with care | ★ 47k | 3d ago | Apache-2.0 |
| Academic Humanizer | 55 · Use with care | ★ 1.9k | 3mo ago | NOASSERTION |
| Multi-Perspective Academic Paper Review Simulator | 52 · Use with care | ★ 51k | 8d ago | NOASSERTION |
How did FollowSkills review this skill?
Evidence: Skill requires executing installation scripts (curl | bash or irm | iex), involving remote code execution without explicit confirmation or integrity checks; lacks data-flow transparency and sensitive-data handling; no explicit least privilege or user confirmation mechanisms. License is Apache-2.0, but publisher identity is unverified. Main risks visible but no red-line issues. Deductions: supply-chain risk of install scripts, missing user confirmation and least privilege, and unverified publisher.
Evidence: Skill provides structured command sequences and QA steps, but referenced docx v2 documentation not in provided files, key-path reproducibility unverifiable. No tests or example outputs to validate, and depends on external services for installation. Static cannot execute validation. Deductions: incomplete documentation, unverified commands and external installation, and lack of tests.
Evidence: Skill clearly defines target scenario (academic papers) and triggers (citation styles, equations, etc.), with clear inputs, outputs, and non-fit boundaries. Chinese-language support present, but installation relies on external services (d.officecli.ai, github.com) potentially unreachable from mainland China, and skill does not explicitly address this. Deductions: not addressing network reachability in mainland China.
Evidence: Skill is well-structured with setup instructions, examples, and troubleshooting hints. License clearly Apache-2.0, but versioning and changelog not mentioned in skill file; references other files not provided. Maintenance responsibility not explicit. Deductions: incomplete versioning, changelog, and maintenance responsibility.
Evidence: Skill claims to generate academic papers, but no actual output validation. Example commands provided, but lack evidence of result quality and marginal value. Static cannot verify output. Deductions: missing output validation and marginal value evidence.
Evidence: No third-party execution evidence, only skill self-claims. CI workflows and tests not provided at skill level, and static review cannot execute. Deductions: lack of reproducible execution evidence and cross-corroboration.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →