CtrlK
BlogDocsLog inGet started
Tessl Logo

officecli-academic-paper

Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper', 'conference paper', 'manuscript', 'thesis', 'APA', 'MLA', 'Chicago', 'IEEE two-column', 'bibliography', 'hanging indent', 'citation style', 'abstract + keywords', 'equation numbering', 'cross-reference', paper with footnotes/endnotes. Output is a single .docx.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An executable, well-gated scene layer with outstanding actionability and workflow clarity — every command is copy-paste ready and QA is enforced with reject-on-failure loops. Its weaknesses are token efficiency (pitfalls restated multiple times across sections) and progressive disclosure (four citation recipes and the IEEE layout recipe inlined in a 500-line body with no reference files).

Suggestions

State each pitfall once — either in its main section or in 'Known Issues & Pitfalls' — and cross-reference the other location, instead of repeating the \left(...\right) parse error, tc[N] guard, hanging-indent pair, recalcFields=seq, and multi-column revert rules verbatim 2–4x.

Split the four citation-style recipes (APA / Chicago / IEEE / MLA) into references/ files (e.g. references/apa.md) and keep only the shared decision table plus one exemplar recipe in SKILL.md, reducing the body by ~130 lines.

Merge 'Mental Model & Inheritance' into the opening scene-layer paragraph, which already makes the same inheritance and read-docx-v2-first points.

DimensionReasoningScore

Conciseness

The body is dense and task-specific with no concept padding, but several facts are repeated 2–4x: the \left(...\right) parse pitfall, the tc[N] equation guard, the 'indent=720 hangingIndent=720' canonical pair, the recalcFields=seq rule, and the multi-column no-auto-revert rule each appear in their main section and again in 'Known Issues & Pitfalls', and 'Mental Model & Inheritance' restates the opening paragraph. This fits 'mostly efficient but could be tightened' (3) rather than 'minor instances' (4).

3 / 5

Actionability

Every section carries fully executable officecli commands: a Quick Start that 'validates clean', per-style citation recipes with exact --prop pairs, computed tab-stop twip positions for equation numbering, and copy-paste bash for all Delivery Gates. Matches the score-5 anchor (copy-paste ready, specific examples cover the common cases).

5 / 5

Workflow Clarity

A clear 5-verb workflow (read venue spec → plan sections → set styles up front → build in order → QA) with a styles-before-content rule and an executable Delivery Gate: Gates 1–5 with REJECT/exit-1 feedback loops, a mandatory HTML visual audit checklist, and re-run guidance after mid-document inserts. Matches the score-5 anchor with explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent), so all content lives in this ~500-line body: the four full citation-style recipes and the IEEE multi-column recipe are inlined where separate reference files would fit. The '→ see docx v2 §X' pointers are clearly signaled but reference a sibling skill, not a bundle. In-file sectioning is good, which lifts it above 2, but the bulk of detail is not split out, which keeps it below 4.

3 / 5

Total

16

/

20

Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong frontmatter description: concrete capability list, explicit 'Trigger on:' clause with natural synonyms, and a stated output format. The only weakness is minor trigger overlap with the base docx skill on generic terms like 'cross-reference' and 'footnotes/endnotes'.

DimensionReasoningScore

Specificity

The description enumerates concrete capabilities — 'journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout' — with no vague filler. It matches the score-5 anchor (multiple specific concrete actions, comprehensive coverage); there is no meaningful coverage gap that would justify 4.

5 / 5

Completeness

It explicitly answers both questions: what ('build academic-style .docx output: … numbered equations … bibliography, or multi-column journal layout') and when ('Trigger on: …'), plus the output contract ('Output is a single .docx'). This matches the score-5 anchor — clear what AND when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Triggers include natural user phrasing and synonyms: 'research paper', 'journal paper', 'conference paper', 'manuscript', 'thesis', 'APA', 'MLA', 'Chicago', 'IEEE two-column', 'bibliography', 'hanging indent', 'citation style', 'abstract + keywords', 'equation numbering', 'cross-reference'. Coverage is comprehensive including style-name synonyms; nothing natural is missing that would drop it to 4.

5 / 5

Distinctiveness Conflict Risk

The academic-venue niche is clear and most triggers (APA, thesis, IEEE two-column, citation style) are distinct, but generic terms like 'cross-reference' and 'paper with footnotes/endnotes' create minor overlap with a closely related general docx skill, and the description does not state that boundary (it lives in the body). Fits the score-4 anchor (mostly distinct, minor overlap risk with closely related skills) better than 5.

4 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (508 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
iOfficeAI/OfficeCLI
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.