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.

72

Quality

88%

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%

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

The body is highly actionable with a rigorous, validated workflow, but it is monolithic and repeats several rules (hanging indent, SEQ cached-value trap, section-numbering convention) across sections. Splitting the per-style citation recipes and the equations/multi-column guides into reference files and de-duplicating the repeated caveats would lift both conciseness and progressive disclosure.

Suggestions

De-duplicate the hanging-indent rule, the SEQ cached-value trap, and the section-numbering convention — state each once and link from the other sections to remove ~3 repeated passages.

Move the four per-style citation recipes (APA, Chicago, IEEE, MLA) and the multi-column / equations guides into reference files under references/, keeping SKILL.md as an overview with a decision table and one-level-deep pointers.

Trim venue background Claude already knows (e.g. what footnotes vs endnotes are, what IEEE is) to the skill-specific deltas only.

DimensionReasoningScore

Conciseness

The file is dense and mostly assumes competence, but it re-explains the same rules in multiple places — the hanging-indent canonical form recurs in Requirements, the APA recipe, the Bibliography section, and Known Issues; the SEQ cached-value trap recurs in the cross-refs section, Gate 5a, and Known Issues — so it is efficient but could be tightened rather than earning the lean score-3.

2 / 3

Actionability

Every section ships copy-paste-ready executable bash (create/open/add/close/validate, raw-set SEQ patches, query-based QA), with concrete prop values and exact xpath expressions, matching the fully-executable score-3 anchor.

3 / 3

Workflow Clarity

A 5-verb workflow plus an executable Delivery Gate (Gates 1–5b) with explicit validate→reject→exit feedback loops and a per-page visual audit checklist satisfies the clear-sequence-with-validation score-3 anchor.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), so the ~500-line skill is a single monolithic file with the four per-style recipes, equations, and multi-column guide all inline; cross-references to the sibling docx skill are clearly signaled ('→ see docx v2 §X'), but content that could be split into reference files is not, landing at score 2.

2 / 3

Total

10

/

12

Passed

Description

100%

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

The description is strong across all four dimensions: it states concrete capabilities, supplies an explicit trigger list, answers both what and when, and carves out a distinct academic niche. It is one of the better-constructed skill descriptions, with only minor room to tighten the long trigger enumeration.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'build academic-style .docx output', 'formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout' — matching the score-3 anchor of several specific concrete actions.

3 / 3

Completeness

Clearly answers both 'what' (build academic-style .docx with citations, equations, cross-refs, bibliography, multi-column) and 'when' via an explicit 'Trigger on:' clause and a closing scope statement ('Output is a single .docx'), matching the score-3 anchor.

3 / 3

Trigger Term Quality

An explicit 'Trigger on:' list covers natural user phrasings ('research paper', 'journal paper', 'conference paper', 'manuscript', 'thesis', 'APA', 'MLA', 'Chicago', 'IEEE two-column', 'bibliography', 'hanging indent', 'citation style'), giving good coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

Scopes to a clear academic niche with distinct triggers (citation styles, equations, IEEE two-column, hanging indent) unlikely to fire for generic docx work; the score-2 'could overlap' concern is mitigated by the venue/citation-style vocabulary.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (505 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
Team-Commonly/commonly
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.