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.

73

Quality

91%

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

88%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 exceptionally actionable, well-validated skill body with executable recipes for every citation style and an honest, gated QA process. Its main weaknesses are cross-section repetition of a few rules and a monolithic structure that could offload the long per-style recipes into reference files.

Suggestions

De-duplicate rules stated in multiple places (caption placement, hanging-indent pair, section-break +1 offset) by stating each once and cross-referencing from the other locations.

Move the four per-style citation recipe details into a references/ file (e.g. CITATION_STYLES.md) and keep SKILL.md as the decision guide + Quick Start, improving progressive disclosure.

Tighten the 'What academic means here (identity)' section, which restates deltas already enumerated in the Requirements section.

DimensionReasoningScore

Conciseness

Dense with genuinely non-obvious, high-value content (SEQ cached-value trap, /section[last()] rejection, OMML pitfalls) and assumes Claude's competence, but several rules are restated across sections — caption placement, hanging-indent pair, and section-break +1 offset each appear 2-3 times — which could be trimmed.

4 / 5

Actionability

Fully executable, copy-paste-ready bash throughout: a ten-line Quick Start that validates clean, complete per-style citation recipes (APA/Chicago/IEEE/MLA), equation insertion, SEQ/PAGEREF fields, and the multi-column recipe — all with exact --prop flags and QA grep commands.

5 / 5

Workflow Clarity

Clear 5-verb workflow sequence followed by an executable Delivery Gate with explicit validation checkpoints (Gate 4 citation round-trip, Gate 5a SEQ presence + distinct cached numbers), REJECT/fix/re-validate feedback loops, and an 8-item visual audit checklist (Gate 5b).

5 / 5

Progressive Disclosure

Well-organized into clear sections and models itself as a scene layer with one-level-deep '→ see docx v2 §X' references, but no bundle files exist and the four full per-style citation recipes plus equations/multi-column are all inlined in a ~500-line SKILL.md rather than split into separate reference files.

4 / 5

Total

18

/

20

Passed

Description

95%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, specific description with comprehensive trigger coverage and an explicit use-when clause. Its only weakness is the second-person 'Use this skill to build...' framing, which costs it the specificity voice bonus.

Suggestions

Rephrase the opening in third person / imperative action voice (e.g. 'Build academic-style .docx output: ...') instead of 'Use this skill to build...' to satisfy the third-person voice guideline.

Consider adding the file extension '.docx' explicitly to the trigger list alongside the style names for even denser keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete academic actions — 'formal citation style (APA, Chicago, IEEE, MLA)', 'numbered equations', 'figure & table cross-references', 'footnotes/endnotes', 'bibliography', 'multi-column journal layout' — but the second-person framing 'Use this skill to build...' triggers the voice penalty, reducing the score by one.

4 / 5

Completeness

Explicitly answers both 'what' (build academic-style .docx with the listed features) and 'when' via a concrete 'Trigger on:' clause with concrete trigger phrases, and closes with 'Output is a single .docx.'

5 / 5

Trigger Term Quality

Comprehensive natural trigger list including synonyms and style names a user would actually say: 'research paper', 'journal paper', 'conference paper', 'manuscript', 'thesis', 'APA', 'MLA', 'Chicago', 'IEEE two-column', 'bibliography', 'hanging indent', 'citation style', 'equation numbering', 'cross-reference'.

5 / 5

Distinctiveness Conflict Risk

Clear academic-paper niche with distinct triggers (citation styles, equations, SEQ/PAGEREF cross-refs, multi-column) unlikely to fire for general docx work; minimal conflict risk.

5 / 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.

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.