CtrlK
BlogDocsLog inGet started
Tessl Logo

latex-output

Use when user requests LaTeX format output or has provided school/journal LaTeX templates

62

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/latex-output/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

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

Highly actionable with complete, executable LaTeX scaffolding and compile commands, and a useful checklist. It is held back by some redundant concept explanations, missing explicit validation/feedback loops for compilation, and a monolithic structure that bundles reference-grade material inline.

Suggestions

Add an explicit validate-then-fix feedback loop after '验证可编译性', e.g. run xelatex, read the .log, fix reported errors, recompile until it builds.

Move the per-university template adaptations (ThuThesis, ucasthesis) and the Markdown-conversion table into a separate referenced file, leaving the body as a lean overview.

Remove the basic \section/\subsection/\subsection command list and the Markdown-to-LaTeX mapping table, since Claude already knows these.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete, well-organized examples, but it includes content Claude already knows (common sectioning commands like \section/\subsection and basic Markdown-to-LaTeX mappings) that could be trimmed.

2 / 3

Actionability

Provides copy-paste-ready main.tex, chapter .tex, references.bib templates, concrete compile commands (xelatex, latexmk), and an explicit checklist of steps to execute.

3 / 3

Workflow Clarity

A checklist sequences the work, but there are no explicit validation checkpoints or feedback loops despite the '验证可编译性' item — error recovery after a failed compile is only implied, capping clarity at 2.

2 / 3

Progressive Disclosure

It is a single ~275-line monolithic file with no bundle files (references/scripts/assets absent) and no external references; the university-template adaptations and compile notes could be split into referenced files.

2 / 3

Total

9

/

12

Passed

Description

80%Weight 40%Scale 1-3

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 concise, third-person description with an explicit 'Use when' trigger and natural keywords that give it a clear, low-conflict niche. Its main weakness is specificity: it describes the triggering condition more than the concrete actions the skill performs.

Suggestions

Add concrete actions to the description, e.g. 'Creates .tex chapter files, main.tex, and references.bib, parses user-provided school or journal LaTeX templates, and records compile commands.'

Mention the compilation step (xelatex/latexmk) since the body treats it as a core capability.

DimensionReasoningScore

Specificity

The description references concrete artifacts ('LaTeX format output', 'school/journal LaTeX templates') but names no specific actions beyond 'requests', leaving the skill's actual capabilities (creating .tex files, parsing templates, compiling) unlisted.

2 / 3

Completeness

It states the when ('Use when user requests LaTeX format output or has provided school/journal LaTeX templates') and implies the what via the trigger, using an explicit 'Use when' clause.

3 / 3

Trigger Term Quality

'LaTeX format output' and 'school/journal LaTeX templates' are exactly the natural terms a user would say when needing this skill, giving good keyword coverage.

3 / 3

Distinctiveness Conflict Risk

The LaTeX-specific trigger is a clear niche unlikely to conflict with other skills, and 'school/journal LaTeX templates' narrows it further.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Norman-bury/research-writing-skill
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.