CtrlK
BlogDocsLog inGet started
Tessl Logo

latex-posters

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

56

Quality

65%

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 ./.claude/skills/latex-posters/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The skill is highly actionable and has excellent workflow clarity with strong validation checkpoints, but it is far too verbose — the AI-graphic sizing guidance is repeated across five near-duplicate sections and large reference-suitable content is kept inline rather than deferred. Consolidating the redundant graphic guidance and moving design/typography/color detail into the existing reference files would materially improve token efficiency and progressive disclosure.

Suggestions

Collapse the five near-duplicate AI-graphic sizing sections (the two CRITICAL sections, Step 0, Step 2, Stage 2, Visual Element Guidelines) into a single canonical block referenced once.

Move the inline design-principles, typography, color-scheme, and accessibility sections into the existing references/poster_design_principles.md and link to them from the body instead of re-stating them.

Trim explanations of concepts Claude already knows (basic font-size advice, 'less is more', generic color-blindness background) and keep only poster-specific, non-obvious guidance.

DimensionReasoningScore

Conciseness

The ~1590-line body is heavily verbose and repetitive: the same '3 elements / giant fonts / 60% white space / readable from 12 feet' AI-graphic guidance is restated in at least five near-duplicate sections, with extensive CAPS/bold repetition and basic concepts Claude already knows (typography, 'less is more', color-blind palettes).

1 / 3

Actionability

Provides fully executable, copy-paste-ready guidance throughout — real pdflatex/lualatex commands, full \documentclass and template examples, complete generate_schematic.py invocations with literal prompts, pdfinfo/pdffonts/pdfimages checks, and an entire review_poster.sh script.

3 / 3

Workflow Clarity

Multi-step workflow with explicit validation checkpoints and feedback loops: a mandatory Step 0 pre-generation checklist, Step 2b post-generation PASS/FAIL review with 'DO NOT PROCEED if ANY graphic fails', and Section 11 overflow checks with a ranked fix hierarchy and regenerate-and-retry loop.

3 / 3

Progressive Disclosure

References real one-level-deep files (four references/*.md, assets/ templates, scripts/) with signaled navigation, but the SKILL.md itself re-inlines vast amounts that belong in those references (design principles, typography, color schemes, accessibility), matching the anchor of content that should be separate kept inline.

2 / 3

Total

9

/

12

Passed

Description

67%

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 specifies concrete capabilities and a distinct niche well, but omits any explicit 'when to use' trigger clause, which caps its completeness. Trigger terms cover the domain but miss the most natural user phrasings. Adding a 'Use when...' clause with common phrasings like 'poster session' or 'make a conference poster' would raise both completeness and trigger quality.

Suggestions

Add an explicit trigger clause such as 'Use when creating conference or academic posters, preparing a poster session, or converting a paper into a poster.'

Replace jargon like 'scientific communication' with natural user phrasings ('make a poster', 'poster session', 'conference poster').

Lead with verb-driven actions and trim the noun-listing tail ('Support for... / Includes...') to keep the description action-dense and concise.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and named packages ('Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter', 'layout design, color schemes, multi-column formats, figure integration'), matching the anchor for several specific concrete actions; the 'Support for'/'Includes' phrasing drifts toward feature-listing but stays action-oriented.

3 / 3

Completeness

Clearly answers 'what' with specific packages and capabilities, but the 'when' is entirely missing — there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

Has solid domain keywords ('research posters', 'conference presentations', 'academic posters', 'LaTeX', package names) but misses common natural phrasings a user would actually say ('make a poster', 'poster session', 'conference poster'); 'scientific communication' reads more as jargon than a trigger.

2 / 3

Distinctiveness Conflict Risk

Targets a clear, narrow niche ('research posters in LaTeX using beamerposter, tikzposter, or baposter') with distinct triggers unlikely to overlap with or mis-trigger other skills.

3 / 3

Total

10

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1597 lines); consider splitting into references/ and linking

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
K-Dense-AI/claude-scientific-writer
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.