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.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/latex-posters/SKILL.md

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 content is highly actionable and the end-to-end workflow is clearly sequenced with strong validation/feedback loops, but it is severely compromised by extreme repetition and verbosity — the same AI-graphic guidance is restated many times — which bloats the file into a monolithic document that undermines the otherwise good progressive-disclosure structure.

Suggestions

Consolidate the AI-generated-graphics guidance (Sections 'AI-Powered Visual Element Generation', 'Preventing Content Overflow', 'Poster-Size Font Requirements', 'AI-Generated Graphic Sizing', Steps 0–2b, 'Visual Element Guidelines', and the Stage 2/'Common Pitfalls' restatements) into a single reference file and leave a concise summary plus a pointer in SKILL.md.

Move the long 'PDF Review and Quality Control' checklist (Steps 1–9) into assets/poster_quality_checklist.md (which already exists) and reference it, rather than reproducing it inline.

Reduce repeated callouts (e.g. the 'PATTERNS THAT ALWAYS FAIL'/'PATTERNS THAT WORK' tables appear twice with overlapping content) to a single canonical version to recover token budget.

Dimension	Reasoning	Score
Conciseness	The body is extremely verbose and repetitive — the same 3-elements/60%-white-space/120pt-font guidance is restated in the AI-generation sections, Step 0/1/2/2b checklists, the complete-workflow example, 'Visual Element Guidelines', Stage 2, and 'Common Pitfalls', padding the file far beyond what Claude does not already know after the first statement.	1 / 3
Actionability	It provides concrete, executable guidance throughout: real `python scripts/generate_schematic.py` commands with full prompt strings, copy-paste LaTeX templates for all three packages, and exact bash review commands (pdfinfo, pdffonts, grep overfull).	3 / 3
Workflow Clarity	The poster-creation workflow is clearly sequenced (Step 0 pre-generation review → generate → Step 2b post-generation review → assemble → compile → overflow check) with explicit validation checkpoints and feedback loops (regenerate-on-fail, 'DO NOT proceed if any graphic fails').	3 / 3
Progressive Disclosure	Bundle structure is sound and one-level-deep (verified references/poster_layout_design.md, references/poster_design_principles.md, references/latex_poster_packages.md, references/poster_content_guide.md, assets/.tex, scripts/.py all exist and are clearly signaled), but SKILL.md itself is a monolithic ~1590-line wall of text with deeply repeated inline content that should have been split into reference files, so the overview is not lean.	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 is specific, well-targeted, and uses strong natural trigger terms with low conflict risk, but it omits an explicit 'Use when...' trigger clause, capping its completeness. It is written in clean third-person voice with no over-claims.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when creating research or academic posters for conferences, thesis defenses, or poster sessions, or when converting a paper into a poster.' to lift completeness to 3.

Lead with concrete verbs the user will see executed (e.g. 'Generate, lay out, and compile research posters in LaTeX...') rather than the noun-heavy feature list ('Support for...', 'Includes...').

Dimension	Reasoning	Score
Specificity	The description names the domain (LaTeX research posters) and several concrete capabilities (layout design, color schemes, multi-column formats, figure integration), but it reads as a feature inventory rather than a list of concrete actions Claude performs; the verbs 'Create' and 'Support'/'Includes' are general.	2 / 3
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' trigger clause; the 'when' is only implied through the domain description, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Strong coverage of natural terms users would say: 'research posters', 'conference presentations', 'academic posters', 'scientific communication', 'multi-column formats', and named packages (beamerposter, tikzposter, baposter) match likely user phrasing.	3 / 3
Distinctiveness Conflict Risk	The niche is clear and specific — LaTeX-based research posters using named packages — making it unlikely to trigger for unrelated skills or conflict with generic document/presentation skills.	3 / 3
	Total	10 / 12 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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/scientific-agent-skills
Path: skills/latex-posters/SKILL.md
Commit: 757b63b

Reviewed: about 11 hours ago

Table of Contents

Discovery Implementation Validation

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.