academic-poster-generator

Complete workflow for generating academic research posters from PDF literature; use when you need to extract paper content from PDFs and produce a LaTeX-based poster (beamerposter/tikzposter/baposter) with mandatory figure generation and a final rendered HTML deliverable.

Quality

83%

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

Quality

Content

73%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.

The body is an executable, well-sequenced multi-stage pipeline with a real validation checkpoint, but it under-uses its own bundle: many reference files exist yet are not surfaced from SKILL.md, weakening navigation.

Suggestions

Link the orphaned references from the relevant sections (e.g., point to references/pdf-extraction.md in 'PDF extraction approach', references/latex-packages.md and latex_poster_packages.md in 'LaTeX package selection', references/poster-design.md and poster_layout_design.md alongside design_principles.md, references/troubleshooting.md near the pipeline, references/poster_content_guide.md in 'Content structuring rules').

De-duplicate the repeated '2-3 figures / 40-50% visual area / >= 300 DPI' mandate by stating it once in 'Figure requirements' and cross-referencing it from the pipeline stages.

Add a concrete code snippet or scripted step for the Stage E agent-rendering step (CSS injection and `<img>` validation), which is currently described only as instructions.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tight bullet lists and copy-paste commands, assuming Claude's competence; the "2-3 figures" mandate and file-policy are restated across multiple sections, which could be trimmed.	4 / 5
Actionability	Provides executable `python scripts/...` commands with real arguments and an expected output tree, but Stage E's agent-rendering step is instruction-only without concrete code, leaving a minor gap.	4 / 5
Workflow Clarity	Stages A-F are clearly sequenced with an explicit mandatory validation gate (Stage F `check_poster_quality.py`, contrast >= 4.5:1, figure-count check) and checklist references for this batch pipeline.	5 / 5
Progressive Disclosure	SKILL.md is an overview and the references it cites (design_principles.md, poster_quality_checklist.md, 3 templates) are real, but 7 of 9 reference files in the bundle (pdf-extraction, latex-packages, poster-design, poster_content_guide, poster_layout_design, troubleshooting, latex_poster_packages) are never signaled or navigated from the body.	3 / 5
	Total	16 / 20 Passed

Description

92%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.

The description is strong: it states concrete capabilities, names the supported poster packages, and gives an explicit "use when" trigger. Minor improvements would add common synonyms and file extensions for broader natural-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "extract paper content from PDFs", "produce a LaTeX-based poster (beamerposter/tikzposter/baposter)", "mandatory figure generation", "final rendered HTML deliverable" — with named packages, giving comprehensive coverage rather than just 1-2 actions.	5 / 5
Completeness	Explicitly answers both what (complete workflow: extract content → LaTeX poster → figures → rendered HTML) and when ("use when you need to extract paper content from PDFs and produce a LaTeX-based poster") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural terms ("research posters", "PDFs", "LaTeX", package names, "figure generation", "HTML") but omits common synonyms/extensions like "conference poster", ".pdf", or "scientific poster", so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (academic research posters from PDF literature) with distinct triggers and named poster packages, leaving minimal overlap risk with unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 4 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/academic-poster-generator/SKILL.md
Commit: 63c61d3

Reviewed: 10 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.