pdf-to-ppt-pack

Convert research paper PDFs into literature-report PPTX decks using a fully offline workflow (extract text/figures, map captions, summarize findings, and generate slides). Use when you need to turn a PDF into a presentation deck, especially for scientific articles with figures and tables.

Quality

72%

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 ./scientific-skills/Other/pdf-to-ppt-pack/SKILL.md

Quality

Content

52%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 content gives concrete, executable commands and a reasonably clear pipeline, but it is heavily padded with a duplicated boilerplate first half and references many files/directories that are not actually bundled. The duplicated generic sections and nonexistent references hurt both conciseness and progressive disclosure.

Suggestions

Remove the duplicated boilerplate first half (lines 9–55) that restates the same When-to-Use / Key-Features / Dependencies / Implementation-Details sections already covered in sections 1–5, keeping only one version to cut roughly half the body.

Either bundle the referenced tools (tools/extract_pdf_figures.py, tools/build_cell_reports_ppt_offline.py, ppt/, PPTX/, pdf-extract/) or replace the broken references with a single accurate pointer so navigation is not dead-ended.

Tighten generic filler lines like "Use this skill when the request matches its documented task boundary" and "keep results reproducible, identify assumptions explicitly" that add tokens without actionable specifics Claude does not already know.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: it duplicates an entire first half ("When to Use", "Key Features", "Dependencies", "Example Usage", "Implementation Details") that is restated almost verbatim in sections 1–5, and adds generic boilerplate ("Use this skill when the request matches its documented task boundary") that pads without adding information.	2 / 5
Actionability	Sections 4 and 5 provide mostly executable guidance with concrete commands (`python "tools/extract_pdf_figures.py" --pdf ... --outdir ...` and the build command) and named outputs; the only minor gap is that the cited tools are not present in any bundle directory, so paths cannot be verified.	4 / 5
Workflow Clarity	The pipeline is sequenced into extraction → deck generation → validate/refine with explicit checkpoints in Step 3 (confirm slide titles, verify figure/caption mapping, edit figure_titles_zh.txt and rerun), though the validation is manual review rather than an automated verify command.	4 / 5
Progressive Disclosure	There is no bundle structure to point to (references/, scripts/, assets/ are absent) yet the body references numerous paths (tools/*.py, ppt/, PPTX/, pdf-extract/, scripts/validate_skill.py) that do not exist, and all content is inlined in one monolithic file rather than split into referenced files.	2 / 5
	Total	12 / 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.

This is a strong, specific description that clearly defines both the task and its trigger conditions with multiple concrete actions. The only minor gap is missing common synonyms and file extensions (e.g. .pdf, .pptx) in the trigger phrasing.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "extract text/figures, map captions, summarize findings, and generate slides" — giving comprehensive coverage of the skill's capabilities, matching the score-5 anchor.	5 / 5
Completeness	It explicitly states both what the skill does and when to use it via "Use when you need to turn a PDF into a presentation deck, especially for scientific articles", matching the score-5 anchor that requires concrete trigger phrases for both.	5 / 5
Trigger Term Quality	It includes natural terms users would say ("PDF", "presentation deck", "scientific articles with figures and tables") but omits common synonyms and the .pptx/.pdf file extensions, leaving it just below the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	The niche is clear and specific — converting research paper PDFs into literature-report PPTX decks offline — with distinct triggers that would not readily collide with other skills, matching the score-5 anchor.	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: 6 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/pdf-to-ppt-pack/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.