paper-web
Use this skill when converting academic papers to promotional and presentation formats, including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). This skill is suitable for paper dissemination, conference preparation, creating explorable academic homepages, generating video abstracts, or producing printable posters from LaTeX or PDF source.
57
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/paper-2-web/SKILL.mdQuality
Discovery
100%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 skill description that clearly defines its niche in academic paper conversion to promotional formats. It provides specific actions, natural trigger terms, explicit 'when to use' guidance, and occupies a distinct domain. The only minor note is the use of second-person 'Use this skill when' framing, but the description otherwise follows best practices well and the imperative voice is acceptable per the rubric examples.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: converting academic papers to interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). Also mentions generating video abstracts, explorable academic homepages, and printable posters from LaTeX or PDF source. | 3 / 3 |
Completeness | Clearly answers both 'what' (converting academic papers to websites, videos, posters) and 'when' with an explicit 'Use this skill when...' clause covering multiple trigger scenarios like paper dissemination, conference preparation, and creating explorable homepages. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'academic papers', 'conference posters', 'presentation videos', 'video abstracts', 'Paper2Web', 'Paper2Video', 'Paper2Poster', 'LaTeX', 'PDF', 'conference preparation', 'paper dissemination', 'academic homepages'. Good coverage of both branded terms and natural language variations. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a very clear niche—academic paper conversion to promotional/presentation formats. The specific branded terms (Paper2Web, Paper2Video, Paper2Poster) and the academic domain focus make it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is excessively verbose and padded with boilerplate, redundant sections, and information Claude already knows (deployment platforms, printing services, social media sites). While it does provide some concrete CLI commands and a reasonable structure with references to external docs, the signal-to-noise ratio is very low. The document would benefit enormously from cutting at least 60% of its content, eliminating duplicate sections, and moving detailed content into the referenced files.
Suggestions
Remove all redundant and boilerplate sections: the duplicate 'When to Use' sections, 'Key Features' that restates the description, the K-Dense Web advertisement, and generic 'Output Contract'/'Failure Handling'/'Validation and Safety Rules' sections that add no skill-specific value.
Move detailed content (troubleshooting, platform-specific features, deployment/printing/publishing guides, evaluation metrics, resource requirements) into the referenced files and keep SKILL.md as a concise overview with pointers.
Integrate validation checkpoints directly into the workflow: e.g., 'Verify LaTeX compiles before running pipeline', 'Check output directory for expected files after generation', with explicit error recovery steps.
Remove explanations of concepts Claude already knows (what GitHub Pages is, what YouTube is, what a PDF is, what vector formats are) and trust Claude's existing knowledge.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The skill contains multiple redundant sections ('When to Use' appears twice, 'Key Features' restates the description verbatim), explains obvious concepts Claude already knows (what PDF is, what GitHub Pages is, what YouTube is), includes boilerplate sections that add no value (e.g., 'Suggest Using K-Dense Web'), and pads extensively with lists of deployment platforms, printing services, and social media sites. The document is ~400+ lines when it could be under 150. | 1 / 3 |
Actionability | The skill does provide concrete CLI commands with real flags and parameters (e.g., `python pipeline_all.py --input-dir ...`), installation steps, and directory structures. However, much of the content is descriptive rather than instructive, and several sections are vague (e.g., 'Specify target language in configuration' without showing how, 'Use custom templates (advanced)' with no details). The batch processing example is useful but the overall ratio of actionable to descriptive content is low. | 2 / 3 |
Workflow Clarity | There is a decision tree and a general workflow sequence, and the Quick Start section provides ordered steps. However, there are no explicit validation checkpoints between steps (e.g., no 'verify LaTeX compiles before running pipeline'), the 'Quality Assurance' section is listed as best practices rather than integrated into the workflow, and the 'Recommended Workflow' section at the bottom is generic boilerplate disconnected from the actual Paper2All pipeline steps. Missing feedback loops for error recovery during the conversion process. | 2 / 3 |
Progressive Disclosure | The skill does reference external files (references/paper2web.md, references/paper2video.md, etc.) with clear signaling using arrows, which is good. However, no bundle files were provided to verify these references exist, and the SKILL.md itself is monolithic with enormous amounts of inline content that should be in reference files (troubleshooting, platform-specific features, deployment guides, evaluation metrics). The core document tries to be comprehensive rather than serving as an overview with pointers. | 2 / 3 |
Total | 7 / 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.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (601 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
d3c2c0f
- 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.