journal-club-presenter
Generate journal club slides with background, critique, and discussion.
28
20%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/journal-club-presenter/SKILL.mdQuality
Discovery
32%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 identifies a specific niche (journal club slides) and mentions key sections (background, critique, discussion), but lacks a 'Use when...' clause, detailed concrete actions, and sufficient trigger term coverage. It would benefit from explicit trigger guidance and more natural keyword variations to help Claude reliably select this skill.
Suggestions
Add a 'Use when...' clause with trigger terms like 'journal club', 'paper review', 'research presentation', 'critique a paper', 'discuss a study'.
Expand the specificity of actions, e.g., 'Summarizes research papers, generates structured slides with background context, methodological critique, key findings, and discussion questions for journal club presentations'.
Include common keyword variations users might say, such as 'paper presentation', 'literature review slides', 'scientific article discussion', or '.pptx'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (journal club slides) and lists some actions (background, critique, discussion), but these are more like section names than concrete actions. It doesn't specify formats, tools, or detailed operations. | 2 / 3 |
Completeness | Describes what it does (generate journal club slides) but has no 'Use when...' clause or equivalent explicit trigger guidance. Per the rubric, a missing 'Use when' clause caps completeness at 2, and the 'what' is also only moderately detailed, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes 'journal club' and 'slides' which are natural terms users would say, but misses common variations like 'paper review', 'presentation', 'research paper', 'scientific article', or file format terms like '.pptx'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Journal club' is a fairly specific niche term that distinguishes it from generic presentation skills, but 'slides' could overlap with general presentation creation skills. The lack of explicit trigger conditions increases conflict risk. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a generic boilerplate template with minimal domain-specific content about journal club presentation generation. The vast majority of the document consists of reusable scaffolding (risk assessment, security checklist, lifecycle status, response template) that wastes tokens without teaching Claude anything about creating effective journal club slides. The actual task-relevant content (parameters, use cases, returns) amounts to a few bullet points buried in an otherwise generic framework.
Suggestions
Replace the generic workflow with a journal-club-specific workflow: e.g., 1) Extract key findings from paper, 2) Identify study design and methods, 3) Generate background context slides, 4) Create critical appraisal slides (bias assessment, statistical validity), 5) Formulate discussion questions.
Add a concrete example showing input (paper details) and expected output (actual slide outline with content for each slide), so Claude knows exactly what format and depth to produce.
Remove boilerplate sections that add no task-specific value: Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, and Response Template. These consume tokens without improving Claude's ability to generate journal club slides.
Provide actionable guidance on critical appraisal frameworks (e.g., CASP checklist items to evaluate, common statistical pitfalls to highlight) rather than abstract instructions like 'Critical evaluation points'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template) that add no actionable value for the task. Many sections are generic templates not tailored to journal club presentation generation. Self-referential links like 'See ## Prerequisites above' and 'See ## Workflow above' add confusion. The actual domain-specific content (Parameters, Returns, Use Cases) is buried under layers of generic scaffolding. | 1 / 3 |
Actionability | No concrete guidance on how to actually generate journal club slides. The workflow steps are entirely abstract ('Confirm the user objective', 'Validate that the request matches the documented scope'). There's no example of what a slide outline looks like, no sample input/output, no executable code showing how the script processes a paper PDF into slides. The 'Example' section just says '20-min presentation with 8 slides' with no actual content. | 1 / 3 |
Workflow Clarity | The workflow is a generic 5-step process that could apply to any skill and provides no journal-club-specific sequencing. There are no validation checkpoints specific to slide generation (e.g., verifying figure extraction, checking critique completeness). The 'Example run plan' is slightly more concrete but still lacks real validation steps for the actual deliverable quality. | 1 / 3 |
Progressive Disclosure | References to `scripts/main.py` and `references/` directory suggest some structure, but no bundle files are provided to verify. The document references `references/audit-reference.md` which is reasonable one-level-deep disclosure. However, the main document itself is a monolithic wall of boilerplate sections that should have been trimmed rather than split into separate files. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
73f6514
- 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.