lay-press-release-writer
Transform academic papers into university press releases for general.
30
23%
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/lay-press-release-writer/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 clear transformation task (academic papers to press releases) but is truncated and incomplete, ending with 'for general' which appears cut off. It lacks a 'Use when...' clause, specific concrete actions beyond 'transform', and natural trigger term variations that users might employ when requesting this type of work.
Suggestions
Complete the truncated sentence and add a 'Use when...' clause, e.g., 'Use when the user asks to convert research findings into public-facing announcements, write press releases, or communicate scientific results to a general audience.'
Add specific concrete actions such as 'Summarizes key findings, simplifies technical jargon, writes attention-grabbing headlines, and formats content for media distribution.'
Include natural trigger term variations like 'research paper', 'science communication', 'media release', 'lay summary', 'public outreach', or 'news release'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (academic papers, university press releases) and one action (transform), but does not list multiple specific concrete actions such as summarizing findings, writing headlines, simplifying jargon, or formatting for media distribution. | 2 / 3 |
Completeness | Describes what it does (transform academic papers into press releases) but has no explicit 'Use when...' clause or equivalent trigger guidance. The description also appears truncated ('for general' seems incomplete), further weakening completeness. Per rubric, missing 'Use when' caps this at 2, but the incomplete sentence pushes it to 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'academic papers', 'university', and 'press releases', but misses common variations users might say such as 'research paper', 'media release', 'science communication', 'public outreach', or 'lay summary'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'academic papers' and 'press releases' is somewhat distinctive, but could overlap with general writing/rewriting skills or science communication skills. The truncated description ('for general') reduces clarity about its specific niche. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with generic boilerplate that applies to any skill rather than providing specific guidance for transforming academic papers into press releases. The core domain-specific content (input parameters, output JSON schema, and notes about scientific accuracy) is buried among repetitive, circular, and generic sections. The skill would benefit enormously from stripping boilerplate and focusing on the actual transformation logic, writing guidelines, and press release structure conventions.
Suggestions
Remove all generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Output Requirements, Response Template) and focus on press-release-specific guidance — e.g., how to simplify jargon, structure an inverted pyramid, craft compelling headlines from research findings.
Consolidate the 5+ overlapping workflow/usage sections into a single clear workflow with press-release-specific validation steps (e.g., 'Verify headline accurately represents findings without sensationalism', 'Check reading level is appropriate for target audience').
Add a concrete end-to-end example showing actual academic paper input text and the resulting press release output, rather than just CLI flags with '...' placeholders.
Remove circular self-references ('See ## Usage above', 'See ## Workflow above') and eliminate duplicate mentions of scripts/main.py and py_compile checks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. Multiple sections reference each other circularly ('See ## Usage above', 'See ## Workflow above'). Contains boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) that add no actionable value for Claude. Explains obvious concepts and repeats the same information (e.g., 'scripts/main.py' is mentioned 8+ times, py_compile check appears 3 times). The skill could be reduced to ~30% of its current size without losing information. | 1 / 3 |
Actionability | Provides concrete CLI commands and a clear JSON output schema, which is useful. However, the actual script doesn't exist in the bundle, making the commands not truly executable. The workflow steps are generic ('Confirm the user objective', 'Validate that the request matches') rather than specific to press release generation. The input parameters table and output format are concrete and helpful. | 2 / 3 |
Workflow Clarity | The workflow section is entirely generic and could apply to any skill — it contains no press-release-specific steps. There are no validation checkpoints for the actual content transformation (e.g., checking scientific accuracy, verifying readability level). Multiple workflow-like sections exist (Example run plan, Implementation Details, Workflow, Response Template) creating confusion about which to follow. No feedback loop for reviewing generated press release quality. | 1 / 3 |
Progressive Disclosure | References 'references/audit-reference.md' and 'requirements.txt' but no bundle files are provided, making these dead references. The content is a monolithic wall of text with many redundant sections that could be consolidated. Information is scattered across overlapping sections (Example Usage vs Usage vs Examples, Workflow vs Implementation Details vs Response Template) rather than being clearly organized with appropriate depth layering. | 1 / 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.