research-article-weekly

Generates a weekly academic literature report based on keywords using PubMed. Use when the user wants to track recent research progress on a specific topic, automatically retrieving, classifying, and summarizing relevant papers from the last 7 days.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/research-article-weekly/SKILL.md

Quality

Content

61%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 skill delivers a concrete, executable PubMed workflow with useful refinement prompts and quality rules, but is weakened by generic boilerplate sections and the absence of an explicit validation/retry checkpoint in a batch-retrieval workflow.

Suggestions

Remove the generic 'When to Use', 'Key Features', and 'Implementation Details' boilerplate that restates the description or applies to any packaged skill; keep only research-article-specific guidance.

Add an explicit validation/retry step in the Workflow (e.g., check the script's JSON/Markdown output for errors or empty results and re-run with adjusted parameters) to satisfy batch-operation feedback-loop requirements.

Pin the 'requests' dependency in the Dependencies section and consider moving the AI-refinement system prompts into a references/ file referenced one level deep.

Dimension	Reasoning	Score
Conciseness	The Workflow and Quality Rules sections are efficient and useful, but 'When to Use', 'Key Features', and 'Implementation Details' contain generic boilerplate (e.g., 'a evidence insight task needs a packaged method instead of ad-hoc freeform output') and verbatim description restatements that could be trimmed.	3 / 5
Actionability	Provides a concrete, copy-paste-ready command ('python scripts/pubmed_search.py --keywords "{keywords}" --days 7 --limit 20 --format markdown') plus complete AI-refinement system prompts; minor gaps are the unpinned 'requests' dependency and the {keywords} placeholder.	4 / 5
Workflow Clarity	The four-step sequence is clearly ordered and includes an error-handling rule for empty results, but this batch retrieval workflow lacks an explicit validate-and-retry checkpoint, which caps the score per the batch-operations guidance.	3 / 5
Progressive Disclosure	Well-organized into clear sections and the referenced bundle file 'scripts/pubmed_search.py' exists and is correctly signaled; minor gap is that the inlined AI-refinement system prompts could live in a separate reference file to keep the overview leaner.	4 / 5
	Total	14 / 20 Passed

Description

87%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.

A strong, third-person description that clearly states both capability and trigger conditions with concrete, domain-specific language. It is specific to PubMed weekly reporting and unlikely to collide with unrelated skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('weekly academic literature report based on keywords using PubMed') and several concrete actions — 'retrieving, classifying, and summarizing relevant papers' — giving comprehensive coverage with only minor gaps.	4 / 5
Completeness	Explicitly answers both 'what' ('Generates a weekly academic literature report... retrieving, classifying, and summarizing') and 'when' via a concrete 'Use when the user wants to track recent research progress on a specific topic' trigger clause.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('track recent research progress', 'weekly academic literature report', 'PubMed', 'papers', 'last 7 days'), though a few common variants like 'literature search' or 'find recent articles' are missing.	4 / 5
Distinctiveness Conflict Risk	The PubMed-specific weekly literature-report niche has distinct triggers and minimal overlap with other skills; the scope ('last 7 days', PubMed) is clearly bounded.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/research-article-weekly/SKILL.md
Commit: 63c61d3

Reviewed: 5 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.