journal-latest-issue

Retrieve the latest journal issue's table of contents and abstracts from URL/DOI/PMID/RSS/TOC sources, then generate Chinese key points locally (no external translation APIs) when a new issue needs quick review and archiving.

Quality

62%

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/journal-latest-issue/SKILL.md

Quality

Content

46%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 body documents the CLI interface well but is padded with generic boilerplate sections and references a script that is not present in any bundle, hurting both conciseness and progressive disclosure. Workflow guidance is generic rather than a skill-specific validated sequence for batch/crawl operations.

Suggestions

Remove the generic boilerplate sections (When Not to Use, Required Inputs, Recommended Workflow, Output Contract, Validation/Safety Rules, Failure Handling, Input Validation, Deterministic Output Rules, Completion Checklist) and keep only skill-specific content, de-duplicating the repeated --help shortcut and batch JSON example.

Either bundle the referenced scripts/journal_digest.py (and the input.json/output.md/output.csv conventions) under a scripts/ directory, or remove the dangling references so the body's navigation points to real files.

Replace the generic 4-step 'Recommended Workflow' with a concrete skill-specific sequence for batch/abstract-fetch runs, including a validate->fix->retry checkpoint for per-journal fetch failures.

Dimension	Reasoning	Score
Conciseness	Roughly nine boilerplate sections (When Not to Use, Required Inputs, Recommended Workflow, Output Contract, Validation/Safety Rules, Failure Handling, Input Validation, Deterministic Output Rules, Completion Checklist) are generic reminders Claude already knows, and content is repeated (the --help shortcut and batch JSON example each appear twice).	2 / 5
Actionability	Provides concrete executable commands and fully documented CLI flags (e.g. 'python scripts/journal_digest.py --journal "Nature" --rss "..."', '--json input.json'), but the referenced script is absent from the bundle and some guidance is hedged ('may attempt built-in source hints', 'exact values depend on the implementation').	4 / 5
Workflow Clarity	The 'Recommended Workflow' is generic 4-step boilerplate rather than skill-specific checkpoints, and for a batch-capable, network-crawling skill there is no concrete validate->fix->retry loop or per-journal error sequence, so the batch-validation cap applies.	3 / 5
Progressive Disclosure	The body repeatedly references scripts/journal_digest.py, input.json, output.md, and output.csv, yet no scripts/, references/, or assets/ bundle directories exist, so the references point to missing files while extensive CLI/JSON content that belongs in separate files is inlined.	2 / 5
	Total	11 / 20 Passed

Description

78%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, specific description that clearly states what the skill does and when to use it, with genuine natural trigger terms and a distinctive niche. The main weakness is the slightly generic 'when' clause and only two core actions.

Dimension	Reasoning	Score
Specificity	Names the journal-issue domain and concrete actions ('Retrieve the latest journal issue's table of contents and abstracts', 'generate Chinese key points locally') plus five explicit source types (URL/DOI/PMID/RSS/TOC), sitting above the 1-2-action anchor but short of comprehensive coverage.	4 / 5
Completeness	Explicitly answers both 'what' (retrieve TOC/abstracts, generate Chinese key points) and 'when' ('when a new issue needs quick review and archiving'), but the trigger phrase is somewhat generic rather than listing concrete scenarios, so it sits just below the fully-explicit anchor.	4 / 5
Trigger Term Quality	Includes natural query terms ('latest issue', 'table of contents', 'abstracts', 'Chinese key points', 'archiving') and real source identifiers (DOI/PMID/RSS/TOC), with only minor synonyms like 'journal'/'periodical' missing.	4 / 5
Distinctiveness Conflict Risk	The combination of journal-issue TOC retrieval with local Chinese key-point generation (no external translation APIs) is a distinct niche with clear triggers and minimal overlap risk.	5 / 5
	Total	17 / 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: 5 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/journal-latest-issue/SKILL.md
Commit: 63c61d3

Reviewed: 11 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.