tooluniverse-literature-deep-research

Conduct comprehensive literature research with target disambiguation, evidence grading, and structured theme extraction. Creates a detailed report with mandatory completeness checklist, biological model synthesis, and testable hypotheses. For biological targets, resolves offic...

Quality

61%

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/tooluniverse-literature-deep-research/SKILL.md

Quality

Content

63%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 is a thorough, well-sequenced, evidence-grading research strategy with strong actionability and clear validation checkpoints, but it is monolithic and verbose: the full report template and bibliography format are inlined and the tool catalog is duplicated across several sections. Splitting large templates into reference files and deduplicating tool lists would meaningfully improve it.

Suggestions

Move the 15-section report template and bibliography JSON format into reference files (e.g., references/report_template.md, references/bibliography_format.md) and link to them from SKILL.md.

Deduplicate the tool catalog: keep one canonical list (the Quick Reference section) and reference it elsewhere instead of repeating tool names in Phase 1 and Phase 2.2.

Tighten the three-tier full-text verification section by consolidating the repeated Advantages/Limitations/When-to-use blocks into a single decision matrix.

Dimension	Reasoning	Score
Conciseness	The body is mostly high-signal domain guidance (it does not re-explain concepts Claude already knows), but at ~1064 lines it repeats the tool catalog in four places (Phase 1.1/1.3-1.6, Phase 2.2, and Quick Reference) and inlines a ~270-line report template that could be trimmed or moved out.	3 / 5
Actionability	Concrete, executable tool calls with real parameters are given throughout (e.g., EuropePMC_search_articles with extract_terms_from_fulltext, SemanticScholar_get_pdf_snippets with window_chars), plus specific query strings and fallback chains; minor gaps remain where examples use illustrative loops with 'pass'.	4 / 5
Workflow Clarity	Phases 0-3 are clearly sequenced with a 'Verify Before Delivery' completeness checklist, evidence-grading quality gates, and a retry/fallback error-recovery loop; inter-phase validation gates are implicit rather than explicit 'only proceed when X passes' gates.	4 / 5
Progressive Disclosure	Section headers organize the content well, but no bundle files exist and content that clearly belongs in separate reference files (the 15-section report template, bibliography JSON format, theme-extraction protocol) is inlined into a single 33KB SKILL.md.	3 / 5
	Total	14 / 20 Passed

Description

58%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.

The description conveys a clear, specific 'what' for an evidence-graded deep literature research skill, but it is truncated mid-sentence and lacks any explicit 'Use when...' trigger guidance. Trigger-term naturalness is also middling, leaning on methodology jargon over user-natural phrases.

Suggestions

Complete the truncated sentence (e.g., 'For biological targets, resolves official IDs, synonyms, and naming collisions before search.') and cap the description cleanly.

Add an explicit 'Use when...' clause with concrete triggers, e.g., 'Use when conducting a literature review, surveying papers on a gene/protein, or building an evidence-graded research report.'

Add user-natural synonyms such as 'literature review', 'find papers', 'survey the literature', and 'PubMed/PMC' alongside the methodology terms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('target disambiguation, evidence grading, and structured theme extraction', 'mandatory completeness checklist, biological model synthesis, and testable hypotheses'), but the final action is truncated ('resolves offic...') leaving a minor gap.	4 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause, and the only 'when' hint ('For biological targets, resolves offic...') is truncated, so completeness is capped at 3 per the missing-trigger guidance.	3 / 5
Trigger Term Quality	'literature research' is a natural user phrase, but common variations like 'literature review', 'find papers', 'survey the literature', or gene/protein-research triggers are missing in favor of methodology jargon.	3 / 5
Distinctiveness Conflict Risk	The evidence-graded deep-research-with-disambiguation niche is mostly distinct from a generic research skill, with only minor overlap risk against plain literature-review skills.	4 / 5
	Total	14 / 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
skill_md_line_count	SKILL.md is long (1064 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/tooluniverse-literature-deep-research/SKILL.md
Commit: 63c61d3

Reviewed: 4 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.