tooluniverse-literature-deep-research

Deep literature review — PubMed, EuropePMC, bioRxiv preprints, citation networks, evidence synthesis. Disambiguates queries, runs collision-aware searches, grades evidence T1-T4, and produces structured reports. Use for systematic literature review, meta-analysis evidence collection, and detailed answer-with-citations workflows.

Quality

98%

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

Quality

Content

96%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 tightly written, highly actionable multi-phase workflow with strong validation and feedback loops. Its only gap is that the five referenced companion files are not present in the bundle to confirm the progressive-disclosure structure resolves as signaled.

Suggestions

Ship the five referenced companion files (TOOL_NAMES_REFERENCE.md, REPORT_TEMPLATE.md, FULLTEXT_STRATEGY.md, WORKFLOW.md, EXAMPLES.md) in ./references/ so the signaled navigation actually resolves.

Consider a one-line note in the References section clarifying each file's trigger (e.g., 'open when writing the report' for REPORT_TEMPLATE.md) to make progressive disclosure intent explicit.

Verify referenced tool names and parameters against TOOL_NAMES_REFERENCE.md so the inline signatures stay accurate as the tool set evolves.

Dimension	Reasoning	Score
Conciseness	Dense and bullet/table-driven with no padding about concepts Claude already knows; every line carries a tool name, parameter, or decision rule, matching the lean-and-efficient anchor.	5 / 5
Actionability	Provides executable tool-call signatures (e.g., "EuropePMC_search_articles(query=\"term1 term2 term3\", limit=5)") and concrete query templates with collision filters, matching the copy-paste-ready anchor.	5 / 5
Workflow Clarity	Clear four-phase sequence (Phase 0→1→2→3) with explicit validation checkpoints and feedback loops — collision detection (">20% off-topic"), PubMed zero-result fallback ("Always retry with EuropePMC... not optional"), and retry→fallback chains — matching the explicit-validation-with-error-recovery anchor.	5 / 5
Progressive Disclosure	Well-organized body with a clear References section signaling five one-level-deep files (TOOL_NAMES_REFERENCE.md, REPORT_TEMPLATE.md, etc.), but the referenced bundle files are not present in ./references/ to verify, so it sits just below the fully-resolved one-level-deep anchor.	4 / 5
	Total	19 / 20 Passed

Description

100%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 is strong across all dimensions: concrete actions, natural trigger phrases, explicit use-when guidance, and a clearly bounded niche. It cleanly separates literature synthesis from entity profiling via delegation. No meaningful weakness to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full workflow — "Disambiguates queries, runs collision-aware searches, grades evidence T1-T4, and produces structured reports" — matching the comprehensive-coverage anchor rather than the minor-gaps level 4.	5 / 5
Completeness	Explicitly answers both what (the listed actions) and when ("Use for systematic literature review, meta-analysis evidence collection, and detailed answer-with-citations workflows"), matching the concrete-trigger-phrases anchor exactly.	5 / 5
Trigger Term Quality	Covers natural user phrases and synonyms — "literature review", "systematic literature review", "meta-analysis", "evidence collection", "answer-with-citations" plus named sources (PubMed, EuropePMC, bioRxiv) — matching the comprehensive synonym coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — deep literature research with specific DBs and citation networks — with distinct triggers and minimal overlap with the sibling entity-profiling skills it explicitly delegates to.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-literature-deep-research/SKILL.md
Commit: 7a0ceb2

Reviewed: 3 days 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.