literature-search

Comprehensive scientific literature search across PubMed, arXiv, bioRxiv, medRxiv. Natural language queries powered by Valyu semantic search.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/literature/literature-search/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete commands and clear error handling, but it carries marketing fluff and a tangential SDK-integration section that hurt conciseness, and it references script files that are not present in the bundle. Trimming the marketing section, moving integration examples to a reference file, and adding a guard for the path-resolution step would improve the score.

Suggestions

Remove or drastically shrink the 'Why This Skill is Powerful' marketing section; focus on instructions Claude needs to run searches.

Add an explicit guard after the find command, e.g. 'If LITERATURE_SCRIPT is empty, fall back to ...' or verify the path before invoking.

Move the Python/TypeScript SDK integration examples into a separate reference file (e.g. references/INTEGRATION.md) and link to it, ensuring the referenced scripts/ files actually ship in the bundle.

Dimension	Reasoning	Score
Conciseness	Most of the body is concrete commands and examples, but the 'Why This Skill is Powerful' marketing bullets and the Python/TypeScript SDK integration section are padding that doesn't directly help Claude execute searches.	2 / 3
Actionability	Copy-paste-ready commands like 'scripts/search "query" 15', jq pipelines, a setup flow, and a concrete output JSON schema give fully executable guidance.	3 / 3
Workflow Clarity	The API key setup flow is a clear numbered sequence with a retry step and error handling is documented via success field/exit codes, but the script path-resolution step lacks an explicit validation checkpoint (e.g. failing when LITERATURE_SCRIPT is empty).	2 / 3
Progressive Disclosure	The file is well-sectioned, but the referenced script files (scripts/search, scripts/search.mjs) do not exist in the bundle, and the inline SDK integration examples could be split into a separate reference file.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 clearly communicates what the skill does and occupies a distinct niche, but it lacks an explicit 'Use when...' trigger clause and stops short of listing multiple concrete actions. Adding when-to-use guidance and a few more natural user phrasings would raise the score.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks for a literature review, wants to find papers across PubMed/arXiv/bioRxiv/medRxiv, or needs cross-domain scientific research.'

List concrete actions beyond 'search', such as retrieving full article text, extracting figures/images, and aggregating results from multiple sources.

Include common user phrasings like 'find papers', 'literature review', and 'preprints' alongside the source names.

Dimension	Reasoning	Score
Specificity	Quotes 'Comprehensive scientific literature search across PubMed, arXiv, bioRxiv, medRxiv' and 'Natural language queries powered by Valyu semantic search' name the domain and sources but describe essentially one action (search) rather than multiple concrete actions like retrieve full text or extract figures.	2 / 3
Completeness	The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Source names (PubMed, arXiv, bioRxiv, medRxiv) are natural trigger terms, but common user phrasings like 'find papers', 'literature review', 'preprints', and 'research' are missing, so coverage is incomplete.	2 / 3
Distinctiveness Conflict Risk	The named scientific databases and Valyu-powered semantic search define a clear niche with distinct triggers that is unlikely to conflict with other skills.	3 / 3
	Total	9 / 12 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: 10 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/literature/literature-search/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.