multi-search-engine

Query scholarly metadata and the web through Crossref, Brave, Tavily, and DuckDuckGo with a single CLI surface. Trigger when the user asks for research search, fact lookup, source discovery, or engine comparison. Results retain DOI, publication year, and authors when supplied by Crossref, then deduplicate by DOI, arXiv ID, or normalized URL. API-key engines gate themselves on the relevant environment variable; Crossref and DuckDuckGo need no key.

Quality

87%

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

82%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.

A well-organized, actionable skill body with an executable quick start, a clear engines table, and an appropriately split reference file. Slight conciseness and progressive-disclosure refinements (tighter prose, explicit reference pointers) would lift it to the top anchor.

Suggestions

Add a short 'References' section explicitly listing scripts/search.py and references/engines.md as pointers, rather than only surfacing them inside example commands and a single inline mention.

Trim the 'Boundaries' and 'Routing tips' prose to bullet-only form where the surrounding table/decision tree already conveys the same information.

Add a one-line validation hint in Quick start (e.g. checking the errors[] array or using --strict) so the workflow's error-feedback step is explicit in the getting-started path.

Dimension	Reasoning	Score
Conciseness	The body is well-sectioned and largely free of padding or explanations of concepts Claude already knows; a few prose passages (routing tips, boundary notes) could be tightened slightly but generally earn their place.	4 / 5
Actionability	The Quick start block is copy-paste executable, CLI flags are documented, the engines table gives concrete key/env-var guidance, and a full example JSON output shape is shown - covering the common cases specifically.	5 / 5
Workflow Clarity	As a single-action CLI skill the primary action is unambiguous, and the batch multi-engine operation has explicit error handling (per-engine soft errors, --strict fail-fast) plus a routing decision tree in engines.md; minor validation gaps keep it just below the explicit-checklist anchor.	4 / 5
Progressive Disclosure	SKILL.md acts as an overview with a clearly signaled one-level-deep reference ('engines.md has the full per-engine guidance') that resolves to a real file, and the executable script lives in scripts/; minor organization gaps (the script path is shown only in examples rather than as an explicit reference pointer) keep it below 5.	4 / 5
	Total	17 / 20 Passed

Description

92%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 both capabilities and explicit trigger conditions, with named engines and concrete data-handling behavior. The only minor gap is slightly less-than-comprehensive synonym coverage in trigger terms.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions - 'Query scholarly metadata and the web', 'retain DOI, publication year, and authors', 'deduplicate by DOI, arXiv ID, or normalized URL', and 'gate themselves on the relevant environment variable' - giving comprehensive, specific coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both 'what' (query/normalize/deduplicate across four named engines) and 'when' via a concrete 'Trigger when the user asks for...' clause with specific trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('research search, fact lookup, source discovery, or engine comparison') a user would plausibly say, but is missing some common synonyms and casual variations, keeping it just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (multi-engine scholarly+web search across Crossref/Brave/Tavily/DuckDuckGo) with distinct triggers and named engines, making overlap with other skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/multi-search-engine/SKILL.md
Commit: 94ac35e

Reviewed: 4 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.