research-lookup

Compile current scholarly evidence for a scientific manuscript or research brief. Use when the user explicitly asks to gather literature, references, background evidence, competing findings, or a manuscript research packet. Uses Parallel Search by default, Parallel Extract for source verification, Parallel Research for explicitly deep/exhaustive work, optional explicit Parallel Chat, and optional Perplexity only when requested or allowed as a failure fallback.

Quality

89%

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

88%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-structured, highly actionable skill with a clear sequenced workflow, verification checkpoints, and copy-paste commands for every backend. Its main weakness is mild verbosity from repeated routing explanations and limited use of separate reference files for bulk detail.

Suggestions

Consolidate the per-backend routing sections (Explicit Chat, Perplexity fallback, Fast lookup, Batch) into the routing table plus a single example each, removing restated selection rules.

Move the packet-file enumeration and detailed CLI flag reference into a references/ file (e.g. PACKET_FORMAT.md) and link from the body to tighten progressive disclosure.

Trim the citing-instructions section to the essential reference and the 'fetch current version' rule.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and action-oriented with little padding of concepts Claude already knows, but the multiple routing sections (Chat, Perplexity, fast lookup, batch) re-explain selection behavior already summarized in the routing table, and the citation section is verbose.	4 / 5
Actionability	Every backend mode ships a copy-paste-ready bash command with concrete flags (--academic, --force-backend, --context-file, --target-references) and a worked context-file JSON example covering the common cases.	5 / 5
Workflow Clarity	The five-step manuscript workflow is explicitly numbered and sequenced with a verification checkpoint (Parallel Extract), plus a coverage/shortfall feedback loop and a failure-handling section with recovery steps; batch operations isolate failures per query.	5 / 5
Progressive Disclosure	Section structure is clear and the bundled script it references (scripts/research_lookup.py) exists, but the full packet-file enumeration and CLI flag surface are inlined rather than split into reference files, and no references/ bundle is used for the bulk detail.	4 / 5
	Total	18 / 20 Passed

Description

91%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 description that clearly answers both 'what' and 'when' with concrete, natural trigger phrases. It is slightly backend-list heavy and could better distinguish itself from adjacent research skills.

Dimension	Reasoning	Score
Specificity	Names the domain (scholarly evidence for manuscripts) and several concrete actions (compile evidence, source verification via Extract, deep research, Chat synthesis), but the action list leans on backend enumeration rather than manuscript-specific tasks, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly states what it does ('Compile current scholarly evidence for a scientific manuscript or research brief') and provides a concrete 'Use when...' clause with specific trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases — 'gather literature, references, background evidence, competing findings, or a manuscript research packet' — that a researcher would actually say, with good synonym coverage.	5 / 5
Distinctiveness Conflict Risk	The manuscript-research-packet niche is mostly distinct, but the description does not delineate it from sibling skills like literature-review or parallel-web, leaving minor overlap risk.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/research-lookup/SKILL.md
Commit: 1e5eeff

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.