bgpt-paper-search

Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.

Quality

92%

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

85%

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

A well-organized, concise single-file skill body with copy-paste setup config and a clear single-action workflow. Its main weakness is actionability: the actual tool invocation is described abstractly without the parameter details a caller needs.

Suggestions

Document the `search_papers` tool's parameters (e.g., query string, filters, result limit) and show a concrete example call with arguments, not just an illustrative query string.

Specify how results are returned (shape/structure of the 25+ fields) so the agent knows how to parse and present them.

Clarify whether an API key must be passed to the tool call for paid usage, or is handled by the MCP server configuration.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence: tight Setup config, a focused 'When to Use' list, and a compact returns summary. The Overview's one comparative sentence describes the proprietary BGPT server (which Claude does not already know) rather than restating generic concepts, so tokens earn their place.	3 / 3
Actionability	The MCP config JSON and `npx bgpt-mcp` command are concrete and copy-paste ready, but the core invocation is left as 'call its `search_papers` tool via the agent's MCP interface' with only an illustrative query string and no documented parameters/argument schema for the tool itself.	2 / 3
Workflow Clarity	This is a simple single-task skill (configure the server, then call search_papers) and the sequence is unambiguous: Setup -> Usage. No destructive or batch operations are involved, so the absence of validation checkpoints does not cap the score per the simple-skills note.	3 / 3
Progressive Disclosure	No bundle files exist, and the single-file body is well-organized into clearly signaled sections (Overview, When to Use, Setup, Usage, Pricing) with no nested references — appropriate for a concise skill that needs no external materials.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, third-person description that states concrete capabilities, lists specific returned fields, and provides an explicit 'Use for...' trigger covering several natural phrasings. It clearly distinguishes the skill from generic literature-search tools.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Search scientific papers and retrieve structured experimental data', 'Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions' — naming both the operation and the specific returned fields.	3 / 3
Completeness	Explicitly answers what it does (search/retrieve structured experimental data via BGPT MCP, 25+ fields) and when to use it ('Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone'), satisfying both halves with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural user terms a researcher would say — 'scientific papers', 'literature reviews', 'evidence synthesis', 'experimental details not available in abstracts' — giving good keyword coverage for triggering.	3 / 3
Distinctiveness Conflict Risk	The niche is narrow and specific — structured experimental data from full-text studies via the named BGPT MCP server — with distinct triggers (evidence synthesis, full-text experimental details) unlikely to conflict with generic search skills.	3 / 3
	Total	12 / 12 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: K-Dense-AI/scientific-agent-skills
Path: skills/bgpt-paper-search/SKILL.md
Commit: 757b63b

Reviewed: about 11 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.