SKILL·36309E

bgpt-paper-search

K-Dense-AI
Aktualisiert 27 days ago
7 Ansichten
48,722
4,378
48,722
Auf GitHub ansehen
Dokumentationai

Über

Diese Fähigkeit durchsucht wissenschaftliche Artikel über BGPT, um belegende Aussagen aus Volltexten zu extrahieren, einschließlich Experimenten, Statistiken und Einschränkungen. Sie wurde für Entwickler konzipiert, die Literaturrecherche- oder Evidenzsynthese-Funktionen aufbauen, und geht über Abstracts hinaus, um detaillierte experimentelle Daten zu gewinnen. Zur Nutzung benötigen Sie eine konfigurierte BGPT-MCP-Verbindung und Internetzugang zu bgpt.pro.

Schnellinstallation

Claude Code

Empfohlen
Primär
npx skills add K-Dense-AI/claude-scientific-skills -a claude-code
Plugin-BefehlAlternativ
/plugin add https://github.com/K-Dense-AI/claude-scientific-skills
Git CloneAlternativ
git clone https://github.com/K-Dense-AI/claude-scientific-skills.git ~/.claude/skills/bgpt-paper-search

Kopieren Sie diesen Befehl und fügen Sie ihn in Claude Code ein, um diese Fähigkeit zu installieren

Dokumentation

BGPT Paper Search

When to use

Use BGPT to find full-text-derived evidence for a research question or a known DOI. It returns extracted claims and their supporting experiments, rather than only bibliographic metadata. Use these records to build a traceable evidence table; they are not a complete systematic-review search or a validated risk-of-bias assessment.

Connect

Configure BGPT in the host before use; installing this skill does not register an MCP server. The provider supports both transports:

TransportEndpoint
Streamable HTTPhttps://bgpt.pro/mcp/stream
SSEhttps://bgpt.pro/mcp/sse

Use the host's native remote-MCP configuration when supported. For a host that uses mcpServers JSON and requires a local stdio bridge, this configuration uses mcp-remote (adapt it to the host's actual settings format):

{
  "mcpServers": {
    "bgpt": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://bgpt.pro/mcp/stream", "--transport", "http-only"]
    }
  }
}

The published bgpt-mcp 1.1.0 npm package is a thin SSE wrapper around mcp-remote, not a local paper database. Its bundled README predates the current tool contract and pricing. Prefer the native connection or configurable bridge above. The linked BGPT GitHub repository was unavailable at review time; use the current provider documentation and live tool schema.

Free access needs no key. For paid usage, configure Authorization: Bearer <key> in the host's remote-server headers, using its credential storage. For the bridge, mcp-remote supports --header-file with a local credential file. Do not put api_key in an MCP tool call: neither current tool declares that argument. Authenticate through the connection.

Search and DOI lookup

Discover the connected server's tools before calling them. The live BGPT 2.14.7 schema reviewed on 2026-09-30 exposes:

Tool / argumentContract
search_papers.queryRequired string. Use short English search terms.
num_resultsInteger, 1–100; default 16. Set it explicitly to control result use.
days_backOptional integer; papers published within the last N days. Omit for all dates.
min_citationsOptional integer; minimum number of references cited by the paper, not citations received.
study_typeOptional string: primary study, systematic review, meta-analysis, narrative review, protocol, dataset, commentary, or other.
output_formatevidence (default), full, or legacy.
lookup_paper.doiRequired DOI string; also accepts output_format. A found paper counts as one result.

Use the filter arguments instead of putting years or filters into the query. No Boolean-query grammar, offset, page, or cursor is documented by this schema. A result limit is not pagination: do not invent continuation arguments or claim the search enumerates every matching paper. For broader coverage, run explicit question variants and deduplicate by DOI while retaining the query history.

Search example verified with one public result (invoke through the connected tool interface):

{"query": "CRISPR human cells", "num_results": 1, "output_format": "full"}

Illustrative filtered search (filters were schema-checked, not executed):

{"query": "CRISPR delivery neurons", "num_results": 5, "days_back": 90, "study_type": "primary study", "output_format": "evidence"}

For a paper already identified, call lookup_paper with its bare DOI rather than hoping a title search returns that exact paper:

{"doi": "10.1016/j.ymeth.2015.10.014", "output_format": "evidence"}

Do not interpret a connection, quota, or tool error as an empty evidence set. The provider publishes a result allowance, but no numeric request-rate limit on the reviewed page; avoid assuming unlimited request throughput.

Read the result contract

Search returns an envelope with a results list and count; record the returned query too, since the service may rewrite search terms. DOI lookup returns found and a single result; handle not-found before reading it. Inspect the MCP result for tool errors before interpreting the envelope.

  • evidence gives compact evidence records; empty optional fields may be absent.
  • full adds legacy paper metadata to the evidence record.
  • legacy requests the older paper metadata representation. Do not assume every paper has all previously advertised fields or a quality score.

The provider says evidence/full formats omit papers without extracted evidence. However, the live smoke test returned a record with schema_version: "legacy", extraction_status: "legacy", and an empty evidence_units list in both formats. A returned record therefore does not guarantee claim-level provenance. An empty search or unfound DOI also does not establish that the paper does not exist. Retain doi, title, publication_date, and publication_name when available, then inspect central_claim and evidence.evidence_units. Each unit links its claim to an experiment, reported statistics, demonstrated scope, and provenance. Keep the schema version: older records can have a different shape. Legacy full metadata can contain nulls, numeric strings, and serialized text instead of native lists; preserve the raw values and never execute them as code.

The provider documents V4 limits of five evidence units per record, two provenance passages per unit, and 320 characters per passage. These are bounded extractions, not the complete article. Check extraction_status, normalization_warnings, and evidence.record_provenance, including truncation information, before synthesis.

Evidence checks

For each extracted result, retain the DOI and source section, table, or figure. Verify sample sizes, units, experimental arms, reported statistics, and uncertainty against the paper before using them in a synthesis. Distinguish author-reported limitations from extraction-generated interpretations. Preserve contradictory or mixed evidence and demonstrated scope. If legacy quality scores are present, use them only as screening aids, not as a study-specific risk-of-bias assessment.

Allowance and review scope

At the review date the provider advertises 50 free results per network, then $0.02 per returned result. A successful DOI lookup counts as one result; unfound lookups cost none. Recheck the allowance and pricing before a large batch. Do not repeatedly retry a quota-exhausted request.

Sources: provider setup, record formats, and billing, live MCP endpoint, published BGPT wrapper metadata, and bridge documentation. The tool schemas, one-result full search, matching evidence-format DOI lookup, and SSE handshake were checked with unauthenticated requests. The public search/lookup returned a legacy-schema record, not a V4 fixture. Paid authentication, filtered search behavior, and host-specific configuration were not tested.

GitHub Repository

K-Dense-AI/claude-scientific-skills
Pfad: skills/bgpt-paper-search
0
agent-skillsai-scientistbioinformaticschemoinformaticsclaudeclaude-skills
FAQ

Häufig gestellte Fragen

Was ist der Skill bgpt-paper-search?

bgpt-paper-search ist ein Claude Skill von K-Dense-AI. Skills bündeln Anweisungen und Ressourcen, die Claude bei Bedarf lädt, um Aufgaben rund um bgpt-paper-search ohne zusätzliche Eingaben auszuführen.

Wie installiere ich bgpt-paper-search?

Verwende die Installationsbefehle auf dieser Seite: Füge bgpt-paper-search als Plugin zu Claude Code hinzu oder klone das Repository in dein Skills-Verzeichnis. Starte Claude danach neu, damit der Skill geladen wird.

Zu welcher Kategorie gehört bgpt-paper-search?

bgpt-paper-search gehört zur Kategorie Dokumentation.

Kann ich bgpt-paper-search kostenlos nutzen?

Ja. bgpt-paper-search ist auf AIMCP gelistet und kann kostenlos installiert werden.

Verwandte Skills

railway-docs
Dokumentation

Diese Fähigkeit ruft aktuelle Railway-Dokumentation ab, um Fragen zu Funktionen, Funktionalität oder spezifischen Dokumentations-URLs zu beantworten. Sie stellt sicher, dass Entwickler genaue, aktuelle Informationen direkt aus den offiziellen Quellen von Railway erhalten. Nutzen Sie sie, wenn Nutzer fragen, wie Railway funktioniert oder auf Railway-Dokumentation verweisen.

Skill ansehen
n8n-code-python
Dokumentation

Dieses Claude Skill bietet fachkundige Anleitung zum Schreiben von Python-Code in n8n-Code-Nodes, insbesondere für die Verwendung der Python-Standardbibliothek und den Umgang mit n8ns spezieller Syntax wie `_input`, `_json` und `_node`. Es hilft Entwicklern, die Grenzen von Python innerhalb von n8n zu verstehen, empfiehlt JavaScript für die meisten Workflows und bietet gleichzeitig Python-Lösungen für spezifische Datenumwandlungsanforderungen.

Skill ansehen
archon
Dokumentation

Die Archon-Funktion bietet semantische Suche auf RAG-Basis und Projektmanagement über eine REST-API. Nutzen Sie sie für das Abfragen von Dokumentation, die Verwaltung hierarchischer Projekte/Aufgaben und die Durchführung von Wissenabruf mit Dokumenten-Upload-Fähigkeiten. Priorisieren Sie stets Archon zuerst bei der Suche in externer Dokumentation, bevor Sie andere Quellen verwenden.

Skill ansehen
n8n-code-javascript
Dokumentation

Diese Claude-Skill bietet fachkundige Anleitung für das Schreiben von JavaScript-Code in n8n-Code-Nodes. Sie behandelt wesentliche n8n-spezifische Syntax wie `$input`/`$json`-Variablen, HTTP-Helfer und DateTime-Verarbeitung und hilft bei der Fehlerbehebung häufiger Probleme. Nutzen Sie sie bei der Entwicklung von n8n-Workflows, die eine benutzerdefinierte JavaScript-Verarbeitung in Code-Nodes erfordern.

Skill ansehen