This skill should be used when the user asks to "set up paper search", reports "paper-search command not found", wants to "replace paper search MCP", or needs help with paper search credentials.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Use fcakyon/paper-search-cli for paper searches, DOI lookup, PDF downloads, and text extraction. It requires uv and Python 3.10+; Docker and an MCP server are unnecessary.
Run uv --version. If missing, follow the uv installation instructions.
Install the CLI:
uv tool install 'git+https://github.com/fcakyon/paper-search-cli'
Run paper-search --help and paper-search sources. If the command is not on PATH, run uv tool update-shell and open a new shell.
Check a public source:
paper-search search 'object detection' -s crossref -n 3
Inspect the JSON errors field before declaring the search successful. An empty result or a provider error does not confirm working access.
For updates, run uv tool upgrade paper-search-cli.
Use the CLI's .env.example for provider keys. Its current configuration path is ~/.config/paper-search-mcp/.env; the legacy path and PAPER_SEARCH_MCP_* names remain supported. Do not print secret values.
IEEE, Scopus, and Web of Science need credentials. Scopus and Web of Science require explicit source selection. Unpaywall needs an email. Metadata access does not guarantee access to a PDF.
This plugin no longer registers the Docker MCP server. Reload the updated plugin to discard its old registration. If the user separately configured a paper-search MCP entry, identify that entry and remove it only when requested; preserve other servers. Run CLI commands directly without waiting for an MCP connection.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".
日本語の概要は準備中です。原文の説明を表示しています。
Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.
日本語の概要は準備中です。原文の説明を表示しています。
Build, debug, or review Cloudflare Agents SDK applications using the agents package.
日本語の概要は準備中です。原文の説明を表示しています。
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
日本語の概要は準備中です。原文の説明を表示しています。
This skill should be used when user asks to "query Azure resources", "list storage accounts", "manage Key Vault secrets", "work with Cosmos DB", "check AKS clusters", "use Azure MCP", or interact with any Azure service.
日本語の概要は準備中です。原文の説明を表示しています。
Build and troubleshoot Cloudflare Basin analytics workflows with Basin Pipelines, Basin Catalog, and Basin SQL. Use for streaming data into R2 Iceberg tables, managing catalogs, or querying those tables; also use for requests using the former Data Platform, Pipelines, R2 Data Catalog, or R2 SQL names.
日本語の概要は準備中です。原文の説明を表示しています。