跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
搜索与研究

asta-skill

Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and author discovery.

Agents365-ai · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add Agents365-ai/365-skills --skill asta-skill

技能说明


name: asta-skill description: Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and author discovery. license: MIT metadata: {"homepage":"https://github.com/Agents365-ai/asta-skill","compatibility":"Requires an MCP-capable host (Claude Code, Codex, Cursor, Windsurf, Hermes, OpenClaw/ClawHub) with the Asta MCP server registered at https://asta-tools.allen.ai/mcp/v1 using an x-api-key header. The skill does not make HTTP calls itself.","platforms":["macos","linux","windows"],"openclaw":{"requires":{"env":["ASTA_API_KEY"]},"emoji":"🔭","mcp":{"name":"asta","type":"http","url":"https://asta-tools.allen.ai/mcp/v1","headers":{"x-api-key":"${ASTA_API_KEY}"}}},"hermes":{"tags":["asta","semantic-scholar","academic","paper-search","citation","mcp"],"category":"research","requires_tools":["mcp"],"related_skills":["semanticscholar-skill","literature-review"]},"pimo":{"category":"research","tags":["asta","semantic-scholar","academic","paper-search","citation","mcp"]},"author":"Agents365-ai","version":"0.3.4"}

Asta MCP — Academic Paper Search

Asta is Ai2's Scientific Corpus Tool, exposing the Semantic Scholar academic graph over MCP (streamable HTTP transport). This skill tells agents which Asta tool to call for which intent, and how to compose them into useful workflows.

Prerequisite Check

Before invoking any tool, verify the Asta MCP server is registered in the host agent. Tool names will be prefixed by the MCP server name chosen at install time (commonly asta__<tool> or mcp__asta__<tool>).

If no Asta tools are visible, do not make raw HTTP calls or invent results. Tell the user to register https://asta-tools.allen.ai/mcp/v1 as a streamable HTTP MCP server with an x-api-key header, then restart/reload the host. Minimal setup hints:

  • Codex CLI: add [mcp_servers.asta] url = "https://asta-tools.allen.ai/mcp/v1" and env_http_headers = { "x-api-key" = "ASTA_API_KEY" } to ~/.codex/config.toml.
  • Claude Code: run claude mcp add -t http -s user asta https://asta-tools.allen.ai/mcp/v1 -H "x-api-key: $ASTA_API_KEY".
  • Generic MCP clients: configure server URL https://asta-tools.allen.ai/mcp/v1 with header { "x-api-key": "<YOUR_API_KEY>" }.

Tool Map — Intent → Asta Tool

User intentAsta toolNotes
Broad topic searchsearch_papers_by_relevanceSupports venue + date filters
Known paper titlesearch_paper_by_titleOptional venues + publication_date_range filters
Known DOI / arXiv / PMID / CorpusId / MAG / ACL / SHA / URLget_paperSingle-paper lookup
Multiple known IDs at onceget_paper_batchBatch lookup — pass ids as a JSON array (not a comma-separated string, unlike snippet_search's paper_ids); prefer over N sequential get_paper calls; unresolvable IDs are silently dropped (no null/error), so reconcile returned paperIds against your input
Who cited paper Xget_citationsForward citations, paginated; accepts publication_date_range but not venues; limit defaults to 100
Find author by namesearch_authors_by_nameDefault fields="name" returns only name + authorId — explicitly request affiliations,paperCount,citationCount,hIndex,externalIds to get anything rankable; externalIds carries ORCID/DBLP (url/homepage are also selectable)
An author's publicationsget_author_papersPass author id; field param is paper_fields (not fields); limit defaults to 1000 — set it explicitly
Find passages mentioning Xsnippet_search~500-word excerpts (title/abstract/body, excludes captions & bibliography); see snippet-specific params below

Most search/citation tools accept publication_date_range (format YYYY-MM-DD:YYYY-MM-DD; year shorthand like "2021:", ":2015-01", "2015:2020" is also accepted), venues, and fields for field selection — pass them whenever the user's intent constrains scope (e.g., "recent", "since 2022", "at NeurIPS"). venues matches Semantic Scholar's exact venue strings (comma-separated, e.g. "Nature,N. Engl. J. Med."); a casual name like "NeurIPS" may not match, so fall back to a date/keyword filter when a venue lookup returns empty.

Per-tool parameter exceptions (verified against the live server — getting these wrong yields a malformed or silently-ignored argument):

  • get_author_papers names its field-selection param paper_fields, not fields (passing fields= is silently ignored — you get titles only), and accepts a publication_date_range but no venues filter. Its date filter is applied after paging and can drop valid in-range papers (a well-known author's 2024:2024 returned []), so for reliable results narrow by topic/venue and date client-side.
  • get_citations accepts publication_date_range but not venues.
  • snippet_search accepts neither fields nor publication_date_range. Instead it has: inserted_before (date filter, YYYY-MM-DD/YYYY-MM/YYYY), paper_ids (comma-separated list of ≤100 IDs to restrict snippets to specific papers), and venues.

⚠️ fields parameter — avoid context blowups

get_paper / get_paper_batch accept a fields string. Never request citations or references via fields — a single highly-cited paper (e.g. Attention Is All You Need) returns 200k+ characters and will overflow the agent's context window. Use the dedicated get_citations tool for forward citations (it paginates). Asta does not provide a dedicated get_references tool — to retrieve a paper's reference list, use get_paper with fields=references only f

阅读完整来源 ↗