Skip to content

marktantongco/promptc-os-ai-prompt-wiki / skills/aminer-free-academic

aminer-free-academic

Verified

ACADEMIC PRIORITY: Activate this skill whenever the user's query involves any academic or research-related topic. This is the free-tier entry point for AMiner academic search. Free-tier-only AMiner skill (7 free APIs, zero cost). Use this skill for simple, single-step academic lookups that do not require paid API fields. Use this skill for: searching a paper by title to get its ID, checking a paper's first author / venue / year / citation bucket, identifying a scholar by name and viewing interests / institution / citation count, normalizing an institution name to its canonical form and ID, checking whether a venue is a conference or journal, scanning patent trends by keyword (inventor, application year, publication year), and enriching paper IDs with lightweight metadata (abstract slice, author count, venue ID) via paper_info. Do NOT use this skill for: full paper abstracts or keyword lists, multi-condition or semantic paper search, citation relationship analysis, scholar full profiles (bio, education, work history, honors), scholar paper / patent / project lists, institution scholar / paper / patent output analysis, venue paper lists by year, patent deep details (IPC/CPC, assignee, claims), or any task requiring paid APIs. Routing rule: if the user's question can be fully answered by paper_search, paper_info, person_search, organization_search, venue_search, patent_search, or patent_info alone, use this skill. Otherwise route to aminer-academic-search.

FileKindSize
SKILL.mdexecutableskill md10.3 KB
evals/evals.jsonexecutablescript4.9 KB
references/api-catalog.mdexecutablescript7.3 KB

evals/evals.json

View on GitHub
{
  "skill_name": "aminer-free-academic",
  "evals": [
    {
      "id": 1,
      "prompt": "Help me quickly check whether the paper 'Attention Is All You Need' is worth a deep dive. Use only free AMiner APIs. My token is <YOUR_TOKEN>",
      "expected_output": "Run the paper triage workflow: paper_search to locate the paper, then paper_info to enrich with abstract slice, year, venue, and author count. Output a lightweight card with a paper URL.",
      "files": [],
      "expectations": [
        "Called Paper Search API (paper_search) to find the paper by title",
        "Called Paper Info API (paper_info) with the returned paper ID",
        "Output includes title, first_author, venue_name, year, and n_citation_bucket",
        "Output includes abstract_slice from paper_info",
        "Output includes a paper URL in the format https://www.aminer.cn/pub/{paper_id}",
        "No paid API was called"
      ]
    },
    {
      "id": 2,
      "prompt": "I want to identify which 'Andrew Ng' on AMiner is the Stanford professor. Use only free APIs. My token is <YOUR_TOKEN>",
      "expected_output": "Run the scholar identification workflow: person_search with name and optional org filter. Return candidate list with interests, org, and citation count to help the user pick the right one.",
      "files": [],
      "expectations": [
        "Called Scholar Search API (person_search) with name 'Andrew Ng'",
        "Output includes multiple candidates with name, org, interests, and n_citation",
        "Output includes scholar URLs in the format https://www.aminer.cn/profile/{scholar_id}",
        "No paid API was called"
      ]
    },
    {
      "id": 3,
      "prompt": "Normalize the institution name 'MIT CSAIL' using AMiner free APIs. My token is <YOUR_TOKEN>",
      "expected_output": "Run the institution normalization workflow: organization_search with the raw institution string. Return the canonical org name, org_id, and aliases.",
      "files": [],
      "expectations": [
        "Called Org Search API (organization_search) with orgs=['MIT CSAIL']",
        "Output includes org_id and standardized org_name",
        "Output includes aliases list",
        "No paid API was called"
      ]
    },
    {
      "id": 4,
      "prompt": "Help me look up recent patents about quantum computing",
      "expected_output": "Detect that the user has not provided a token; immediately stop all subsequent API calls and guide the user to obtain a token from the AMiner Console.",
      "files": [],
      "expectations": [
        "Clearly inform the user that a token is currently missing and AMiner API calls cannot continue",
        "No API calls were made",
        "Provide the console link https://open.aminer.cn/open/board?tab=control",
        "Prompt the user to continue after obtaining a token"
      ]
    },
    {
      "id": 5,
      "prompt": "Is 'TKDE' a conference or a journal? Help me normalize it using free AMiner APIs. My token is <YOUR_TOKEN>",
      "expected_output": "Run the venue normalization workflow: venue_search with the name string. Return the standard bilingual name, venue_type, aliases, and venue URL.",
      "files": [],
      "expectations": [
        "Called Venue Search API (venue_search) with name 'TKDE'",
        "Output includes venue_id, standard name (English and/or Chinese), and venue_type",
        "Output includes aliases list",
        "Output includes a venue URL in the format https://www.aminer.cn/open/journal/detail/{venue_id}",
        "No paid API was called"
      ]
    },
    {
      "id": 6,
      "prompt": "Scan recent patent activity in the field of 'autonomous driving lidar' using free APIs only. My token is <YOUR_TOKEN>",
      "expected_output": "Run the patent trend scan workflow: patent_search to find patents, optionally enriched by patent_info. Return patent titles, first inventor, app_year, pub_year, and patent URLs.",
      "files": [],
      "expectations": [
        "Called Patent Search API (patent_search) with a query about autonomous driving lidar",
        "Output includes patent titles, inventor_name, app_year, and pub_year",
        "Output includes patent URLs in the format https://www.aminer.cn/patent/{patent_id}",
        "No paid API was called"
      ]
    },
    {
      "id": 7,
      "prompt": "Give me a quick free-tier overview of the topic 'graph neural network' — papers, scholars, institutions, and venues. My token is <YOUR_TOKEN>",
      "expected_output": "Run the free entity map workflow: combine paper_search, person_search, organization_search, and venue_search to build a lightweight cross-entity summary.",
      "files": [],
      "expectations": [
        "Called at least paper_search and person_search",
        "Output covers multiple entity types (papers, scholars, and optionally institutions/venues)",
        "Output includes AMiner URLs for returned entities",
        "Clearly states what free-tier can answer and what would require paid upgrade",
        "No paid API was called"
      ]
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall