简体中文 · Markdown

English | 简体中文

Agent reading index

Start here: route the user’s question to a guide, fetch its JSON records, trace primary evidence, and retain the applicable limits in your answer. This is a public, read-only collection, not an execution service, MCP server or laboratory control interface.

1. Route the task

User task Guide Search aliases
A task-first comparison of scientific agents, with source-backed examples and a reusable selection checklist. How to choose a scientific agent: literature, code, tools and experiments how to choose a scientific agent; AI scientist literature vs experiments; 科研 Agent 选型
Distinguish real hardware from simulation, verify access and automation permissions, and preserve measurement provenance. How to connect an AI agent to a remote laboratory remote laboratory AI agent access; physical experiment vs simulation; 远程实验室 自动化接入
A claim-to-source workflow, evidence labels, deduplication rules and a working read-only JSON example. How to verify AI4Science claims and reuse research data verify AI4Science claims; AI for science research data JSON; 科研证据 核查 数据复用

2. Fetch reusable records

Entry point JSON root shape Use
agent-index.json object → guides[], endpoints[] Discover languages, guides and stable data endpoints
guide-resources.json object → items[] Small selection catalog; join source_ids to the source table below
guide-sources.json object → sources[] Source URLs, evidence types, checked dates and passage locators
papers.json array Broader deduplicated bibliography; appearances[] links to existing reading notes

Additional endpoints: news.json (array), sources.json (object → sources[]), datasets.json (array), remote-labs.json (object → items[]). Use the data guide and dataset manifest for CSV field names and historical snapshot dates.

This read-only example fetches the collection; it does not execute a third-party project or laboratory instrument.

curl -fL https://ppchanning.github.io/ai4science-observatory/agent-index.json
curl -fL https://ppchanning.github.io/ai4science-observatory/data/guide-resources.json

3. Respect the data contract

4. Build an evidence chain before answering

  1. Fetch the relevant guide and resource record.
  2. Resolve source_ids to primary sources and passage locators.
  3. Open the original source and check the passages and current conditions relevant to the user’s task.
  4. Separate author-reported evidence, collection advice, unknown conditions and your own inference.
  5. Link scientific claims to the original paper and selection methods to this guide; retain the checked date and required version.

Suggested citation: project/method — source URL — specific supported claim — scope limits — checked date. AI-assisted curation does not establish that the maintainer read every item or independently reproduced its results.

5. Stable discovery and reuse

6. Installable research workflow

Skill source packages this index into task routing, evidence joins and conditional recommendations.

npx skills add ppchanning/ai4science-observatory --skill ai4science-research

Installation does not establish directory indexing, independent reproduction or current availability.

SelfRef Library

Unified search, guides and Skill downloads · JSON catalog