baidu baike search

The Baidu Baike Component is a knowledge service tool designed to query authoritative encyclopedia explanations for various nouns. Its core function is given a specific "noun" (object, person, location, concept, event, etc.) provided by the user, it returns a standardized, detailed entry explanation sourced from Baidu Baike.

MIT-0 · Free to use, modify, and redistribute. No attribution required.
3 · 8.6k · 53 current installs · 56 all-time installs
MIT-0
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the code and SKILL.md: the script performs lemmaList/lemmaContent queries against a Baidu-hosted API. Minor inconsistencies: the SKILL.md/homepage points to baike.baidu.com while the code calls https://appbuilder.baidu.com/v2/baike (an API host). _meta.json version differs from registry metadata. These are implementation/metadata mismatches but not evidence of malicious intent.
Instruction Scope
SKILL.md instructs the agent to extract a noun and call the script which only sends the search parameters to the Baidu API and returns JSON. The instructions do not ask the agent to read unrelated files, other env vars, or transmit data to unexpected endpoints.
Install Mechanism
No install spec (instruction-only) so nothing is written automatically to disk by an installer. The included script depends on the Python 'requests' library but the skill does not declare that dependency; the runtime environment must provide it. Network calls go to the Baidu appbuilder API host (not to shorteners or unknown servers).
Credentials
The only required environment variable is BAIDU_API_KEY (declared as the primary credential), which is appropriate for an API client. No other secrets, config paths, or unrelated credentials are requested.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modify other skills. It will run only when invoked (or when the agent chooses to invoke it), which is expected.
Assessment
This skill is coherent with its description, but check a few practical things before installing: (1) BAIDU_API_KEY is required — ensure you trust the skill and the API key's scope, and avoid using a high-privileged production key during testing. (2) The script makes HTTPS requests to https://appbuilder.baidu.com/v2/baike — confirm your environment allows outbound network calls and that sending query terms to Baidu is acceptable for your privacy needs (queries may contain sensitive nouns). (3) The code imports the Python 'requests' package but the skill doesn't declare it; ensure your runtime has it available or install it in a controlled way. (4) Note small metadata mismatches (homepage vs API host, version in _meta.json) — these suggest minimal maintenance/packaging issues rather than malicious behavior. If you need higher assurance, run the included script locally with a throwaway API key and inspect traffic (or review the key usage policy) before enabling the skill in an agent.

Like a lobster shell, security has layers — review code before you run it.

Current versionv1.1.0
Download zip
latestvk972amr29wn4wv310797brhjqd812vps

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

📖 Clawdis
Binspython3
EnvBAIDU_API_KEY
Primary envBAIDU_API_KEY

SKILL.md

Baidu Baike

Query encyclopedia entries from Baidu Baike.

Two Usage Scenarios

Scenario 1: Direct Search

Get default matching entry for a keyword.

python3 scripts/baidu_baike.py --search_type=lemmaTitle --search_key="keyword"

Scenario 2: Homonym Resolution

When term has multiple entries, list them and select by ID.

# List entries with same name
python3 scripts/baidu_baike.py --search_type=lemmaList --search_key="keyword" --top_k=5

# Get specific entry by ID
python3 scripts/baidu_baike.py --search_type=lemmaId --search_key="entry_id"

API

  • LemmaList: List entries with same title
  • LemmaContent: Get entry details by title or ID

Setup

export BAIDU_API_KEY="your_api_key"

Workflow

  1. Extract noun from query
  2. For ambiguous terms, call LemmaList first
  3. User selects entry from list
  4. Call LemmaContent with selected ID
  5. Return structured data

Files

4 total
Select a file
Select a file to preview.

Comments

Loading comments…