ClawHub

smart-search-aisa

v1.0.0

Combine web and academic search into one smart AISA search mode. Use when: the user needs a balanced research pass that mixes public web coverage with academ...

⭐ 0· 65·0 current·0 all-time
by@bibaofeng

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for bibaofeng/smart-search-aisa.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "smart-search-aisa" (bibaofeng/smart-search-aisa) from ClawHub.
Skill page: https://clawhub.ai/bibaofeng/smart-search-aisa
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: AISA_API_KEY
Required binaries: python3
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install smart-search-aisa

ClawHub CLI

Package manager switcher

npx clawhub@latest install smart-search-aisa
Security Scan
Capability signals
Requires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (smart multi-source search) align with the bundled Python CLI which calls AISA endpoints (web, scholar, smart, tavily, sonar, explain). Required items (python3 and AISA_API_KEY) are appropriate for this purpose.
✓
Instruction Scope
SKILL.md tells the agent to run the included Python client (python3 scripts/search_client.py). The script only uses the AISA_API_KEY env var and makes HTTPS POSTs to https://api.aisa.one/apis/v1 endpoints; it does not read unrelated system files or other environment variables. The extract endpoint accepts user-provided URLs (expected behavior for content extraction).
✓
Install Mechanism
No install spec; the skill is instruction-only with a bundled script. Nothing is downloaded at install time and no external installation URLs are used.
✓
Credentials
Only a single credential (AISA_API_KEY) is required and is justified by the script's use of the AISA service. No unrelated secrets, config paths, or extra credentials are requested.
✓
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide settings, and has no elevated persistence requirements.
Assessment
This skill appears to be a straightforward CLI client for the AISA search API. Before installing, confirm you trust the AISA service (https://aisa.one) and the GitHub repo origin in _meta.json. Protect your AISA_API_KEY (do not share it). If you're concerned about network calls or data sent to the AISA API, review the script locally (scripts/search_client.py) and consider running it in a sandboxed environment. If you plan to use the extract feature with arbitrary URLs, be aware the content of those pages will be sent to the AISA service.

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

Runtime requirements

Binspython3
EnvAISA_API_KEY
Primary envAISA_API_KEY
latestvk979bexnarw42avkx6ag816gz9850jjm
65downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0
@bibaofeng
latest
Download

Smart Search

When to Use

  • Combine web and academic search into one smart AISA search mode. Use when: the user needs a balanced research pass that mixes public web coverage with academic depth.

When NOT to Use

  • Do not use this skill for browser-cookie extraction, passwords, Keychain access, or other local sensitive credential access.
  • Prefer a different skill when the user request is outside this skill's domain.

Capabilities

  • Blend public web coverage with academic retrieval in one query flow.

Quick Start

export AISA_API_KEY="your-key"

Primary Runtime

Use the bundled Python client as the canonical ClawHub runtime path:

python3 scripts/search_client.py

Example Queries

  • Research benchmark progress for open-weight reasoning models.

Notes

  • Good default when the query spans both news and papers.

Comments

Loading comments...