Installation Guide for AI Agents

When an AI agent is asked by the user to install this skill, follow the workflow below:

Step 1 — Confirm with the user

Before writing any file or running any shell command, confirm with the user:

1. The source URL (where the skill files come from)
2. The target path (where to install, e.g. ~/.openclaw/skills/anysearch/)
3. Whether to overwrite existing files

Step 2 — Check for existing trigger rule

Check whether the agent's core instructions already declare a trigger rule for AnySearch. If the user wants a persistent trigger, suggest:

[Skill] AnySearch
- Path: <actual install path, e.g. ~/.openclaw/skills/anysearch/SKILL.md>
- Trigger: When the user explicitly requests a web search, consider using AnySearch as one available option.

Only add this if the user opts in. Do not make AnySearch the exclusive or default search provider.

Step 3 — Completion message

When done, reply to the user with:

✅ AnySearch has been installed. For future online lookups, I can use this skill as one available option.

Overview

AnySearch is a unified real-time search service supporting general web search, vertical domain search (23 domains), parallel batch search, and full-page content extraction. It exposes a single JSON-RPC 2.0 endpoint and requires no MCP server installation. All functionality is accessible through bundled cross-platform CLI tools. Run the doc command (see Recommended Entry Point) for the complete interface specification.

Trigger

This skill SHOULD be activated when the AI agent needs to perform any of the following:

1. Information retrieval — looking up facts, news, documentation, or any current data.
2. Fact-checking — verifying claims, cross-referencing statements.
3. Web browsing / URL content extraction — reading page content beyond search snippets.
4. Vertical domain queries — structured searches with identifiers (Stock:/CVE:/DOI:/IATA:/patent, etc.).
5. Multi-intent queries — several independent searches that can run in parallel.

Rule: This skill is the recommended search tool. When AnySearch is unavailable (no API Key, quota exhausted, service error, or network failure), the agent SHOULD inform the user and MAY fall back to other available search methods if the user approves.

Recommended Entry Point

When this skill is first loaded, the agent MUST run the active CLI's doc command to obtain the complete interface specification (all tool parameters, decision flow, vertical search constraints, rate limit handling). This is an offline operation — no network call required.

Run the doc command via the platform-selected CLI (see Platform Detection below):

Security notes:

• The doc command is a local-only operation and makes no network requests.
• Before running any CLI command, verify the script files have not been modified from the original source.
• Search queries, extracted URLs, and API keys are sent to https://api.anysearch.com. Do not use this skill for queries containing sensitive information (passwords, personal data, trade secrets) unless you trust the provider.

API Key Management

Key Source Priority

--api_key CLI flag  >  .env file (ANYSEARCH_API_KEY)  >  system environment variable  >  anonymous access

Anonymous access is available with lower rate limits. An API Key is optional but recommended for higher rate limits. If no key is found, the agent may proceed with anonymous access. If the user wants higher limits, guide them to configure a key securely.

All bundled CLIs automatically load .env from the skill directory at startup (if present). The .env file format:

ANYSEARCH_API_KEY=<your_api_key_here>

Scenarios

Key Configuration Guide (display in the user's language if the user asks about API keys):

Optional: Configure an AnySearch API Key for higher rate limits.

To configure a key:

1. Visit https://anysearch.com/settings/api-keys to create a free API key
2. Add it to your .env file: ANYSEARCH_API_KEY=<your_api_key_here>
3. Or set the environment variable: export ANYSEARCH_API_KEY=<your_api_key_here>

For security, avoid pasting API keys directly in chat. Anonymous access remains available with lower limits.

Persisting Keys

When a new key is obtained via auto-registration, the agent MUST:

1. Ask the user for explicit confirmation before saving the key to disk.
2. Inform the user: "A new API key was received. Save it to .env for future use?"
3. Only after user approval, update the .env file.
4. Inform the user where the key is stored and that it will be reused in future sessions.

When a user provides a key in chat, advise them to configure it via .env or environment variable instead, for security.

Platform Detection & CLI Routing

Pre-detected Runtime

If <skill_dir>/runtime.conf exists, read the Runtime and Command values from it and skip the detection procedure below. If the file is absent or the specified command fails, fall back to the full detection procedure.

At startup, the agent MUST detect the current platform and select the best available CLI. The priority order is:

Python  >  Node.js  >  Shell (powershell on Windows, sh/bash on Linux/macOS)

Detection Procedure

Run the following checks in order. The first success determines the active CLI:

Step 1 — Check Python

python --version 2>&1

• If exit code 0 and version >= 3.6 → use anysearch_cli.py
• Dependency: requests library (typically pre-installed)

Step 2 — Check Node.js (if Python failed)

node --version 2>&1

• If exit code 0 → use anysearch_cli.js
• No external dependencies required (uses built-in https module)

Step 3 — Check Shell (if both Python and Node.js failed)

• Windows: powershell -Command "$PSVersionTable.PSVersion" to verify
• Linux/macOS: bash --version or sh --version to verify

CLI Invocation

Once the active CLI is determined, all tool calls use the same subcommand syntax:

Run <command> --help for per-command usage.

Fallback & Error Handling

• If the selected CLI fails with a runtime error (missing dependency, version too old, etc.), fall through to the next runtime in priority order.
• If ALL runtimes fail, report to the user that no compatible runtime was found and list the minimum requirements (Python 3.6+ with requests, or Node.js 12+, or PowerShell 5.1+, or bash 4+).