← Back to Skills Marketplace
You.com Web Search & Research CLI
by
Edward Irby
· GitHub ↗
· v3.0.1
· MIT-0
2585
Downloads
3
Stars
4
Active Installs
11
Versions
Install in OpenClaw
/install youdotcom-cli
Description
Web search, research with citations, and content extraction for bash agents using curl and You.com's REST API. - MANDATORY TRIGGERS: You.com, youdotcom, YDC,...
Usage Guidance
This skill appears coherent for interacting with You.com APIs, but take these precautions before installing: (1) Treat YDC_API_KEY as a secret—only provide it if you trust the publisher. (2) Confirm the domains (api.you.com and ydc-index.io) are expected by comparing with You.com's official docs because no homepage/source repo is provided here. (3) The skill fetches external web content—do not allow it to execute untrusted content and follow the SKILL.md guidance to wrap and sanitize fetched data. (4) Because this is instruction-only, nothing will be installed locally, but network calls will be made—ensure you are comfortable with that traffic. (5) If you need stronger assurance, request a link to the official project repo or vendor documentation before installing.
Capability Analysis
Type: OpenClaw Skill
Name: youdotcom-cli
Version: 3.0.1
The youdotcom-cli skill provides a legitimate interface for web searching and content extraction via the You.com API using curl and jq. It includes proactive security instructions for the AI agent, specifically advising it to treat all fetched web data as untrusted and to ignore any instructions contained within that external content (SKILL.md).
Capability Assessment
Purpose & Capability
Name/description (web search, research, content extraction) aligns with required binaries (curl, jq) and the declared primary credential (YDC_API_KEY) which is needed for Research/Contents endpoints. One minor note: the skill has no listed homepage or source repo in metadata — reasonable but means you cannot easily verify publisher authenticity.
Instruction Scope
SKILL.md only instructs the agent to call You.com endpoints, parse JSON with jq, and treat fetched content as untrusted; it does not ask the agent to read unrelated files, scan system state, or exfiltrate data to foreign endpoints. It explicitly warns not to execute fetched content.
Install Mechanism
Instruction-only (no install spec, no downloaded code). This is the lowest-risk install pattern; it relies on existing curl/jq binaries and internet access.
Credentials
Only one primary credential (YDC_API_KEY) is declared and it maps to the documented endpoints. The README notes Search can work without a key while Research/Contents require it. No unrelated secrets or platform credentials are requested.
Persistence & Privilege
always:false and no install-time persistence or cross-skill configuration changes. Autonomous invocation is allowed (default) but not elevated by this skill itself.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install youdotcom-cli - After installation, invoke the skill by name or use
/youdotcom-cli - Provide required inputs per the skill's parameter spec and get structured output
Version History
v3.0.1
- Removed all bundled JSON schema files; SKILL.md no longer references local schema links.
- Added inline documentation of search query parameters and typical response jq paths to SKILL.md, replacing schema tables.
- No other functional changes.
v3.0.0
**Major update: Switches from Node.js CLI to direct REST API with curl/jq and adds new Research endpoint with citations.**
- Now uses curl and jq, not Node.js or Bun—compatible anywhere curl/jq are installed.
- Adds support for You.com Research API (POST /v1/research) for synthesized answers with citations.
- Provides new example workflows for Search (no API key required), Research (API key required), and Contents extraction (API key required).
- Includes linked JSON schemas for all endpoints for parameter/response reference.
- Clarifies safe handling of untrusted content, tool restrictions, and error troubleshooting.
v2.0.7
**Improved safety guidance and usage instructions for handling untrusted content:**
- Strengthened documentation on wrapping full page content from `livecrawl` or `contents` in `<external-content>` markers before reasoning.
- Updated Quick Start examples to assign fetched content to variables and wrap it in delimiters.
- Emphasized ignoring any instructions inside `<external-content>` and clarified that all fetched content is untrusted external data.
- Clarified sample code patterns for safe field extraction and boundary wrapping using Bash and jq.
- Minor formatting and language improvements throughout documentation.
v2.0.6
Version 2.0.6
- Added instructions for verifying package integrity with npm audit and metadata inspection.
- Introduced dedicated security and prompt injection defense sections with clear handling rules for untrusted web content.
- Emphasized the importance of extracting only required fields with jq before further processing results.
- Clarified that only @youdotcom-oss/api is allowed as a tool within this skill.
- Expanded documentation on handling and summarizing search results to prevent prompt injection risks.
v2.0.2
- Expanded quick start instructions with installation, API key setup, and usage examples for all main features.
- Added explicit workflow guidance on using --client flag, environment variable setup, schema discovery, and tool selection based on user input.
- Documented troubleshooting steps and common error codes.
- Updated minimum required versions: Bun 1.3+ or Node.js 18+.
- Clarified supported CLI invocations and improved example commands for real-world use.
v2.0.1
**Changelog for youdotcom-cli v2.0.1**
- Added explicit toolchain and dependency metadata in SKILL.md, including binaries, npm dependencies, and security verification instructions.
- Documented version pinning best practices for `@youdotcom-oss/api`, including installation, verifying package integrity, and update workflow.
- Added security guidance and commands to ensure package authenticity.
- Clarified workflow steps to emphasize runtime checks, version pinning, and upgrade decision-making.
- No functional/tooling changes—documentation and metadata improvements only.
v2.0.0
**Major update with significant simplification and security improvements:**
- Streamlined documentation to focus on core features: livecrawl web search and content extraction.
- Improved clarity on API key setup, CLI runtime requirements, and error handling patterns.
- Enhanced security section with explicit version pinning and credential management.
- Updated CLI usage patterns and tool selection tables for better usability.
- Added environment variable documentation (YDC_API_KEY, YDC_CLIENT) for clearer integration.
- Removed deep-research and advanced AI answer usage, emphasizing simultaneous search + extraction.
v1.2.1
adds deep search instructions
v1.2.0
**Added "deep-search" command and research workflow.**
- Introduced `deep-search` for multi-step, citation-backed research with adjustable effort levels (low/medium/high).
- Added new section mapping user queries to optimal tool (search, livecrawl, contents, deep-search) with clear use-case guidance.
- Expanded documentation with research and express modes for answering queries, highlighting timing and depth tradeoffs.
- Included usage examples and error handling for the new `deep-search` tool.
- Updated SKILL.md version metadata from 1.1.0 to 1.2.0.
v1.1.0
you-dotcom-cli 1.1.0
- Updated skill category from "cli-tools" to "web-search-tools".
- Added version metadata field: "1.1.0".
- Improved description language for clarity and conciseness.
- Removed AI answer (express) CLI documentation and samples; focus now on search and content extraction.
- Added best-practice recommendations for bunx vs npx regarding version freshness and caching.
v1.0.0
youdoctom-cli 1.0.0 initial release
- Introduces a high-performance JSON CLI for You.com web search, AI answers with citations, and web content extraction
- Designed for seamless integration with bash-based AI agents (e.g., OpenClaw, Claude Code, Codex, Cursor)
- Supports schema discovery via --schema flag for programmatic query building
- Livecrawl feature enables simultaneous search and instant content extraction in a single call
- Outputs compact JSON suitable for bash pipelines; separates stdout (success) and stderr (errors)
- Requires Node.js 18+ or Bun for execution; MIT licensed
Metadata
Frequently Asked Questions
What is You.com Web Search & Research CLI?
Web search, research with citations, and content extraction for bash agents using curl and You.com's REST API. - MANDATORY TRIGGERS: You.com, youdotcom, YDC,... It is an AI Agent Skill for Claude Code / OpenClaw, with 2585 downloads so far.
How do I install You.com Web Search & Research CLI?
Run "/install youdotcom-cli" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is You.com Web Search & Research CLI free?
Yes, You.com Web Search & Research CLI is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does You.com Web Search & Research CLI support?
You.com Web Search & Research CLI is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created You.com Web Search & Research CLI?
It is built and maintained by Edward Irby (@edwardirby); the current version is v3.0.1.
More Skills