Skywork Search

Skywork Search is a skill for Claude Code, Codex from SkyworkAI/Skywork-Skills. It costs 184 tokens per session (835 once invoked), scanned A, original, MIT.

A web-search skill that uses the Skywork Search API to find current information online. It accepts up to three search queries and saves the results for you to read.

In plain words
What is it for?
Use it to research topics, find sources and statistics, check recent events, or gather material for another task. It requires a Skywork API key.
Why use it?
It helps when your answer depends on recent facts, news, research, or other information that may have changed.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to research topics, find sources and statistics, check recent events, or gather material for another task. It requires a Skywork API key.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skyworkai/skywork-skills/skywork-search
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add SkyworkAI/Skywork-Skills --skill skywork-search
Clone the repo
git clone --depth 1 https://github.com/SkyworkAI/Skywork-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Skywork Search

README.md
[![agentmods](https://agentmods.dev/badge/skills/skyworkai/skywork-skills/skywork-search/github.svg)](https://agentmods.dev/skills/skyworkai/skywork-skills/skywork-search)
Your own site
<a href="https://agentmods.dev/skills/skyworkai/skywork-skills/skywork-search"><img src="https://agentmods.dev/badge/skills/skyworkai/skywork-skills/skywork-search/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Skywork Search

Your own site · 80×15
<a href="https://agentmods.dev/skills/skyworkai/skywork-skills/skywork-search"><img src="https://agentmods.dev/badge/skills/skyworkai/skywork-skills/skywork-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 835 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00184 $0.00835
Opus 5.5 $0.00074 $0.00334
Sonnet 5.5 $0.00037 $0.00167
Haiku 4.5 $0.00018 $0.00084

Measured 1mo ago against content hash aaeb6e44a6b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Skywork Search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/constant.py, scripts/skywork_auth.py, scripts/web_search.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skywork-search/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Search Skill

Search the web for real-time information via the Skywork search API. This skill lets you run up to 3 queries in a single invocation and returns structured results with source URLs and content snippets.

When to use

  • The user asks you to research a topic or find current information
  • You need up-to-date facts, statistics, or news to answer a question
  • Another task (writing a report, creating a PPT, drafting a document) needs web research as a preliminary step
  • The user explicitly asks to search or look something up

Prerequisites

API Key Configuration (Required First)

This skill requires a SKYWORK_API_KEY to be configured in OpenClaw.

If you don't have an API key yet, please visit: https://skywork.ai

For detailed setup instructions, see: references/apikey-fetch.md

How to use

Run the bundled script from this skill's scripts/ directory:

python3 <skill-path>/scripts/web_search.py "query1" ["query2"] ["query3"]
  • Pass 1–3 search queries as positional arguments
  • Results are saved to individual text files in a temporary directory
  • The script prints the file paths to stdout so you can read them

Crafting good queries

Search quality depends heavily on query phrasing. A few tips:

  • Be specific: "Tesla Q4 2025 revenue" works better than "Tesla financials"
  • Use natural language: The API handles full questions well — "What is the current population of Tokyo?" is fine
  • Split broad topics: If the user wants a comprehensive overview, break it into 2–3 focused queries rather than one vague one
  • Include time context when relevant: "best Python web frameworks 2026" rather than just "best Python web frameworks"

Reading results

After running the script, read the output files. Each file contains:

query: <the original query>

[result-1] <source URL>
<content snippet>

[result-2] <source URL>
<content snippet>
...

Synthesize the results into a clear answer for the user. Always cite sources when presenting factual information — include the URLs from the results so the user can verify.

Read the full file on GitHub · 92 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 92 lines · 184 tokens per session scan A aaeb6e44a6b4

Subscribe to this mod's changes

Skywork Search is a skill published in the GitHub repository SkyworkAI/Skywork-Skills (205 stars, last pushed 6mo ago), licensed MIT. It adds 184 tokens to every session and 835 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.