agentleFS
garibong-labsgaribong-labs/openclaw-skills/brave-api-setup/SKILL.md

brave-api-setup

Skill3 starsChanged 10 days agoMITView on GitHub

Set up Brave Search API for OpenClaw web_search. Use when user needs to configure Brave API, get Brave API key, enable web search, or fix "missing_brave_api_key" error.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If user doesn't have an account:

    line 90
  2. Distinctive:

    Create API key in dashboard

    line 94

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brave API Setup

Automates Brave Search API key extraction and OpenClaw configuration.

Included Files

FileDescription
SKILL.mdThis document
scripts/apply-api-key.jsApplies API key to OpenClaw config (Node.js)

Dependencies

  • Node.js (for apply-api-key.js)
  • OpenClaw browser capability (browser tool)

When to Use

  • User wants to enable web_search in OpenClaw
  • Error: missing_brave_api_key
  • User asks to set up Brave Search API

Prerequisites

  • User must have a Brave Search API account
  • User must be logged in (openclaw browser profile)
  • API key must exist in dashboard

Workflow

Step 1: Navigate to API keys page

browser(action="navigate", profile="openclaw", 
        targetUrl="https://api-dashboard.search.brave.com/app/keys")

Step 2: Click reveal button (eye icon)

Take snapshot, find the reveal button, click it:

browser(action="act", kind="click", ref="<eye-button-ref>")

Step 3: Extract key via JavaScript (avoids LLM transcription error)

browser(action="act", kind="evaluate", 
        fn="(() => { const cells = document.querySelectorAll('td'); for (const cell of cells) { const text = cell.textContent?.trim(); if (text && text.startsWith('BSA') && !text.includes('•') && text.length > 20) return text; } return null; })()")

The result field contains the exact API key.

Step 4: Apply to config (direct file write, no LLM involved)

Relative to skill directory:

node <skill_dir>/scripts/apply-api-key.js "<extracted-key>"

Or use gateway config.patch with the extracted key.

Why This Approach

Problem: LLM can confuse similar characters when transcribing (O vs 0, l vs 1).

Solution:

  1. evaluate extracts key via JavaScript → returns exact string
  2. apply-api-key.js writes directly to config → bit-perfect

The key never passes through LLM text generation.

Manual Account Setup

If user doesn't have an account:

  1. Go to https://api-dashboard.search.brave.com
  2. Sign up with email
  3. Subscribe to Free plan (requires credit card)
  4. Create API key in dashboard
  5. Then run this skill

문의 / Feedback

버그 리포트, 기능 요청, 피드백은 아래로 보내주세요.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.