file-browser-tool is a read-only workspace skill that helps AI agents safely browse directories, read files, and return structured results with high efficiency.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install file-browser-tool
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install file-browser-tool using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
file-browser-tool is a read-only file browsing and reading skill designed for AI agents working inside a SkillHub workspace. It lets agents inspect directories, read text files, and process workspace content without modifying files, making it a safe choice for analysis, extraction, and document review workflows in Openclaw Skills.
This skill is optimized for relative-path navigation, JSON-oriented output, and repeatable automation patterns. In Openclaw Skills, it is especially useful when you need fast file discovery, content extraction, formatting conversion, and structured metadata handling while preserving workspace safety and reducing manual effort.
Set your API key as an environment variable:
export API_KEY="${API_KEY:?please set environment variable}"
After configuring credentials, restart the session or open a new terminal so the environment changes take effect. Keep API keys out of version control and store them securely.
file-browser-tool organizes its data around a simple request/response contract optimized for read-only workspace access in Openclaw Skills.
| Field | Type | Required | Purpose |
|---|---|---|---|
rel_path |
string | No | Relative path to a file or directory in the workspace. |
mode |
string | No | Output format: json, text, or markdown. Default: json. |
max_retries |
integer | No | Maximum retry attempts per step. Default: 2. |
skip_steps |
array | No | Step numbers to skip for checkpoint/resume workflows. |
{
"success": true,
"data": {
"final_result": {
"tool_result": "tool_result_value",
"tool_metadata": "tool_metadata_value",
"tool_status": "tool_status_value"
},
"execution_log": [
{
"step": 1,
"name": "step name",
"status": "completed",
"duration_ms": 1200,
"output_summary": "summary"
}
],
"total_duration_ms": 7600,
"gates_passed": 3,
"gates_total": 3
},
"error": null
}
success: Boolean success flag.data.final_result: Main tool payload, metadata, and status.data.execution_log: Step-by-step execution trace.data.total_duration_ms: Total runtime in milliseconds.data.gates_passed / data.gates_total: Workflow gate progress.error: Error message when execution fails.mode switching for JSON, text, and Markdown rendering.max_retries control for resilient step execution.skip_steps support for checkpoint-based continuation and interrupted workflows.Loading
ci-cd-and-automation helps teams automate CI/CD pipeline setup, quality checks, retries, and deployment workflows with structured, reliable processing.

Openclaw Skills helps you decide whether a workflow is suitable for an AI agent and returns practical, best-practice design recommendations.

Xueshu Search is an Openclaw Skills academic search workflow for multilingual paper discovery, citation tracing, DOI lookup, BibTeX export, and AI summaries.

Openclaw Skills for Agent KB helps you create, maintain, validate, and optimize a repository-local knowledge base for coding agents.

Openclaw Skills for social media operations, multi-agent coordination, batch actions, analytics, and relationship graph management.

Openclaw Skills for Slack workspace administration, enabling Enterprise Grid management, audit log review, Canvas editing, user groups, and bulk operations.








































