← Back to Skills Marketplace
Clawhub
by
Mr.Octopus
· GitHub ↗
· v1.5.8
414
Downloads
0
Stars
0
Active Installs
10
Versions
Install in OpenClaw
/install octoflow
Description
Use when the user wants to run GPU-accelerated computations, analyze data, process images/audio/video, train ML models, or generate code from natural languag...
Usage Guidance
This skill appears to be what it claims: a front-end to a local 'octoflow' GPU binary. Before installing or running it: (1) ensure you obtain the octoflow binary from the official GitHub release page and verify the exact asset name and checksum (the SKILL.md's install URL is missing the asset filename); (2) be deliberate when granting --allow-read / --allow-write / --allow-net / --allow-exec flags — only allow the minimal paths/domains/commands needed; (3) running octoflow mcp-serve exposes a local RPC endpoint to your agent — only enable that if you trust the binary and your agent config; (4) expect OctoFlow to write small preference files to ~/.octoflow and per-project .octoflow/; and (5) if you need stronger assurance, verify the release signature/checksum on GitHub or build the binary from source.
Capability Analysis
Type: OpenClaw Skill
Name: octoflow
Version: 1.5.8
OctoFlow is a GPU-native programming language and MCP server designed for data analysis, machine learning, and image processing via Vulkan. The skill bundle (SKILL.md, _meta.json) describes a legitimate tool with a well-defined security model featuring Deno-style explicit permissions (e.g., --allow-read, --allow-net) to prevent unauthorized access. There are no indicators of malicious intent, data exfiltration, or prompt injection; the tool's capabilities are transparently documented and aligned with its stated purpose.
Capability Assessment
Purpose & Capability
The name/description match the declared runtime requirement (an 'octoflow' binary) and the SKILL.md instructions show only operations relevant to GPU compute, data analysis, and running an MCP server. Requiring a local octoflow binary is reasonable for this functionality.
Instruction Scope
Runtime instructions are narrowly scoped: run the octoflow binary, pass permission flags, run as an MCP server for agent integration, and operate on user-permitted files/domains. The SKILL.md adheres to a deny-by-default permission model and does not instruct reading unrelated system files or exfiltrating secrets.
Install Mechanism
The SKILL.md includes an install hint pointing to GitHub Releases (a normal source). However the provided URL ends at the release directory (no specific asset filename) which is an inconsistency and would need resolution by an installer. Overall, using GitHub Releases is expected and low risk compared to arbitrary hosts.
Credentials
The skill declares no required environment variables or credentials. It does note that OctoFlow may save preferences under ~/.octoflow and per-project .octoflow/ which is plausible and proportionate to the tool's function.
Persistence & Privilege
always is false and the skill does not request permanent elevated platform privileges. It can run a local MCP server (expected for agent integration) — this grants a local RPC surface only when the user starts it or allows the agent to. The deny-by-default flags limit automatic access.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install octoflow - After installation, invoke the skill by name or use
/octoflow - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.5.8
v1.5.8: 445 stdlib modules, 150 GPU kernels, 4.5 MB binary, Loom Engine v2, SHA-256 checksums
v1.4.1
- Added macOS (Apple Silicon) support to install instructions, platform table, and OS metadata.
- Updated install section with macOS binary download link and SHA-256 instructions.
- Expanded platform listings to reference macOS in key capabilities and requirements.
v1.4.0
OctoFlow 1.4.0 introduces expanded multimedia support and significant library growth.
- Adds support for audio and video processing in addition to images.
- Increases standard library to 303 modules across 20 domains, including 57 algorithm and 18 multimedia modules.
- Bumps GPU compute kernels to 113 and built-in functions to 207.
- Updates install/download links to version 1.4.0.
- Skill description and feature tables updated to list the new capabilities.
v1.3.3
OctoFlow 1.3.3
- Documentation now emphasizes a strict "deny by default" permission/security model; details permissions table and explicit opt-in via `--allow-*` flags.
- Updated links and download instructions: now points to latest GitHub Release; includes SHA-256 checksums for binaries.
- Clarified supported platforms (Windows, Linux); macOS and Apple Silicon references removed.
- Metadata refined: tags, permissions, and installation info simplified; OpenClaw requirements updated.
- Data storage policy documented: user/project config stays local, fully opt-out with `--no-memory`.
- General cleanup and conciseness improvements throughout SKILL.md.
v1.3.2
- Updated install instructions and metadata to use OctoFlow 1.3.0 binaries for both Windows and Linux platforms.
- Added SHA-256 checksums for binary downloads.
- Improved clarity in the install section for easier verification and reproducibility.
v1.3.1
- Improved and clarified the security model section, explicitly documenting default-deny permissions and Deno-style opt-in flags.
- Clarified supported platforms, now explicitly listing only Windows and Linux in install and MCP support sections.
- Updated installation instructions with versioned binary links and SHA-256 checksums for added security.
- Enhanced the data storage section to document exactly what OctoFlow stores, how to disable it, and ensured clarity around privacy (no telemetry, no network unless allowed).
- Minor updates to tags, required bins, and improved consistency in language and formatting.
v1.3.0
OctoFlow 1.3.0 introduces MCP server support and expands platform features:
- Added MCP server mode (`octoflow mcp-serve`) for integration with AI agent systems.
- 7 new structured tools via JSON-RPC 2.0, including GPU compute, stats, image, and CSV analysis.
- Detailed instructions for MCP integration with OpenClaw, Claude Desktop, Cursor, and Windsurf.
- New features: persistent cross-session memory, project config, auto-skill loading, and knowledge tree context engine.
- Expanded platform compatibility notes, now highlighting Apple Silicon support through MoltenVK.
v1.2.2
OpenClaw-optimized: metadata.openclaw frontmatter, trigger-explicit body, agent-comprehension patterns, declared permissions and install spec.
v1.2.1
Fix security scan warnings: declared permissions in frontmatter, GitHub Releases as primary install, added sandbox documentation, softened example prompts.
v1.2.0
GPU-native language with natural language chat mode.
Metadata
Frequently Asked Questions
What is Clawhub?
Use when the user wants to run GPU-accelerated computations, analyze data, process images/audio/video, train ML models, or generate code from natural languag... It is an AI Agent Skill for Claude Code / OpenClaw, with 414 downloads so far.
How do I install Clawhub?
Run "/install octoflow" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Clawhub free?
Yes, Clawhub is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Clawhub support?
Clawhub is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, win32, darwin).
Who created Clawhub?
It is built and maintained by Mr.Octopus (@mikedconcepcion); the current version is v1.5.8.
More Skills