codebase-guideUse for every task involving this project. Covers running Ganglion, its CLI commands, HTTP bridge API, pipeline execution, knowledge queries, configuration,...
Install via ClawdBot CLI:
clawdbot install tensorlink-dev/codebase-guideGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
${OPENAISends data to undocumented external endpoint (potential exfiltration)
POST → http://127.0.0.1:8899/v1/run/pipelinePotentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://github.com/TensorLink-AI/ganglionGenerated Mar 21, 2026
Startups developing AI models can use Ganglion to automate hyperparameter tuning and architecture search, reducing manual experimentation time. By running pipelines locally, they iteratively test configurations, record successful patterns in the knowledge store, and accelerate model deployment. This is ideal for teams with limited ML expertise seeking efficient optimization.
Blockchain projects on Bittensor can deploy Ganglion to orchestrate subnet mining agents that search for optimal consensus or validation models. Using remote mode with multiple bot IDs, teams can run distributed servers that share knowledge, improving mining efficiency and adaptability across decentralized nodes. This supports scalable, autonomous mining workflows.
Academic researchers can scaffold projects with Ganglion to manage experimental pipelines for machine learning studies. They can run stages like data preprocessing or model training locally, query knowledge for past results, and use the HTTP bridge for collaborative remote access. This streamlines reproducibility and knowledge accumulation in lab settings.
MLOps teams in enterprises can integrate Ganglion into CI/CD pipelines to automate model testing and deployment. By using remote mode with mutation endpoints, they can dynamically update tools or rollback changes, ensuring robust operational workflows. This reduces manual intervention and enhances reliability in production environments.
Consulting firms can use Ganglion to build and refine AI agents for client-specific tasks, such as data analysis or report generation. By leveraging the knowledge store and multi-bot workflows, they can train agents across projects, share insights, and quickly adapt to new requirements. This enables scalable, tailored AI solutions.
Offer Ganglion as a cloud-based service where users pay a subscription to access optimized pipeline execution and knowledge sharing. Revenue comes from tiered plans based on usage, such as pipeline runs or storage limits, targeting startups and SMEs needing cost-effective AI tools. This model leverages remote mode capabilities for scalable deployment.
Sell enterprise licenses for Ganglion with custom integrations, training, and premium support. Revenue is generated through one-time licensing fees and annual maintenance contracts, appealing to large organizations in blockchain or tech sectors requiring robust, supported solutions. This model capitalizes on advanced features like mutation and rollback.
Provide a free version of Ganglion for basic local use, with premium features like remote mode, advanced knowledge queries, and multi-bot workflows available via paid upgrades. Revenue streams include in-app purchases or one-time payments for enhanced capabilities, targeting individual developers and small teams. This model encourages adoption while monetizing advanced functionality.
💬 Integration Tip
Set up environment variables like OPENAI_API_KEY and GANGLION_URL early to avoid mode confusion; use the knowledge store to accumulate insights across runs for better performance.
Scored Jun 19, 2026
AI Analysis
The skill primarily documents a legitimate open-source project's CLI and local API. The 'external endpoint' flagged is the user's own localhost server (127.0.0.1), not an unauthorized external service. The credential access is limited to reading the standard OPENAI_API_KEY environment variable, which is required for the tool's stated LLM functionality.
Audited Apr 16, 2026 · audit v1.0
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.