Agent skills for Windsurf (legacy)

Together AI reference architecture for inference, fine-tuning, and model

Together AI sdk patterns for inference, fine-tuning, and model deployment.

Together AI security basics for inference, fine-tuning, and model deployment.

Together AI upgrade migration for inference, fine-tuning, and model

Together AI webhooks events for inference, fine-tuning, and model deployment.

Intercept the response flow to offer the user a choice about response depth before Claude answers. Use the repository's canonical…

Plan a token-efficient Claude Code or Codex setup, or get a quick health check.

Automate Token Metrics tasks via Rube MCP (Composio).

Use this skill when analyzing codebases, especially large ones (50+ files, 1000+ lines output).

Audit a Claude Code or Codex setup for context-window waste, then fix it and measure the savings.

Open the Token Optimizer dashboard in your browser (context usage, quality, savings).

Audit your OpenClaw setup for token waste, context bloat, and cost optimization opportunities

Get current USD price for any token on Base via Birdeye (CoinGecko fallback).

This skill should be used when building trading bots, implementing swap functionality, or adding cross-chain bridge support.

Measurement-driven model router for Claude Code.

Automate Tomba tasks via Rube MCP (Composio).

Make sure to use this skill whenever the user mentions anything related to job searching on Akademikernes Jobbank, jobbank.dk, or looking…

Write like the user, not like AI. ToneClone trains on the user's actual writing to generate content in their authentic voice — not just…

Generates and edits high-quality AI images using Alibaba's DashScope models directly within the Claude Code environment.

Write an Architecture Decision Record — document what was decided, why, what alternatives were considered, and what trade-offs were…

Keep the executable tool registry out of client-reachable module graphs — when to read `@/tools/metadata` instead of `getTool`, how to…