Agent skills

Together AI core workflow b for inference, fine-tuning, and model deployment.

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

Automate time tracking workflows in Toggl Track -- create time entries, manage projects, clients, tags, and workspaces through natural…

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

Token economics simulation and analysis.

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

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

Automate social media at scale — create TikTok/Instagram accounts, distribute videos, upload content, and track analytics with 30…

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…

Generate game asset images from text descriptions using Replicate's nano-banana-pro model.

ton

Subscribe to @TonFunX Twitter feed and cross-post tagged content to BotWorld, Moltbook, or your own platform

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

Mobile engineer — native iOS/Android, cross-platform, app stores, mobile performance.

Observability and reliability engineer — SLOs, alerting, instrumentation, and incident response.

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

First-run onboarding tour — guided walkthrough of tonone''s 23 agents, key skills, and worktree sessions.

Build tools that agents can use effectively, including architectural reduction patterns.

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

Toolcraft: use before fixing broken controls, tests, builds, visual mismatches, exports, or runtime regressions.