Agent skills built and battle-tested in production by Avenox.
These aren't demos. Each one runs real work — shipping YouTube videos, driving Codex fleets, packaging codebases for external review — and each carries the gotchas that only show up after something breaks at 2am. That's the part worth having.
Compatible with Claude Code, Cursor, and any
harness that reads SKILL.md-style agent skills.
Install
Copy any skill directory into your agent's skills folder:
git clone https://github.com/avenoxai/avenoxskills.git
cp -R avenoxskills/skills/codex-fleet ~/.claude/skills/
Or take just the one file you want — every skill is self-contained except the
video trio, which shares avenox-studio/ (see below).
The skills
Agent operations
| Skill | What it does |
|---|---|
| codex-fleet | Standalone Codex CLI runner + fleet orchestrator. General codex exec tasks, gpt-image-2 image generation, and parallel multi-lane fleets with worktree isolation. Dependency-free — no control plane required. |
| omp-fleet | The same job for Oh My Pi (omp) — a second coding-agent CLI onto the same Codex subscription. Provider pinning so a lane can't fall through to a metered aggregator, a 25×-cheaper model tier for recon, and in-process subagent fan-out. Includes the measured RAM comparison that decides which harness you actually want. |
| fable-orchestration | Delegation policy for a multi-model stack: when the main loop runs on a scarce top-tier model, what goes to cheaper sub-agents, and what goes to Codex lanes. Routes on difficulty, not just task type. |
External model review
| Skill | What it does |
|---|---|
| gptpro | Export a monorepo into review-ready zip bundles for a non-agentic frontier model — node_modules-free, split by subsystem, with a secret scan that hard-aborts the export rather than shipping a key to a chat UI. |
| gptpro-handoff | The workflow around it: author the prompt, receive the report, verify every finding against the live codebase before implementing. Includes the prompt house style. |
Video production
A local-first, agent-operated YouTube pipeline. Nothing uploads to render.
| Skill | What it does |
|---|---|
| avenox-video | The router — read this first. 7-step pipeline from intake to export. |
| avenox-roughcut | Transcript-driven rough cut: silence removal and flub/retake removal, in the right order. |
| avenox-graphics | Brand-locked motion graphics via HyperFrames, composited onto the cut. |
| avenox-thumbnail | High-CTR thumbnail factory for a mascot-driven channel. Parallel gpt-image-2 jobs, hook-pattern playbook, hard safety rules. |
The three video skills share runtime files in avenox-studio/
— scripts, the edit.json template, and the brand spec:
export STUDIO_ROOT="$PWD/avenox-studio"
export STUDIO_JOBS="$HOME/video/projects" # heavy media — keep OUT of cloud sync
cp avenox-studio/brand/frame.template.md avenox-studio/brand/frame.md
cp avenox-studio/brand/caption-corrections.example.json avenox-studio/brand/caption-corrections.json
Blockchain
| Skill | What it does |
|---|---|
| chainscan | Multi-chain block explorer via the Etherscan V2 unified API + Foundry cast fallbacks. Contract ABI/source, txs, logs, balances, token info across 60+ chains. One key, one endpoint. |
Bring your own assets
Two skills expect files this repo deliberately doesn't ship:
No comments yet.