Automation

Sends risk-approved stock orders to Alpaca or Interactive Brokers behind three separate approval gates, paper by default, and logs fills plus end-of-day flattening.

Drives a real Chrome instance over CDP to compose Weibo posts and long-form 头条文章 articles from text or Markdown.

A zero-config engine that turns any goal into a validated PRD and a materialised board of executable tasks.

A consulting-operations skill that routes client work through six stages and keeps every agreement, decision, and piece of evidence in a local `.fde/` engagement record.

A retro skill that finds the loops where you keep acting as a manual step for your agents and proposes concrete ways to lift you out of them.

A pre-delegation checklist that makes you write stakes, hypothesis, scope and a concrete definition of "verified" before handing work to an agent.

Copies, registers, and validates the Google Chat adapter for a NanoClaw project, then walks you through Google Cloud credentials.

An idempotent install recipe that wires a NanoClaw agent into Linear issue comment threads.

A release-automation skill that takes a patch/minor/major bump, triggers the GitHub Actions publish workflow, and won't stop until the release, npm packages, and Discord announcement are all verified.

Runs five mutually hostile AI agents through three rounds of cross-critique, then hands only the surviving insights to a dedicated planner agent for an executable plan.

A product-development coach skill that applies Getting Real, Rework and Shape Up to cut scope, shape work and ship in six-week cycles.

An orchestrator skill that drains a GitHub Project board through Build → QA → Review → Done lanes autonomously.

Creates properly linked Epic → Feature → Story → Subtask hierarchies in Jira Cloud using SAFe conventions and REST API v3.

Runs the full Jira lifecycle for you — drafting SAFe stories, getting your approval, creating issues, and transitioning them to Done as work completes.

Runs the full Jira loop — draft a SAFe story, get your approval, create the issue, transition states, and log implementation details.

Five mutually hostile agents debate your plan across three rounds, and only the surviving insights get formalized into an executable plan by a dedicated planner.

A durable goal-execution skill that decomposes work into atomic steps, requires real observable evidence for every success criterion, and delegates to Codex subagents.

An execution loop skill that decomposes long-running work into goals, evidence-bound steps, and delegated background subagents.

Tracks long-running goals across sessions and forces an evidence-based audit before anything is marked complete.

An orchestration skill that executes an approved `.omo/plans` work plan by delegating every unit to parallel subagents and closing checkboxes only against captured evidence.