Automation

Classifies a single Slack bug report, dedupes against your issue tracker, and posts exactly one verdict back in the source thread.

Decides which model, effort level, and cascade shape each subagent gets, routing on measured cost per completed task instead of per-token price.

Places risk-approved orders one at a time through Alpaca or Interactive Brokers, never without an explicit typed yes plus Claude's own Allow once.

Designs production-grade multi-agent workflows with the right pattern, explicit handoff contracts, failure handling, and cost/context budgets.

Delegates repository exploration or implementation to Google Antigravity CLI (agy), then reviews, verifies, repairs and delivers the result under explicit human approval.

A driving-adapter skill for operating a caller-selected Gas City 1.4 runtime while keeping GC runtime state out of AgentOps verdicts.

A read-only playbook for watching Hyperliquid markets and your account between trades: daily desk briefs, book checks, price/funding watches and alert rules.

A step-by-step incident playbook for Hyperliquid trading desks covering unknown send results, unprotected positions, API outages and suspected key compromise.

A constitution for running multiple AI bots as a single trading desk, with defined seats, an evidence standard, and a hard approval gate.

A six-phase research pipeline that mines GitHub and skill registries for public SKILL.md files, classifies repos by archetype, and documents reusable processes and plugin ideas.

An autonomous 13-step loop that pulls the next TaskMaster task, dispatches a complexity-tiered subagent, and only marks it done after evidence-gated triple verification and a reachability sweep.

Orchestrator skill that runs task waves across isolated git worktrees, verifies each worker branch by evidence, merges sequentially, and ends with a single PR.

Prepares per-package CHANGELOG.md entries before tagging a Ratel release — git-cliff draft, human curation, then write.

A cc-fleet skill that spawns long-lived third-party LLM teammates in tmux panes and coordinates them across turns via SendMessage.

Delegates one-shot or flat parallel batches of work to cc-fleet provider models (DeepSeek/GLM/Kimi/Qwen/MiniMax/Codex/Claude) via the headless `cc-fleet subagent` CLI.

Teaches Claude to author and run multi-phase, resumable JS orchestration scripts over cc-fleet provider subagents.

Author a JS script that orchestrates multi-phase, resumable runs across many cc-fleet provider subagents, off the main context.

Runs headless provider LLMs (DeepSeek, GLM, Kimi, Qwen, MiniMax) via the cc-fleet CLI for one-shot answers or lock-free parallel fan-out.

Enforces a strict output contract for claude-mem observer jobs on Grok Bot: either skip_summary or exactly one observation XML, never prose.

Judges an exact implementation subject against its acceptance criteria and returns a single PASS/FAIL/NOT_PROVEN verdict with evidence.