superbot

Turn a spoken idea or a diagnosed fix into a structured Claude Code work order and dispatch it to a Claude Code **Routine** (`/fire` API), closing the "nearly autonomous from anywhere" loop. Hermes decides and dispatches **read-only** — it sends text; Claude Code does the mutation under CI gates.

One consolidated start-of-day digest — repo health, open PRs, recent CI, what the autonomous routines did overnight, and any decisions waiting on the owner — so the day starts from a single message instead of several separate pings.

Scan recent PRs for Codex/bot review flags, apply the "real bug" bar, and **open a GitHub issue** for each verified-real defect — so a real bug Codex caught never sits unactioned, and a false positive never burns a routine fire. **Issue-only: no merge, no dispatch authority.**

Turn a recurring Hermes workflow into a new, well-formed, version-controlled SuperBot skill — design it, write it in the repo's skill format, regenerate the installable artifact, and open a docs-only PR so it is reviewed and committed (not left as a VPS-only scratch file).

Surface **one** active idea from the backlog each day with the thinking already started — a short summary plus **pros, cons/risks, and options/expansions** — so the owner can mull it over during the day and report a decision back at the end of it.

Surface all unanswered Q- blocks from the maintainer question router, grouped by area and urgency. Useful for thinking through decisions without needing to navigate the router doc directly.

Traffic-light health snapshot. Answers "is anything broken right now?" without opening a full Claude Code session.

Turn a loose "work on X" into a **concrete, correctly-scoped work order routed to the right runner** — by resolving the live roadmap into the first startable item + its executor, then either firing the dispatch routine (Claude work), doing it itself (a Hermes read-only op), or handing the owner a manual step. The missing link between "the dispatch menu exists" and "the correct worker fires".

Handle an inbound real-world input — a bug report, an idea/suggestion, a feature request, a complaint, or a question — by classifying it and routing it to the right home (bug-book / ideas / question router / dispatch / a direct answer) with the right action, instead of guessing or building off the wrong signal.

Read SuperBot's production logs and turn them into a plain-language diagnosis — what's erroring, how often, and the likely cause — without opening a Claude Code session or SSHing in by hand. This is the "why is the bot unhappy?" skill.

Independent (non-Claude) review of a plan or a PR diff — the monoculture-breaking second opinion in the autonomous loop. Produces a structured critique **and** a plain-language maintainer-facing summary for the approve/deny gate.

Snapshot of the BTD6 data pipeline — what the bot knows, what it doesn't, and what's broken. Useful after a live testing session where you hit wrong answers.

Review the ideas backlog from mobile without a full Claude Code session. Shows what lifecycle state every idea is in and suggests one grooming move.

Turn a task description (including a spoken voice-mode idea) into a structured, oriented Claude Code prompt. Arrive at the session with a prompt ready to execute rather than spending context figuring out where to start.

Generate a compressed orientation brief that you paste into Claude Code at the start of a session. Skips the standard 15-minute orientation read.