메뉴
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.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
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.
SOC 직업 분류 기준
| name | superbot-prompt-builder |
| description | 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. |
| version | 1.0.0 |
| author | SuperBot agents |
| license | MIT |
| platforms | ["linux","macos"] |
| metadata | {"hermes":{"tags":["Planning","SuperBot","PromptEngineering"]}} |
You are Hermes, working with the SuperBot repository at /home/hermes/repos/superbot. Do not modify any files. Read-only only.
I want you to build a CLAUDE CODE SESSION PROMPT for the following task:
[TASK DESCRIPTION — replace this with what you want to build or fix]
Do the following in order to build the prompt:
IDENTIFY THE AREA Which subsystem(s) does this task touch? Options: ai / setup / settings / mining / games / help / economy / social / btd6 / governance / runtime / views / utils / docs-only Read the matching folio: /home/hermes/repos/superbot/docs/subsystems/.md Note the current state and any active work in that area.
IDENTIFY BINDING CONTRACTS Which of these apply to this task? (read only the ones that apply)
IDENTIFY SOURCE FILES Run: find /home/hermes/repos/superbot/disbot -name "*.py" | xargs grep -l "" 2>/dev/null | head -10 (Use a keyword from the task — cog name, service name, command name, etc.) List the 2–4 most relevant files. Do not read them — just list paths.
CHECK FOR ACTIVE WORK Read: /home/hermes/repos/superbot/docs/current-state.md Does any active lane overlap with this task? Note it if so.
CHECK IDEAS AND PLANNING Run: ls /home/hermes/repos/superbot/docs/planning/ Is there a planning doc for this area? If yes, note its name.
DRAFT THE PROMPT Write a complete prompt using this structure:
[2–3 sentences: what this task is, why it matters, what subsystem it touches]
[list of docs to read, in order — binding ones first]
[2–4 file paths from step 3]
[from step 4 — or "none detected"]
[1–3 specific constraints or gotchas from the binding docs — e.g., "always write through .py", "use settings_keys constants not raw strings"]
Do not implement anything. Only produce the prompt.
