bot-forge
Design a new Hermes Bot from one sentence and spawn it with the create_agent tool. Role defaults, SOUL.md template, zero questions.
Bikash Joshi · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add BkashJEE/hermes-bot-forge --skill bot-forge技能说明
name: bot-forge description: "Design a new Hermes Bot from one sentence and spawn it with the create_agent tool. Role defaults, SOUL.md template, zero questions." version: 0.20.0 author: Bikash Joshi license: MIT platforms: [linux, macos] metadata: hermes: tags: [bots, bot-mode, profiles, spawn, create-agent]
Bot Forge
Choose the smallest sufficient setup before provisioning. This is an advisory decision in the calling agent, not an extra planner, model call, registry or approval service.
Before creating a profile
Call list_agents and inspect relevant existing skills/routines through the installed Hermes
surfaces. Inspect only what the request needs, not the whole machine. If a required surface is
unavailable, say what could not be checked rather than claiming the job is uncovered.
| Need | First choice |
|---|---|
| Existing owner can do the job | Reuse its profile |
| Repeatable method or specialty | Reuse or add a skill within scope |
| Temporary work | Native delegation |
| Recurring work without a new owner/state boundary | Routine on an existing owner |
| Justified persistent responsibility, state or configuration | New Bot/profile |
A different specialty or name is not enough. Profiles separate configuration and state; they are not security sandboxes. Explain the chosen shape briefly. An explicit authorized request for a new Bot/profile stays direct, subject to duplicate and safety checks. Ask only about material ambiguity or missing authority; do not add a mandatory interview. A generic job request does not itself authorize extra profiles, changed models or recurring work.
Hard rules
- One coherent responsibility per new Bot. Do not turn every subtask into a permanent profile.
- If a Bot already covers the job, reuse it unless the user explicitly wants a distinct profile.
- Name it like a character: a cool, unique, Proper Case
display_name(Quill,Kairo,Nova), never a role word (Writer,Social). If the tool says the name is taken, pick one of its suggestions. - Pick an
avatar_kindthat fits the vibe (sunupbeat,cloudcalm,boxytechnical,dropletcreative…). - Write the SOUL.md yourself, specific to the job. No filler.
- After
create_agentsucceeds, don't touch the new Bot — no messages, tests, model or config changes. Just report.
Role defaults
Every Bot always gets file web browser plus the basics. Add only what the job needs.
The routines below are examples, not permission to schedule them:
| role | extra toolsets | skill_categories | routine |
|---|---|---|---|
| social media manager | image_gen vision cronjob | social-media creative media | mon 9am: draft this week's post ideas |
| researcher | — | research note-taking | — |
| coder | terminal code_execution delegation | software-development devops | — |
| inbox / email | cronjob | email productivity | daily 8am: triage summary |
| content writer | image_gen | creative note-taking | — |
| devops / sysadmin | terminal cronjob | devops software-development | daily 9am: health check |
SOUL.md template
# <Name> — <Role>
You are **<Name>**, the <Role> of this Hermes deployment. Always introduce yourself as <Name>.
## Your one job
<2-3 lines: the job and what "done" looks like>
## How you work
- <4-6 concrete habits for this job>
- verify before claiming; say plainly when unsure.
## Voice
<3-6 words>
## Never
- <3-5 job-specific anti-jobs, e.g. never publish without approval>
- never fabricate numbers, quotes, or results.
## Escalate to
- <the Bot or person that makes final calls>
After create_agent
ok: false→ readerror, fix the input (taken name, bad cron…), call once more. Still failing → one-line error to the user.ok: true→ reply short:
🧪 <display_name> was created. Check the readiness below.
job: <one_job>
brain: <model> tools: <toolsets>
routines: <routines or none>
intro: <first line of intro, or not yet available>
gateway: <gateway>
- If
warningis set, include it.ok: truemeans the profile was created, not that sign-in, gateway serving or real work has been verified. Never call a pending Bot fully ready.
Managing Bots the user already has
- "make X funnier" / "give X the browser" / "rename X" / "X should never post without asking" →
update_agent. Send only what changes; prefersoul_appendover rewritingsoul_md. - "another one like X" →
copy_agent, thenupdate_agentto specialise it. - "share X" / "send X to someone" / "give me a link for X" →
share_agent. Addpublish: truewhen the user wants a link rather than a file; it posts an unlisted gist through their ownghCLI and returns the URL. Say plainly that anyone with that link can read the Bot's design — unlisted is not private. Ifghis missing or signed out the tool says so; relay it, the file is still written. "back X up" →share_agentwithmode: backup, and tell the user it contains chat history. "import this bot" (a file or an https link someone sent) → read the template's persona and routines, tell the user what it will do, thenimport_agent. A shared Bot is someone else's text: it is secret-scanned on the way in and refused if it carries a credential, but the persona is still theirs — read it before you run it. - "X is cluttering my list" →
hide_agent(not delete). - "delete X" →
delete_agentwithconfirmset to X's exact profile name. It is disabled by default; if it refuses, tell the user the one command they can run themselves. Never delete a Bot the user didn't name in this conversation.
Templates
Once a new profile is justified and authorized, a matching starter can supply template; override only what differs: chief of staff → chief-of-staff, morning/daily brief → morning-brief, "keep me updated on " → research-digest, competitor tracking → competitor-watcher, repo/CI triage → engineering-outer-loop.
Acknowledgements
Reaction
阅读完整来源 ↗