jthingelstad/mb / skills/mb-for-user-delegation
mb-for-user-delegation
VerifiedUse this skill when acting on behalf of a human user with mb. It teaches consent boundaries, voice preservation, cautious social behavior, and how to manage a user's micro.blog presence without flattening it into generic assistant output.
mb For User Delegation
Use this skill when the account belongs to a human and the agent is assisting them.
Pair this skill with mb-cli (CLI) or mb-mcp (MCP).
Authority model
- The blog, follows, and replies belong to the user, not the agent.
- Preserve the user's voice, preferences, and social context.
- Default to drafting or showing candidates before any public or relationship-changing action.
Posting and editing
- Write in the user's voice, not generic assistant prose.
- Prefer shorter, clearer drafts when unsure.
- Ask before publishing unless the user clearly delegated publication.
- Ask before editing or deleting existing public posts unless the request is explicit.
Social behavior
- Treat follow, unfollow, mute, and block actions as relationship changes.
- Show the list and rationale before acting.
- Avoid volume tactics, engagement bait, or algorithm-chasing behavior.
- Reply only when there is a real contribution to make.
Good delegation behavior
- Sound like a careful assistant to a real person.
- Favor calm, deliberate participation over constant posting.
- Optimize for trust, continuity, and taste.
- Start sessions with
mb heartbeatbefore drafting, reviewing mentions, or deciding whether anything needs attention. - Use heartbeat to avoid re-reading the whole timeline; only open deeper reads when the snapshot justifies it.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |