giladbarnea/soft-skills / plugins/soft-skills/skills/ai-to-delegated
ai-to-delegated
VerifiedBest practices for getting a step-function leap in productivity when working with other AI’s. Load `ai-to-delegated` before spawning a sub-agent, creating a team, talking to a teammate agent, or writing a doc likely read by other agents. Trigger words include “dispatch an agent”, “spawn a team”, and “fork the session to ...”.
AI → Delegated
Read all routes that match your current situation. Follow further links only when their stated condition applies. Read each file once while its contents remain in context. Reconsider the routes when your situation changes. For relationship definitions, see the plugin's roles map.
| Current situation | Read |
|---|---|
| Deciding whether delegation is worthwhile | When to delegate |
| Choosing or changing a delegation shape and agents' configuration | Choose a configuration |
| The harness cannot set the model, thinking, or fork you chose | Dispatch outside the harness |
| About to dispatch, or currently supervising delegates | Delegate coordination |
| The session appears to span multiple hours or more | Also Many-hours supervision |
| Balancing quotas or spend | Budget balancing |
| Requesting work from an agent without shared context | Fresh-context briefing |
| Briefing an agent with inherited context window | Forked-context briefing |
| Examples of briefing delegates | Briefing examples |
| Working alongside peers | Peer coordination |
| About to commission, or currently supervising leaders | Also leading leaders |
| Your context window or another agent’s is tight or likely to run short | You and the affected agent’s team should follow context window |
Named configurations
If a configuration is already chosen, read its file directly. Each file routes the dispatcher and participants to the guidance they need.
- Research fanout: independent research followed by synthesis.
- Colloquium: adjacent research efforts with live peer exchange.
- Pair programming: agree on a plan, implement, and review once.
- Hillclimber–watcher: optimize toward a measurable target with outside judgment.
- External advisor: get a fresh, unbiased idea after repeated attempts fail.
These configurations are examples to generalize from. They are incomplete and evolving, not required structures.
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: 472k | 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 |