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 ...”.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.9 KB |
| briefing/examples.md | markdown | 12.7 KB |
| briefing/forked-context.md | markdown | 613 B |
| briefing/fresh-context.md | markdown | 1.6 KB |
| configurations/colloquium.md | markdown | 2.2 KB |
| configurations/external-advisor.md | markdown | 1.1 KB |
| configurations/hillclimber-watcher/protocol.md | markdown | 4.0 KB |
| configurations/hillclimber-watcher/watcher.md | markdown | 1.5 KB |
| configurations/pair-programming.md | markdown | 5.1 KB |
| configurations/research-fanout.md | markdown | 2.8 KB |
| coordination/budget-balancing.md | markdown | 1.0 KB |
| coordination/delegates.md | markdown | 4.9 KB |
| coordination/leading-leaders.md | markdown | 4.2 KB |
| coordination/many-hours-supervision.md | markdown | 3.6 KB |
| coordination/peers.md | markdown | 2.4 KB |
| planning/choose-configuration.md | markdown | 7.9 KB |
| planning/dispatch-outside-the-harness.md | markdown | 1.3 KB |
| planning/when-to-delegate.md | markdown | 8.7 KB |
configurations/hillclimber-watcher/protocol.md
View on GitHub---
name: hillclimber-watcher-team
shape: Team
description: Pairs an iterative optimizer with a watcher that prevents tunnel vision.
---
# Hillclimber–Watcher Team Pattern
If you haven’t yet:
Before creating this team, read [delegate coordination](coordination/delegates.md).
When briefing participants without shared context, read [fresh-context briefing](briefing/fresh-context.md).
Participants: read [peer coordination](coordination/peers.md). The watcher also reads [watcher.md](configurations/hillclimber-watcher/watcher.md).
Use this pattern when the task has a measurable target, a search space, and a real risk that a busy agent will tunnel-vision while iterating. The point is not ordinary implementer/reviewer pairing. The point is **autonomous optimization with periodic outside-the-loop steering**.
## Shape
Create a two-teammate team:
1. **Hillclimber** — owns the work. It experiments, implements, measures, and iterates toward the target. Owns completion.
2. **Watcher** — stays mostly idle. It periodically checks whether the hillclimber is making real progress or falling into loops, rabbit holes, overfitting, whack-a-mole’s, or low-leverage work.
The watcher should not become a second implementer. Its value is judgment under low cognitive load.
## When to use
Use this when:
- There is an explicit metric or acceptance target.
- The solution may require trial and error.
- The main risk is local optimization, whack-a-mole patches, or tunnel vision.
- A somewhat-detached observer can improve the execution without duplicating the heavy work.
Do not use this for straightforward implementation, simple research, or work where a normal adversarial reviewer is enough.
## Context floor
> This section applies to the dispatcher.
> The instructions in this sections should be read idempotently; if the prepared context and/or prompt are already available, do not write new ones. Prefer referencing existing resources. Remember that “included in its context window” also counts as “already available”. This is relevant when session forks are involved; for example, if you have a good grasp of what needs to be done, a fork of yours, by definition, also does. A non-fork does need an explicit context floor.
Before spawning the team, write a short context file and tell both teammates to read it first. Put it in a subdirectory of an existing desk directory, or create a new desk directory if none exists.
The floor context should include:
1. The actual goal and metric.
2. The current baseline, if any.
3. The constraints that prevent cheap wins.
4. The relevant files, referenced by path rather than copied wholesale.
5. The validation command or measurement harness.
6. What the final handoff must contain.
Keep it a mission brief, not a transcript. Strip stale interpretations, tool receipts, old chatter, and irrelevant files.
## Team prompt template
The dispatcher supplies the goal and context file. Both participants follow the agreement below.
Paths in this template are relative to the `ai-to-delegated` skill root.
```text
{{ context-loading instructions, references, and this Skill }}
You are a hillclimber–watcher team. The shared goal is: <goal and measurable target of the team as a whole>.
Hillclimber: own the {{ task nature: either 'implementation', or 'optimization loop' for ML-shaped tasks, etc. }}. Try approaches, measure them, keep the work reproducible, and iterate toward the target. Prefer simple, principled changes over piles of special-case patches. Ping Watcher when you have meaningful progress, and answer Watcher's check-ins.
Watcher: read `configurations/hillclimber-watcher/watcher.md` for your observation procedure. Do not take over the implementation.
Both: set short, current statuses frequently. Keep summaries concise. Continue until you either reach the target or have been plateuing for more than an hour straight without progress (look at the clock from time to time if you have no feeling of passage of time.).
Communicate directly with each other and converge without main-agent micromanagement.
```
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: 323k | 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: 323k | 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: 323k | Updated | Claude CodeCodex | Verified | Install |