pivoshenko/pivoshenko.ai / skills/herdr-dispatch
herdr-dispatch
VerifiedRun a task list across parallel visible Herdr workers - one tab per worker in the Herdr app (`hc` plus `herdr-app`), or a budgeted pane grid in the Herdr TUI (`herdr`) - start one agent per task, brief it, collect results from files, handle blocked workers, clean up. Use when the user says "dispatch these", "run these in parallel", "fan this out", "spin up agents", "/herdr-dispatch", or whenever the `herdr-workflow` instruction sends delegated work to Herdr. That instruction holds the policy; this is the mechanics. Full CLI references -> `hc --skill` and `herdr-app --skill` in the app. Requires HC_TERMINAL_ID (app) or HERDR_ENV=1 (TUI).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.3 KB |
| references/brief.md | markdown | 759 B |
references/brief.md
View on GitHub# Worker Brief
Fill every `<...>` and keep the closing line for your Herdr. In the app, `<parent>` is the dispatcher's `$HC_TERMINAL_ID`, expanded before sending.
```text
<What to do, concretely: the change, the files, the expected outcome.>
Scope:
- You own: <paths>
- Do not touch: <paths, or "anything outside your paths">
- Do not start agents or terminals of your own
Verify with: <the repository's check command>
App: Write your complete result as Markdown to <absolute result path>. Then run hc send <parent> "<absolute result path>" and nothing else.
TUI: Write your complete result as Markdown to <absolute result path>. Reply with only that absolute path, nothing else.
Report a blocker the same way, with the blocker written in the file.
```
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: 471k | 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 |