rampstackco/claude-skills / skills/dispatch-authoring
dispatch-authoring
VerifiedWrite the structured handoff from a planning session to a coding agent: a dispatch with a header, Gate 0 checks, scope, specification, verification, delivery rules, and stop conditions, so the agent can execute unattended and return a reviewable draft PR. Use this skill whenever the user wants to hand work to an agent, write an agent brief, write instructions for Claude Code, Codex, or a Cursor agent, queue work to run overnight, or turn a plan into something an AI coder can execute without asking questions. Triggers on dispatch, hand off to an agent, agent brief, agent handoff, task brief for an AI coder, instructions for Claude Code, Codex task, Cursor agent, background agent, run this overnight, give this to an agent, unattended run. Also triggers when the user has a plan or a spec and asks how to get an agent to build it, even if they never say dispatch.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 359 B |
| SKILL.md | skill md | 8.0 KB |
| references/dispatch-template.md | markdown | 3.7 KB |
| references/example-dispatch-new-skill.md | markdown | 5.5 KB |
| references/gate-zero-checklist.md | markdown | 3.1 KB |
| references/pr-body-template.md | markdown | 1.8 KB |
references/pr-body-template.md
View on GitHub# PR Body Template
The draft PR body is the agent's report. The reviewer reads it before the diff, so it should say what changed, prove it with pasted output, and surface every decision the dispatch did not cover.
Put this template, or a pointer to it, in the dispatch's delivery section.
---
## Template
````
## Summary
[Two to four sentences. What this PR does and why. Link the dispatch or the source spec.]
## Scope
| Item | Change |
|---|---|
| [file, folder, or component] | [added / changed / regenerated] |
Out of scope, untouched: [list from the dispatch]
## Verification
Each command as run, with its output pasted. Not summarized.
### 1. [Check name]
```
$ [command]
[output]
```
### 2. [Check name]
```
$ [command]
[output]
```
[Repeat for every verification step in the dispatch.]
## Gate 0 record
- Remote: [what was found]
- Visibility: [what was found]
- Branch and worktree: [names]
- Generated files and their generators: [file: script and flag]
## Judgment calls
Decisions the dispatch did not cover, and what was chosen:
- [Decision]: [choice]. Reason: [one line].
## Stop conditions hit
[None, or each one with what was found and what was done.]
## Open questions
- [Question for the planner or reviewer]
## Not done
[Anything in the dispatch that was not completed, and why. Or "none."]
````
---
## Rules for the agent
- Paste output. "All checks pass" without output is not verification.
- Run each verification after the final commit, not before.
- List every judgment call, even small ones. The reviewer decides whether it was small.
- If something is not done, say so in "Not done." A complete-looking PR that is partly done costs more review time than an honest partial.
- Leave the PR as draft. Do not request review unless the dispatch says to.
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 |