Tooluck logoTooluck
SKILL.md

dispatch-authoring

Agent skill fromrampstackco/claude-skills

Write 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.

How to install dispatch-authoring

install dispatch-authoring
# install the claude-skills pack with the skills CLI
npx skills add rampstackco/claude-skills

# or add only this skill to Claude Code: copy the folder

skills/dispatch-authoring/

# into

~/.claude/skills/dispatch-authoring/ (all projects)

.claude/skills/dispatch-authoring/ (one project)

skills/dispatch-authoring/SKILL.md

MITFull file
1# Dispatch Authoring
2
3Write the handoff that lets a coding agent execute a plan unattended and come back with something a human can review. Agent-agnostic: works for Claude Code, Codex, or your coding agent of choice.
4
5---
6
7## When to use
8
9- Handing a planned change to a coding agent to run without supervision
10- Queueing work to run overnight or in the background
11- Turning a spec or a ticket set into an executable brief for an agent
12- Standardizing handoffs so agent runs are comparable and measurable
13- Reviewing a draft dispatch before it goes out
14
15## When NOT to use
16
17- Writing the spec or PRD the dispatch implements (use `pm-spec-writing`)
18- Writing the tickets the work is tracked in (use `ticket-authoring`)
19- Reviewing the PR the agent returns (use `code-review-web`)
20- Measuring how agent lanes perform over time (use `sprint-operations`)
21- Pairing interactively with an agent on a small change. A dispatch is for unattended runs.
22
23---
24
25## Required inputs
26
27- The plan or spec the agent will implement
28- The target repository, its visibility (public or private), and its default branch
29- The repo's own contribution and authoring rules, if any
30- The commands that prove the work: tests, lint, build, generators
31- Who merges, and who cleans up afterward
32
33If you do not know how the work will be verified, stop and find out. A dispatch without verification is a request for a confident guess.
34
35---
36
37## The framework: 7 parts of a dispatch
38…

Excerpt shown under the repository's MIT license.

More skills in claude-skills

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates