dispatch

2

josephneumann

Use when multiple tasks are ready and you want to assign them to parallel workers

finish-task

2

josephneumann

Use when implementation and tests are complete and you're ready to close out a beads task

reconcile-summary

2

josephneumann

Review a worker session summary and reconcile beads tasks with implementation reality

start-task

2

josephneumann

Start working on a beads task (claim, gather context, define acceptance criteria)

spec

2

josephneumann

Use when you have an idea, goal, or feature description and need to turn it into an actionable plan with tasks

auto-run

2

josephneumann

Use when you need unattended execution across many tasks without manual dispatch cycles

summarize-session

2

josephneumann

Use for a read-only progress snapshot without committing, pushing, or closing anything

orient

2

josephneumann

Use at the start of an orchestrator session to understand project state and find available work

multi-review

2

josephneumann

This skill should be used when the user wants a comprehensive code review using multiple specialized reviewers in parallel. Invoked with /multi-review or when user asks for 'thorough review', 'full code review', or 'review from multiple perspectives'.

debug

2

josephneumann

Use when facing a bug, test failure, or unexpected behavior that isn't immediately obvious

verify

2

josephneumann

Use when making any completion claim, reviewing findings, or processing agent reports

Humanizer

2

josephneumann

Identify and remove AI writing patterns to make text sound natural and human. Use when the user wants to 'humanize' text, remove AI-isms, or make writing sound less like ChatGPT.

writing-skills

2

josephneumann

Use when creating or substantially revising a skill definition