Adonis0123/adonis-skills / skills/agent-dispatch
agent-dispatch
FlaggedChoose the lightest agent setup for a coding, review, drafting or design-research task: do it yourself, fan out to 2-3 workers with independent parts across the Claude Code, Codex, Grok Build, Cursor or other CLIs and accounts on this machine, run a scoped architecture loop, or send one brief to independent researchers; pick a cross-model reviewer, test budget and cleanup; track dispatched work, external waits and user decisions on a Run Board. Use when work may need delegation, or the user asks to dispatch, fan out, parallelize, run several agents or accounts, get another AI's review or independent design opinions, or asks how dispatched work is going. Chinese triggers: 派活、并行、要不要多开几个 agent、分给多个 Claude 账号 / codex / grok、找另一个 AI 审、对比优秀设计、多方意见、进度看板、派出的任务进行到哪了。Not for unrelated read-only questions, trivial edits, research with no delegation, a single review of an existing diff (agentic-review-handoff), or the machine-wide session list (sideby sessions). Inside another named workflow, only size its workers.
references/research-brief.md
View on GitHub# Research brief
One file, given unchanged to every researcher. Every field is required; write `none` rather than deleting a field.
```markdown
# <question in one line>
## Role and rules
You are an independent <designer / engineer / analyst>. Others answer this same brief separately. A finding is used when two of you share it, or when one of you backs it with first-hand evidence the coordinator can check (a source URL, a reproduction), so give your own judgment with evidence. Read-only: do not edit any repository file.
## Context
The product, its users, and the rule the result must serve (for example "beginners never have to stop and think"). Repository path and the files worth reading.
## Inputs
Screenshots, logs or data, each with a path and what it shows. (The coordinator has looked at every one.)
## Questions
Numbered. Each asks for one recommendation, the alternatives rejected and why, and a confidence (high / medium / low).
## Evidence
At least N real sources with URLs (for design: GitHub projects of the same kind and well-known products). Mark anything not verified UNVERIFIED.
## Output
Language, format, word limit, ranking (P0 / P1 / P2 with effort S / M / L), and what is out of scope (for example new backend features).
```
Keep the brief free of the coordinator's own conclusions; they would make the answers agree for the wrong reason.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |