dadwadw233dadwadw233/team-collab-skills/skills/wave/SKILL.md

wave

Skill4 starsChanged 6 months agoApache-2.0View on GitHub

Use when the user invokes `$wave`, asks to start or enter a multi-agent wave, or asks to spin up / set up a wave for a batch of tasks coordinated across agents.

Installs packages

4 other projects use a version of this.

Adopted by

Most recently taken up by

timursafiullin/aodtheir own version, first seen Nov 15, 2026
jmusick/skillstheir own version, first seen Nov 8, 2026
sensorswave/agent-skillstheir own version, first seen Sep 22, 2026
apideck-libraries/api-skillstheir own version, first seen Aug 13, 2026

Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
apideck-libraries/api-skills★ 4same name
sensorswave/agent-skills★ 1same name
jmusick/skills★ 0same name
timursafiullin/aod★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- checkpointSkill
- digestSkill
- docs-refreshSkill
- gateSkill
- handoffSkill
- team-collab-protocolSkill
- team-progressSkill

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 2 are distinctive, and 7 are very specific to this project.

0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Follow the installed team-collab-protocol skill and its references/multi-agent.md flow.
line 21
Very specific:
Before running any CLI command, check command -v team-collab.
line 22
Very specific:
Treat the text after $wave as a slug only when it is a single token matching ^[a-z][a-z0-9-]{2,63}$.
line 23
Distinctive:
Ensure the project has multi-agent mode enabled.
line 24
Distinctive:
If the wave folder does not yet exist, create it:
line 28
Very specific:
If <slug-or-goal> was a free-text goal rather than a slug, read the generated multi-agent/<slug>/PRD.md and pr-plan.md and draft a first …
line 32
Very specific:
If the wave folder already exists, just orient: read multi-agent/<slug>/PRD.md, pr-plan.md, and any existing agent-runs/, then summarize …
line 33
Very specific:
Follow references/multi-agent.md for the wave layout, ownership, and command boundaries.
line 34
Very specific:
If a future Codex version supports custom slash commands and /wave reaches the model as plain user text, handle it exactly the same way as …
line 38

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Team Collab Wave

This is a Codex-friendly command wrapper for the multi-agent wave entry point. Codex does not currently support arbitrary custom top-level slash commands like /wave, so the supported Codex entry point is:

$wave <slug-or-goal>

What this does

A wave is a batch of multi-agent work coordinated entirely through committed files. $wave is the human→coordinator shortcut for starting or entering one, so you don't have to type the full multi-agent enable / multi-agent init CLI flags by hand.

Required behavior

Follow the installed team-collab-protocol skill and its references/multi-agent.md flow. If the protocol skill is not available in the current session, read ~/.codex/skills/team-collab-protocol/SKILL.md; if that file is missing, stop and tell the user to run team-collab install-skills --agent codex --force.
Before running any CLI command, check command -v team-collab. If missing, stop and tell the user to install the CLI with npm install -g @embodot/collab@latest, then refresh skills with team-collab install-skills --agent codex --force if needed.
Treat the text after $wave as a slug only when it is a single token matching ^[a-z][a-z0-9-]{2,63}$. Otherwise, treat it as a goal, derive a slug, and confirm the slug with the user before creating anything.
Ensure the project has multi-agent mode enabled. If it does not, run:
```
team-collab multi-agent enable
```
If the wave folder does not yet exist, create it:
```
team-collab multi-agent init --slug <slug>
```
If <slug-or-goal> was a free-text goal rather than a slug, read the generated multi-agent/<slug>/PRD.md and pr-plan.md and draft a first cut of the wave plan (goal, task breakdown, suggested roles) into them, then tell the user what you drafted and ask for confirmation.
If the wave folder already exists, just orient: read multi-agent/<slug>/PRD.md, pr-plan.md, and any existing agent-runs/**, then summarize the current wave state to the user.
Follow references/multi-agent.md for the wave layout, ownership, and command boundaries. Do not improvise task assignments from this wrapper alone — present the plan and let the user, coordinator, or CLI task lifecycle commands drive the next step.

Compatibility note

If a future Codex version supports custom slash commands and /wave reaches the model as plain user text, handle it exactly the same way as $wave.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free