squad
Skill0 starsChanged 43 days agoMITView on GitHub
Route a data task to the right member of the data squad (Debbie for pipelines, Vera for data quality, Max for ML) and coordinate multi-agent hand-offs for end-to-end work, such as "ingest this source, validate it, then forecast it". Use when a request spans more than one of pipelines, data quality and ML, or when it's unclear who should take it.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- github/squadtheir own version, first seen Nov 8, 2026
- microsoft/github-vteam-industry-demostheir own version, first seen Oct 25, 2026
- microsoft/wazatheir own version, first seen Oct 20, 2026
- kubefleet-dev/kubefleettheir own version, first seen Oct 8, 2026
- microsoft/fsi-banking-payments-dispute-resolution-acceleratortheir own version, first seen Aug 14, 2026
- inkwell-finance/claude-skillstheir own version, first seen Aug 13, 2026
Used with
Projects with it also use squad-commands and {skill-name}.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Microsoft AzureSkillsquad-commands
Categorized catalog of common Squad operations. Coordinator reads this file and presents it as an interactive menu when the user asks for available commands or help.
Also in 3 projects that use this
- Microsoft AzureSkill
{skill-name}
{what this skill teaches agents}
Also in 5 projects that use this
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- github/gh-aw★ 5.6ksame name
- github/squad★ 3.4ksame name
- microsoft/waza★ 1.5ksame name
- Azure/fleet★ 227same name
- kubefleet-dev/kubefleet★ 164same name
- rmotgi1227/CCSquad★ 4same name
- inkwell-finance/claude-skills★ 2same name
- microsoft/github-vteam-industry-demos★ 2same name
- buildstr/claude-skill-squad★ 1same name
- berch-t/Kopern-OS★ 0same name
1 more not listed
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 repository4 other files it gives its agents.
- data-qualitySkill
- ml-engineeringSkill
- pipeline-engineeringSkill
- setupSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Read data-agents.config.yaml.
- Very specific: line 21
If workflow.require_plan_before_code is true, show a numbered plan (one line per step, with the owner) and wait for approval.
“Common” is measured: kept by at least 6 in 10 of the 10 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.
Files
The Squad — who takes what
| If the task is about... | Lead | Supports |
| Ingesting, transforming, orchestrating, refactoring or debugging a pipeline | Debbie | Vera adds the gates |
| "Is this data right?", rules, profiling, reconciliation, freshness, anomalies | Vera | Debbie wires them in |
| Features, training, forecasting, evaluation, MLflow, drift | Max | Vera checks the training data, Debbie builds the feature pipeline |
| New end-to-end use case (source → table → model) | Debbie → Vera → Max, in that order | — |
| Numbers wrong on a dashboard or in a model output | Vera investigates first | then Debbie or Max fixes |
Protocol
- Read
data-agents.config.yaml. If it's missing, tell the user to run/data-agents:setupfirst. - Restate the task in one line and name the lead agent and the sequence. For example: "Debbie builds
silver.orders→ Vera adds 6 gates → Max trains the baseline." - If
workflow.require_plan_before_codeis true, show a numbered plan (one line per step, with the owner) and wait for approval. - Delegate each step to the matching subagent (
debbie,vera,max, ordata-agents:debbieand so on when installed as a plugin). Pass along the previous agent's hand-off block as context, so nothing is re-discovered. - Independent steps can run in parallel. Examples: Vera profiling the source while Debbie reads the existing notebooks, or Max framing the problem.
- Finish with one combined summary: files changed, checks added, experiment results, open decisions for the user.
Task: $ARGUMENTS
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
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.