swarm
Skill0 starsChanged 4 months agoMITView on GitHub
When the user invokes /swarm, decompose independent work across multiple native subagents, scale the worker count with complexity, and synthesize one coherent result.
93 other projects use a version of this.
Adopted by
Most recently taken up by
- Fighter90/career-ops-uitheir own version, first seen Nov 15, 2026
- backnotprop/pstacktheir own version, first seen Nov 15, 2026
- marcopesani/swarm-skilltheir own version, first seen Nov 15, 2026
- sammyjoyce/prime-pstacktheir own version, first seen Nov 15, 2026
- pronvis/skillstheir own version, first seen Nov 15, 2026
- upamune/skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use poteto-help, make-bot-ui and 10 more.
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.
ianclearySkillpoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Also in 14 projects that use this
eryzerzSkillmake-bot-ui
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
Also in 19 projects that use this
ianclearySkillprinciple-explain-the-number
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Also in 27 projects that use this
bnemaSkillsetup-pstack
Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.
Also in 23 projects that use this
jaydubya818Skillprinciple-attack-the-premise
Apply when repeated fixes fail and a shared assumption may be wrong.
Also in 31 projects that use this
jaydubya818Skillpoteto-mode
Use when non-trivial work should follow the smallest rigorous Jstack workflow.
Also in 27 projects that use this
- +5 more from jaydubya818
Other versions93 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 93
- backnotprop/pstack★ 4.2ksame name
- langchain-ai/langchain-skills★ 1.3ksame name
- moeru-ai/xsai★ 667same name
- ZaxbyHub/opencode-swarm★ 531same name
- zaxbysauce/opencode-swarm★ 519same name
- guaardvark/guaardvark★ 320same name
- iha2/superlite★ 311same name
- apple-ouyang/book-to-skill★ 148same name
- jtaroreh/agystack★ 128same name
- uzairansaruzi/p3-stack★ 126same name
83 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 repository5 other files it gives its agents.
- agent-bridgeSkill
- awsSkill
- debate-shutdownSkill
- debateSkill
- prism-statusSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 89 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
How to run the swarm: Use the host agent's native subagent or delegation tool to launch separate workers in parallel (same turn if …
- Distinctive: line 25
After subagents return, merge: resolve conflicts, unify design, run or request a single validation pass, and produce one coherent answer …
- Distinctive: line 36
Use a general-purpose worker unless the host offers a more appropriate specialist.
“Common” is measured: kept by at least 6 in 10 of the 89 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
Swarm (/swarm)
When to use
Apply this skill whenever the user sends /swarm (with or without extra text in the same message). Treat it as an explicit command to parallelize the request across multiple subagents.
Rules
- Minimum agents: n ≥ 2. Never satisfy
/swarmwith a single subagent or a single serial plan without delegation. - Scale n with complexity — bias upward; when in doubt, add another agent rather than overload one.
- Small / localized (one file, one bug, narrow question): n = 2–3 (e.g. implement + verify, or explore + implement).
- Medium (feature touching several files, API + UI, tests): n = 3–5 (e.g. backend, frontend, tests, docs or integration).
- Large (refactor, multi-package, audit, unfamiliar codebase): n = 5–8+ (partition by subsystem, directory, concern, or risk).
- Very large / open-ended: split by independent workstreams so agents do not block each other; n as high as is useful within practical limits (each
Taskmust have a crisp prompt and clear deliverable).
- How to run the swarm: Use the host agent's native subagent or delegation tool to launch separate workers in parallel (same turn if possible). If the host has no delegation capability, explain that
/swarmis unsupported instead of simulating parallelism. Each worker gets:- A narrow scope and concrete output (files to touch, questions to answer, or artifacts to produce).
- No duplicate ownership of the same file unless one agent reads and another writes with an explicit handoff in your merge step.
- You (orchestrator) must:
- Briefly state n and why that count matches complexity (one short paragraph).
- After subagents return, merge: resolve conflicts, unify design, run or request a single validation pass, and produce one coherent answer for the user.
- If the user also gave a task description in the
/swarmmessage, that description is the goal; decomposition is yours.
Anti-patterns
- One giant
Taskprompt that does everything. - n = 1 or purely sequential subagents when work could run in parallel.
- Skipping synthesis so the user sees disconnected partial reports.
Model hint
Use a general-purpose worker unless the host offers a more appropriate specialist. Use isolated worktrees for concurrent code edits when the host supports them.
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.

