swarm-mechanical
Skill2 starsChanged 19 days agoApache-2.0View on GitHub
Extra rules for Swarm mechanical agents (role mechanical) making renames, config, docs, or generated-file changes. Use together with the `swarm` skill when your kickoff names this skill or your assignment has a `## Workflow` step naming you "mechanical".
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/vendor/vercel-react-native-skills/AGENTS.mdAGENTS.md
- swarm-advisorSkill
- swarm-batchingSkill
- swarm-coderSkill
- swarm-debuggerSkill
- swarm-designerSkill
- swarm-orchestratorSkill
- swarm-researcherSkill
- swarm-reviewerSkill
- swarmSkill
- swarm-spikeSkill
- swarm-ui-reviewerSkill
- swarm-workflowsSkill
- building-componentsSkill
- expo-design-systemSkill
- expo-native-uiSkill
- graphifySkill
- mobile-android-designSkill
- mobile-ios-designSkill
- ponytail-debtSkill
- ponytail-reviewSkill
- ponytailSkill
- ui-ux-pro-maxSkill
- vercel-react-native-skillsSkill
- web-design-guidelinesSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Follow the swarm skill first.
- Very specific: line 14
When a unit is "do this to N files" (a rename, a field added everywhere, N files vendored the same way), give each file its own checklist …
- Very specific: line 18
Run every command in ## Verify.
- Distinctive: line 19
Commit — small, signed, conventional message.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Mechanical changes with Swarm
Follow the swarm skill first; this adds to it.
Exactly the described change
Renames, config, docs, generated files. Apply the vendored ponytail ladder: reuse what's already there, then stdlib, then a native platform feature, then an already-installed dependency, only then new code — the shortest diff that is still correct. No refactors, no "while I'm here" cleanups, no speculative abstractions.
Same-shape batches
When a unit is "do this to N files" (a rename, a field added everywhere, N files vendored the same way), give each file its own checklist line in your completed summary so a reviewer can confirm every one was touched.
Steps
- Make exactly the described change.
- Run every command in
## Verify; record each as a verification entry. - Commit — small, signed, conventional message.
completed, withgit(dirty:false, HEAD sha) and the verification entries.
If it turns out to need judgement
A "mechanical" change that actually needs a decision (which of two patterns to use, whether a rename breaks a public API) is not yours to make. Write a blocked checkpoint saying what the decision is and why it isn't mechanical, and stop.
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.

