gear-architecture-planner
Skill17 starsChanged 7 months agoMITView on GitHub
Use when an approved Gear or Vara spec must be mapped onto program boundaries, services, message flow, and integration surfaces. Do not use when the feature is still undefined or when the task is already reduced to code edits.
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read ../../references/vara-domain-overview.md, ../../references/sails-cheatsheet.md, …
- Very specific: line 16
If the architecture choice depends on what Gear programs can express through gstd, review ../gear-gstd-api-map/SKILL.md before locking the …
- Very specific: line 18
Use ../../assets/architecture-template.md as the output shape.
- Very specific: line 20
Write the result to docs/plans/YYYY-MM-DD-<topic>-architecture.md.
- Very specific: line 32
Keep #[program] thin and push business logic into services.
- Distinctive: line 34
Treat generated clients or equivalent Sails Header-aware encoding as the default Sails message contract.
- Distinctive: line 35
Treat actor boundaries and async flow as design constraints.
- Distinctive: line 36
Call out remote-call failure policy instead of leaving it implicit.
- Distinctive: line 37
Do not collapse architecture into a file-by-file coding checklist.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Gear Architecture Planner
Overview
Turn an approved spec into a concrete Gear/Sails architecture note.
Start Here
Read ../../references/vara-domain-overview.md, ../../references/sails-cheatsheet.md, ../../references/sails-program-and-service-architecture.md, ../../references/gear-messaging-and-replies.md, and ../../references/sails-idl-client-pipeline.md.
If the architecture choice depends on what Gear programs can express through gstd, review ../gear-gstd-api-map/SKILL.md before locking the design.
Use ../../assets/architecture-template.md as the output shape.
Write the result to docs/plans/YYYY-MM-DD-<topic>-architecture.md.
Workflow
- Confirm the spec artifact exists and is approved.
- Choose program constructors and service boundaries.
- Map state ownership, routing, messages, replies, and events.
- Record generated-IDL or generated-client implications.
- Capture off-chain components, failure paths, and explicit non-goals.
Guardrails
- Keep
#[program]thin and push business logic into services. - Make the constructor shape and storage pattern explicit instead of leaving them to implementation guesswork.
- Treat generated clients or equivalent Sails Header-aware encoding as the default Sails message contract.
- Treat actor boundaries and async flow as design constraints.
- Call out remote-call failure policy instead of leaving it implicit.
- Do not collapse architecture into a file-by-file coding checklist.
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- vara-skillsSkill
- vara-skillsSkill
- awesome-sails-vftSkill
- gear-builtin-actorsSkill
- gear-gstd-api-mapSkill
- gear-message-executionSkill
- gtest-tdd-loopSkill
- idea-to-specSkill
- sails-architectureSkill
- sails-dev-envSkill
- sails-ethexe-architectureSkill
- sails-ethexe-implementerSkill
- sails-feature-workflowSkill
- sails-frontendSkill
- sails-gtestSkill
- sails-idl-clientSkill
- sails-indexerSkill
- sails-local-smokeSkill
- sails-new-appSkill
- sails-program-evolutionSkill
- sails-rust-implementerSkill
- ship-sails-appSkill
- task-decomposerSkill
- vara-skills-upgradeSkill
- vara-walletSkill
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.