idea-to-spec
Skill17 starsChanged 7 months agoMITView on GitHub
Use when a user has a new Gear or Vara feature idea, product request, or protocol change that must become an implementable spec. Do not use for deployment-only work, runtime review, or post-release observation.
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
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 16
Use ../../assets/spec-template.md as the output shape.
- Very specific: line 18
Write the result to docs/plans/YYYY-MM-DD-<topic>-spec.md.
- Distinctive: line 26
Stop when the next step is architecture, not coding.
- Distinctive: line 30
Treat async messaging as the default execution model.
- Distinctive: line 32
Keep the spec implementation-agnostic enough that architecture still has work to do.
- Distinctive: line 33
Do not skip invariants or acceptance criteria.
“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.
Files
Idea To Spec
Overview
Convert a rough request into a spec that is specific enough for architecture and implementation planning.
Start Here
Read ../../references/vara-domain-overview.md first.
Use ../../assets/spec-template.md as the output shape.
Write the result to docs/plans/YYYY-MM-DD-<topic>-spec.md.
Workflow
- Clarify the user goal, scope, and non-goals.
- Identify actors, state changes, messages, replies, and events.
- Record invariants, failure paths, and edge cases that follow from Gear/Vara actor semantics.
- Turn the result into explicit acceptance criteria.
- Stop when the next step is architecture, not coding.
Guardrails
- Treat async messaging as the default execution model.
- Name recovery and retry behavior when the feature crosses actor boundaries.
- Keep the spec implementation-agnostic enough that architecture still has work to do.
- Do not skip invariants or acceptance criteria.
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- DevelopersGlobal/ai-agent-skills★ 216same name
- pasqal-io/agent-marketplace★ 4same name
- dragon375014/spec-sonar★ 1same name
- HelloWorldU/skill-collection★ 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 repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- vara-skillsSkill
- vara-skillsSkill
- awesome-sails-vftSkill
- gear-architecture-plannerSkill
- gear-builtin-actorsSkill
- gear-gstd-api-mapSkill
- gear-message-executionSkill
- gtest-tdd-loopSkill
- 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.