agentleFS
engineering-alpinaengineering-alpina/spec-to-linear/.claude/skills/spec-to-tickets/SKILL.md

spec-to-tickets

Skill0 starsChanged 53 days agoMITView on GitHub

Decompose a ready spec into well-scoped tickets with dependencies, acceptance criteria and estimates, validate them against the architecture, and sync them to Linear as a project with epics, sub-issues, labels and blocking relations. Use for "break this spec into tickets", "plan this in Linear", "estimate this spec", "update the tickets after the spec changed".

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. kevin-burns/claude-skills★ 11same name
    2. alastairlundy/skills★ 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 repository4 other files it gives its agents.

The file

Files
SKILL.md

spec-to-tickets

Mirrors .cursor/rules/spec-to-tickets.mdc.

Gate

lint_spec must return ready: true. Otherwise stop and go back to spec-coauthor.

Loop

  1. get_architecture_context.
  2. Draft the plan (schema: packages/core/src/schema.ts). One ticket per reviewable PR, new packages get their own scaffolding ticket with createsPackages, every new import edge in newDependencies, bottom-up dependsOn, Fibonacci estimates up to 8, two to four testable acceptance criteria, stable keys.
  3. validate_plan until no errors. Boundary findings are not negotiable; reroute through an allowed layer.
  4. Show the tree, take edits, save_plan.
  5. preview_linear_sync, show the diff, wait for an explicit yes, then apply_linear_sync.
  6. Reply with the project and epic URLs.

Headless alternative

pnpm stl plan <spec.md> runs the decomposition through the Claude API with the same validator repair loop, then pnpm stl sync plans/<id>.plan.json --team ENG previews and --apply writes.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.