← ClaudeAtlas

to-speclisted

Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
MalcolmMcNeely/skillworks · ★ 3 · Testing & QA · score 76
Install: claude install-skill MalcolmMcNeely/skillworks
This skill takes the current conversation context and codebase understanding and produces a spec. Do NOT interview the user — just synthesize what you already know. The issue tracker should have been provided to you. If not, tell the user to run `/skillworks:skillworks-setup`. ## Process 1. Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the spec, and respect any ADRs in the area you're touching. 2. Sketch out the seams at which you're going to test the feature. Existing seams should be preferred to new ones. Use the highest seam possible. If new seams are needed, propose them at the highest point you can. The fewer seams across the codebase, the better - the ideal number is one. Write them into the spec's Testing Decisions. 3. Read `tracker` and `target-branch` in `docs/agents/loop.json`. A branch name is the Target branch for this spec. The word `spec` means the spec gets a branch of its own; see [The spec's branch](#the-specs-branch) and do its first part now. 4. Commit whatever the conversation changed on disk — `CONTEXT.md`, ADRs, glossary entries — and push it to the Target branch. The spec points at decisions that must already be in the repo, because every session after this one starts with an empty context and can only find them there. 5. Write the spec using the template below. The spec title should begin with "SPEC:". Then publish it: - With `github`, publish