spec-coauthor
Skill0 starsChanged 53 days agoMITView on GitHub
Co-author a feature spec with the engineer, grounded in the monorepo architecture. Use when someone wants to write, draft, flesh out or review a spec, PRD or design doc under specs/, or says "let's spec this out".
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/spec-coauthoring.mdcCursor rule
- .cursor/rules/spec-to-tickets.mdcCursor rule
- spec-to-ticketsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Write only what the engineer decided.
≈ “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
spec-coauthor
The same procedure as .cursor/rules/spec-coauthoring.mdc, so Cursor and Claude Code behave the same. Tools come from the spec-to-linear MCP server in .mcp.json.
Loop
get_architecture_contextfirst. Never name a package that is not in it.- New spec:
new_spec(slug, title). Existing: read it. - Go section by section. Ask at most three questions per section, only ones that change the ticket breakdown: scope edges, data model and per-tenant migrations, owning layer and boundary rules (quote the rule name), failure behaviour, permissions, rollout.
- Write only what the engineer decided. Everything else goes under Open questions as
- [ ]. Tick answered ones and keep the answer inline. lint_spec(path)untilready: true, then offer to hand off tospec-to-tickets.
Headless alternative
pnpm stl spec review <spec.md> runs the same review through the Claude API and prints blocking questions, affected packages and boundary risks. Useful in CI on a spec PR.
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.

