spec-to-screen
Skill0 starsChanged 2 months agoMITView on GitHub
Generate or update UI implementation from a screen spec in docs/product/screens/.
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/CLAUDE.mdcCursor rule
- .cursor/rules/code-style.mdcCursor rule
- .cursor/rules/docker-compose-local.mdcCursor rule
- .cursor/rules/github-cli-pr.mdcCursor rule
- .cursor/rules/git.mdcCursor rule
- .cursor/rules/git-worktree.mdcCursor rule
- .cursor/rules/ticket-driven-workflow.mdcCursor rule
- address-pr-feedbackSkill
- agentic-e2eSkill
- close-ticketSkill
- docs-app-syncSkill
- review-dependabot-prSkill
- screen-to-specSkill
- spec-lookupSkill
- start-ticketSkill
- address-pr-feedbackSkill
- agentic-e2eSkill
- close-ticketSkill
- docs-app-syncSkill
- review-dependabot-prSkill
- screen-to-specSkill
- spec-lookupSkill
- spec-to-screenSkill
- start-ticketSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 16
If any required field is empty → STOP.
- Very specific: line 21
Read the screen spec markdown.
- Distinctive: line 22
Read related architecture/product docs linked from the spec.
- Distinctive: line 25
Update spec if implementation reveals necessary spec corrections (same PR).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 to screen
Target screen: $ARGUMENTS
Gate: stack-paths.md
- Read
docs/development/stack-paths.md - If any required field is empty → STOP. Tell user to fill stack-paths and retry.
Steps
- Normalize screen name to kebab-case file under
screen_spec_dir. - Read the screen spec markdown; if missing, suggest creating from
_template.md. - Read related architecture/product docs linked from the spec.
- Plan component/file changes under
implementation_root. - Implement UI matching the spec; match existing project patterns when code exists.
- Update spec if implementation reveals necessary spec corrections (same PR).
Output
- List of created/updated files
- Manual verification steps for the user
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.