SiTaggart Polish
Start the dev server, open the feature in a browser, and iterate. You use the feature, say what feels off, and fixes happen.
Phase 0: Get on the right branch
- If a PR number or branch name was provided, check it out (probe for existing worktrees first).
- If blank, use the current branch.
- Verify the current branch is not main/master.
Phase 1: Start the dev server
1.1 Check for .claude/launch.json
Run bash scripts/read-launch-json.sh. If it finds a configuration, use it — the user already told us how to start the project.
1.2 Auto-detect (when no launch.json)
Run bash scripts/detect-project-type.sh to identify the framework.
Route by type to the matching recipe reference for start command and port defaults. If the detector returns a framework type not listed here, ask the user how to start the project:
| Type | Recipe |
|---|---|
next |
references/dev-server-next.md |
vite |
references/dev-server-vite.md |
nuxt |
references/dev-server-nuxt.md |
astro |
references/dev-server-astro.md |
remix |
references/dev-server-remix.md |
sveltekit |
references/dev-server-sveltekit.md |
procfile |
references/dev-server-procfile.md |
unknown |
Ask the user how to start the project |
For framework types that need a package manager, run bash scripts/resolve-package-manager.sh and substitute the result into the start command.
Resolve the port with bash scripts/resolve-port.sh --type <type>.
1.3 Start the server
Start the dev server in the background, log output to a temp file. Probe http://localhost:<port> for up to 30 seconds. If it doesn't come up, show the last 20 lines of the log and ask the user what to do.
1.4 Open in browser
Load references/ide-detection.md for the env-var probe table. Open the browser using the IDE's mechanism (Claude Code → open, Cursor → Cursor browser, VS Code → Simple Browser).
Tell the user:
Dev server running on http://localhost:<port>
Browse the feature and tell me what could be better.
Phase 2: Iterate
This is the core loop. The user browses the feature and tells you what to improve. You fix it. Repeat until they're happy.
- When the user describes something to fix → make the change, the dev server hot-reloads
- When the user asks to check something → use available browser tooling to screenshot or inspect the page
- When the user says they're done → commit the fixes and stop
When the design "isn't coming together" after a couple of passes, or the user
asks for iterative visual refinement or N polish iterations, dispatch a
sub-agent (per ../ce-conventions/SKILL.md §Sub-agent dispatch) that reads
references/design-iterator.md — expanded to an absolute path by the
parent — and runs its screenshot-analyze-improve loop against the target route; hand it the route
URL, the target section, an iteration budget, and explicit non-goals. Run it
inline when sub-agents are unavailable.
No checklist. No envelope. Just conversation.