generate.md: reuse the harness's page, ask when the wording has no direction

The lane is now one page open, three commands and one edit: find the dev
server the harness already runs, open it in the harness's own browser,
start with `--dev-url --boot --wait-for-browser`, edit once, reply and
wait with `--then-poll`, and let the helper bake the accept. A wording
with no direction ("better", "improve") asks one vocabulary question
before anything starts. DESIGN.md is a boundary for the variants, not a
mood board. Knobs are out of the lane. Setup step 1 exempts `generate`,
whose start command loads the same context. Reviewed against
writing-for-agents and the house reference style: a search miss never
starts a second dev server, one move per branch, a checkable done line.

Written with AI assistance (Claude).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

skill/SKILL.src.md

@@ -18,7 +18,7 @@ Core principles:
 
 ## Setup
 
-1. Run `<skill-base-dir>/scripts/impeccable context` once per session, where `<skill-base-dir>` is the directory that contains this SKILL.md (the skill folder, not a plugin root two levels above it); keep cwd at the user's project. That base directory resolves every `{{scripts_path}}/impeccable <verb>` command in this skill and its references, and `{{scripts_path}}` is the fallback only when the runtime reports no base directory. On a Windows shell without `sh`, call `{{scripts_path}}/impeccable.cmd` instead. The launcher runs a self-contained binary that ships next to it or is downloaded once on first run; no Node or other runtime is required. Pass a named source file or route as `--target <path>`. It loads PRODUCT.md, DESIGN.md, the matching surface brief, and native-platform guidance when applicable; follow its directives and do not rerun it. <!-- rule:skill-setup-context -->
+1. Run `<skill-base-dir>/scripts/impeccable context` once per session, where `<skill-base-dir>` is the directory that contains this SKILL.md (the skill folder, not a plugin root two levels above it); keep cwd at the user's project. That base directory resolves every `{{scripts_path}}/impeccable <verb>` command in this skill and its references, and `{{scripts_path}}` is the fallback only when the runtime reports no base directory. On a Windows shell without `sh`, call `{{scripts_path}}/impeccable.cmd` instead. The launcher runs a self-contained binary that ships next to it or is downloaded once on first run; no Node or other runtime is required. Pass a named source file or route as `--target <path>`. It loads PRODUCT.md, DESIGN.md, the matching surface brief, and native-platform guidance when applicable; follow its directives and do not rerun it. The one exception is `generate`: skip this step for it, its own start command loads the same files. <!-- rule:skill-setup-context -->
 2. Load the request's playbook: its Commands-table reference for an explicit/implied sub-command, or [reference/new-work.md](reference/new-work.md) for a new surface or replacement visual world. Inspect target and incumbent visual truth before editing. When the app cannot run, start with committed visual-regression goldens or screenshot fixtures; verify target and freshness against current tokens, CSS, components, or assets, resolve conflicts, and compare theme/variant captures. <!-- rule:skill-setup-command-ref --> <!-- rule:skill-setup-read-project -->
 3. After resolving analysis and direction, read [reference/craft-floor.md](reference/craft-floor.md) immediately before any UI edit, including small refinements. It carries the quality floor, the absolute bans, and the reflexes no detector catches. Do not load it for planning-only work. <!-- rule:skill-craft-floor-load -->