- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add educlopez/ui-craft --skill finalize -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add educlopez/ui-craft --skill finalize -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add educlopez/ui-craft --skill finalize -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add educlopez/ui-craft --skill finalize -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/educlopez/ui-craft/tree/HEAD/.agents/skills/finalize来自发布者
Context: this sub-skill is one lens of the broader ui-craft skill. If the ui-craft skill is also installed, read its SKILL.md first for Discovery + Anti-Slop + Craft Test, then apply the specific lens below.
Load the ui-craft skill. This command produces findings only — do NOT edit code.
Look for .ui-craft/brief.md.
/brief first. /finalize requires a design brief to distinguish intentional decisions from findings." Do not proceed.Run npx ui-craft-detect on $ARGUMENTS (or current working surface if no argument).
Capture all output. Every Critical detector finding maps directly to a block-ship finding in the report. Preserve detector source labels.
Quick three-question audit (no deep read required):
Any "no": flag as Major. Do not block ship. Append a recommendation: "Run /tokens to close the gap at [category]."
Applies only when the target is a complete surface (dashboard, landing, auth, settings shell, portfolio) — skip for single components.
references/craft-intent.md §3 (product / auth / marketing lists). Zero → Major ("no signature — surface is competent but anonymous; run /bolder or /polish"). Two or more competing → Major ("signature bets stack — keep the strongest, cut the rest")..ui-craft/spec.md section or session declared a Craft Read, verify the built surface matches it (theme, variance, signature). Mismatch → Major with the specific delta.These findings are Major, never Critical — they gate NOT READY, not BLOCKED.
Applies to landings, portfolios, and campaign pages — skip for product shells.
Load references/recipe-landing.md and run its Acceptance-bar mechanical checks against the built surface — thresholds (eyebrow count, layout-family budget, hero discipline) live there, not here; this step only names which checks apply and where a violation lands.
references/copy.md Copy Self-Audit.references/recipe-landing.md Eyebrow budget. Over budget → Major ("eyebrow flood — delete labels until the count passes").references/recipe-landing.md Layout-family budget. Any repeat or consecutive-split overrun → Major.references/copy.md CTAs & Buttons (one label per intent; CTA fits one line at desktop). Violation → Major.references/recipe-landing.md Hero discipline. Over budget → Major.Load references/finish-bar.md. Run all 10 passes in document order. Do not reorder.
Knob behavior (apply before running):
CRAFT_LEVEL ≤ 6 AND user did not explicitly invoke /finalize: run Passes 1, 6, 8 only; mark remaining as N/A (knob-gated).CRAFT_LEVEL ≥ 7 OR user explicitly invoked /finalize: run all 10 passes.MOTION_INTENSITY ≤ 3: Pass 7 = motion-gap audit only; do not fail on absent entrance animations.VISUAL_DENSITY ≥ 8 AND brief documents compressed rhythm: Pass 4 accepts compressed spacing values.For each pass:
finish-bar.md (Critical / Major / Minor).brief.md: downgrade to "Deferred per brief" and cite the exact principle. If no brief principle covers it, it remains a finding regardless.Load references/review.md Feedback Hierarchy section.
Group all findings (detector + token + finish-bar) into three tiers:
If any Value findings exist: surface them first in the report and add a standing recommendation to defer all Delight findings until Value findings are resolved. This prevents polish work masking broken functionality.
Print this report. Do not add preamble.
## Finalize report — <surface name>
**Ship verdict:** READY / NOT READY / BLOCKED
> BLOCKED = any Critical finding present.
> NOT READY = any Major finding present, no Critical.
> READY = zero Critical, zero Major (Minor explicitly accepted).
### Block-ship findings (must fix before merge)
- [Pass / detector source] — [finding] — [file:line if available]
### Major findings (fix or defer with recorded reason)
- [...]
### Minor findings (polish; ship-okay if explicitly accepted)
- [...]
### Deferred per brief
- [finding] — [principle from brief.md that defers it]
### Recommended next actions
- [ordered, 3–5 items max]
If a tier has no findings, omit the section header entirely.
Convergence mode activates ONLY when the user explicitly says "run in convergence mode", "converge until the bar passes", or uses a --converge flag. A vague "keep going", "fix it", or "make it pass" does NOT trigger convergence — the default remains findings-only (Step 7 hard-stop applies).
When explicitly triggered: load skills/ui-craft/references/loops.md and run preset visual-anti-slop (budget the default loop budget defined in loops.md, hard cap 5). Emit the pre-flight cost notice before iteration 1. After each single highest-impact fix, re-run finalize Steps 2–6 (this command's own steps) until READY or budget exhausted. Note: finalize's findings-only hard-stop (Step 7) is lifted ONLY inside convergence mode — fixes are applied during iteration.
Do not edit any file. Do not propose code changes inline. The verdict is the output. If the user asks for fixes after reading the report, respond to that as a separate request.
Next step: Ship. If the gate is red, the findings name the pass to re-run — /polish, /harden or /clarify.
Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by feedback hierarchy. Use when the user wants to ship, merge, or finalize a surface and needs
---name: finalizedescription: Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by…---# .agents/skills/finalize/SKILL.md概览
Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by feedback hierarchy. Use when the user wants to ship, merge, or finalize a surface and needs a verdict (READY / NOT READY / BLOCKED) before committing. Invoke when the user asks for finalize on their UI, or mentions 'finalize' alongside design / UI / frontend work.
常见问题
从发布者处下载 .agents/skills/finalize/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/educlopez/ui-craft。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。