一键导入
design-eval
Design quality rubric scoring — evaluates implementation against design doc on 4 dimensions
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Design quality rubric scoring — evaluates implementation against design doc on 4 dimensions
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | design-eval |
| description | Design quality rubric scoring — evaluates implementation against design doc on 4 dimensions |
Scores an implementation against its design doc on 4 dimensions. Reads the design doc path from bash scripts/config-get.sh meta_dev.paths.design_doc.
Each dimension scored 1-10:
| Score | Label | Criteria |
|---|---|---|
| 9-10 | A | Design-accurate; minor acceptable deviations documented |
| 7-8 | B | Close match; a few deviations but no user-visible regressions |
| 5-6 | C | Noticeable deviations; some design specs missed |
| 3-4 | D | Major deviations; significant rework needed |
| 1-2 | F | Does not match design; needs full reimplementation |
## Design Quality Evaluation
| Dimension | Score | Weight | Weighted |
|-----------|-------|--------|----------|
| Visual Accuracy | X/10 | 30% | X.X |
| Interaction Fidelity | X/10 | 25% | X.X |
| Component Consistency | X/10 | 25% | X.X |
| Accessibility | X/10 | 20% | X.X |
| **Overall** | | | **X.X/10 (Grade X)** |
### Findings
- [severity] file:line — description
Stand up and drive a campaign runbook — a single orchestration manuscript that sequences multiple related plans by dependency and walks them through the 6-stage waterfall in serial/parallel waves, with a live computed dashboard. Use when coordinating a multi-plan feature arc (not a single plan — that's /meta-dev). Invoked by the /runbook command.
The shared execute→review→fix loop for headless plan execution. A fresh worker per task (DeepSeek default via claude-headless-exec, GLM/Sonnet-200K on flag, Codex review-only) executes and self-runs its task Verify hook; review gates at the PHASE boundary (not per task) via the meta-dev:review-agent Opus subagent, which computes its own git diff and returns a verdict; a fixer worker repairs on non-pass (tier-specific fix ladder). Only N worker lines + one phase verdict return to the conductor — diffs never enter the main thread. Used by /meta-execute --deep|--glm|--sonnet|--codex and /auto-execute. Protocol: references/loop-protocol.md.
Patterns for headless Claude execution via claude -p --output-format json. Tool allowlist tiers, env inheritance, model override for Sonnet routing.
Stand up and maintain a visible stage-level task list for the /meta-dev 6-stage waterfall. Use in autopilot/walk runs so the user can walk away and watch Brainstorm→Design→Plan→Harden→Execute→Review progress live. Stage granularity only — never mirrors /meta-execute's per-task list.
Forward-moving compaction handoff. Use when a long session is getting context-heavy mid-project and you want to compact WITHOUT losing momentum — writes a durable, forward-looking handoff so the post-compaction session resumes the exact next step instead of being left hanging. Also used to proactively flag clean compaction boundaries during work. Triggered on-demand via /meta-compact or proactively when a clean boundary meets a heavy context.
Grug-brain sniff test for plans AND code — detect over-engineering, complexity demons, vague tasks, and bad practices in plans/specs (primary) or code (secondary). Report-only, never edits. Invoked as /sniff-test. By default sniffs the subject under discussion in the current conversation; takes a path, or --diff/--staged/--all. Use before executing a plan, before merging code, or when something "smells off".