scaffold-bulk-review-prototypes

Review all prototypes at once for cross-prototype consistency, coverage gaps, ADR follow-through, and scope discipline. Use for a full audit of all prototypes.

16 stars

Best use case

scaffold-bulk-review-prototypes is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Review all prototypes at once for cross-prototype consistency, coverage gaps, ADR follow-through, and scope discipline. Use for a full audit of all prototypes.

Teams using scaffold-bulk-review-prototypes should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/scaffold-bulk-review-prototypes/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/design/scaffold-bulk-review-prototypes/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/scaffold-bulk-review-prototypes/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How scaffold-bulk-review-prototypes Compares

Feature / Agentscaffold-bulk-review-prototypesStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Review all prototypes at once for cross-prototype consistency, coverage gaps, ADR follow-through, and scope discipline. Use for a full audit of all prototypes.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Bulk Prototype Review

Review every registered prototype for completeness, quality, and cross-prototype consistency.

## Steps

### 1. Gather All Prototypes

1. **Read the prototypes index** at `scaffold/prototypes/_index.md`.
2. **Read every prototype file** in `scaffold/prototypes/` (Glob `scaffold/prototypes/PROTO-*.md`).
3. **Read the design doc** at `scaffold/design/design-doc.md`.
4. **Read all system designs** — Glob `scaffold/design/systems/SYS-*.md`.
5. **Read all engine docs** from `scaffold/engine/`.
6. **Read all ADRs** — Glob `scaffold/decisions/ADR-*.md`.
7. **Read known issues** at `scaffold/decisions/known-issues.md`.
8. **Read design debt** at `scaffold/decisions/design-debt.md`.
9. If no prototypes exist, report that and stop.

### 2. Per-Prototype Completeness

For each prototype, check pre-spike sections (all prototypes) and post-spike sections (Complete prototypes only):

**Pre-Spike:**

| Section | What "Complete" Means |
|---------|----------------------|
| Question | ONE specific, answerable question |
| Hypothesis | Expected answer with reasoning |
| Scope: Build | Numbered list of minimum steps |
| Scope: Skip | At least 2 explicit exclusions |
| Approach | Numbered execution steps |
| Related Documents | At least 1 valid scaffold doc reference |

**Post-Spike (if Status is Complete):**

| Section | What "Complete" Means |
|---------|----------------------|
| Answer | Direct answer to the Question |
| Evidence | Specific measurements or observations |
| Surprises | Findings listed or explicitly "None" |
| Design Impact | Table of affected docs with changes |
| ADRs Filed | Every Design Impact has a corresponding ADR |
| Disposition | Discarded / Archived / Absorbed with reason |

### 3. Per-Prototype Quality

For each prototype, check:
- **Question is specific and singular** — not compound or vague.
- **Scope is minimal** — Build scope is the minimum to answer the question.
- **Skip boundaries are explicit** — clear discipline boundary.
- **Right-sized** — achievable in one spike session.

### 4. Cross-Prototype Consistency

This is unique to bulk review — check relationships BETWEEN prototypes:

- **Question overlap.** Flag prototypes with substantially similar questions. Suggest merging or clarifying the distinction.
- **Scope overlap.** Flag prototypes with overlapping Build scopes — they may be doing redundant work.
- **Coverage gaps.** Cross-reference with systems, engine docs, slices, and known issues. Flag areas of significant uncertainty that have no prototype.
- **ADR follow-through.** For Complete prototypes: verify every Design Impact entry has a filed ADR. Flag missing ADRs.
- **Disposition consistency.** Flag Absorbed prototypes without a referenced TASK-###. Flag prototypes marked Complete but with empty post-spike sections.
- **Stale prototypes.** Flag Draft prototypes that reference documents which have since changed significantly or been deprecated.
- **Status consistency.** Check that index status matches file status for every prototype.

### 5. Registration Check

- Every prototype in `scaffold/prototypes/_index.md` must have a corresponding file.
- Every prototype file must be registered in `scaffold/prototypes/_index.md`.
- IDs, names, statuses, and dispositions must match between files and index.

## Output Format

```
## Bulk Prototype Review — X prototypes audited

### Overview
| ID | Name | Status | Pre-Spike | Post-Spike | Quality Issues | ADRs |
|----|------|--------|-----------|------------|----------------|------|
| PROTO-001 | ... | Draft | 5/6 | — | 1 issue | — |
| PROTO-002 | ... | Complete | 6/6 | 5/6 | 0 issues | 2 |

### Per-Prototype Details

#### PROTO-001 — [Name]
| Section | Status | Notes |
|---------|--------|-------|
| ... | ... | ... |

Quality Issues:
- [specific issues with quotes]

(repeat for each prototype)

### Cross-Prototype Consistency
- **Question overlap:** [OK / overlapping prototypes found]
- **Scope overlap:** [OK / redundant Build scopes found]
- **Coverage gaps:** [OK / areas without prototypes]
- **ADR follow-through:** [OK / X missing ADRs]
- **Disposition consistency:** [OK / issues found]
- **Stale prototypes:** [OK / X stale prototypes]

### Registration
[Any mismatches between index and files]

### Recommendations (prioritized)
1. [Most impactful fix across all prototypes]
2. [Second priority]
3. ...
```

## Rules

- This skill is read-only. Do not modify any files.
- **Cross-prototype checks are the main value** of bulk review over individual `/scaffold-review-prototype` calls. Emphasize relationship issues.
- Be specific. Quote problematic text when flagging issues.
- **Coverage gaps are high-value findings.** Identifying what SHOULD be prototyped but isn't is as important as auditing existing prototypes.
- If all prototypes are well-written, say so. Don't manufacture issues.
- Prioritize recommendations by blast radius — issues that affect multiple prototypes or the pipeline rank higher.

Related Skills

review:ux

16
from diegosouzapw/awesome-omni-skill

UX Review - analyzes feature for efficiency-first UX patterns, keyboard navigation, and pro-tool experience

review-model-guidance

16
from diegosouzapw/awesome-omni-skill

Guidance for selecting models when performing code review with subtasks. Load this skill to enable intelligent model selection for review analysis — choosing faster models for simple tasks and deeper reasoning models for complex analysis.

pr-review

16
from diegosouzapw/awesome-omni-skill

Guidelines for conducting thorough pull request code reviews

ascii-design-reviewer

16
from diegosouzapw/awesome-omni-skill

Review Phase 1 ASCII UI designs from a product owner perspective. Analyze user journeys, identify potential issues, ask clarifying questions about requirements and user flows, create Mermaid diagrams (flowcharts, sequence diagrams, state charts), provide detailed system behavior documentation, and document error handling strategies. Use when reviewing ASCII mockups to validate design against actual user needs, understand system workflows, and ensure completeness before moving to implementation.

academic-reviewer

16
from diegosouzapw/awesome-omni-skill

Expert guidance for reviewing academic manuscripts submitted to journals, particularly in political science, economics, and quantitative social sciences. Use when asked to review, critique, or provide feedback on academic papers, research designs, or empirical strategies. Emphasizes methodological rigor, causal identification strategies, and constructive feedback on research design.

systematic-literature-review

16
from diegosouzapw/awesome-omni-skill

当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。AI 自定检索词,多源检索→去重→AI 逐篇阅读并评分(1–10分语义相关性与子主题分组)→按高分优先比例选文→自动生成"综/述"字数预算→资深领域专家自由写作(固定摘要/引言/子主题/讨论/展望/结论),保留正文字数与参考文献数硬校验,强制导出 PDF 与 Word。支持多语言翻译与智能编译(en/zh/ja/de/fr/es)。

spec-review

16
from diegosouzapw/awesome-omni-skill

How to verify implementation against OpenSpec artifacts

reviewing-agent-prompting

16
from diegosouzapw/awesome-omni-skill

Review and improve prompts for coding agents. Use PROACTIVELY when auditing, checking, or evaluating agent instructions, system prompts, or task delegation text. Applies state-machine thinking to identify structural gaps and improve effectiveness.

review-changes

16
from diegosouzapw/awesome-omni-skill

Orchestrate multiple review agents for a comprehensive pre-PR code review. Analyzes diff, verifies intent alignment with linked issues, and checks for broader codebase impacts. Use before opening a PR to catch bugs, security issues, silent failures, and performance problems. Keywords: review, code review, pre-PR, diff review, check changes, audit changes

review-agents-md

16
from diegosouzapw/awesome-omni-skill

Creates minimal, effective AGENTS.md files using progressive disclosure. Triggers on "create agents.md", "refactor agents.md", "review my agents.md", "claude.md", or questions about agent configuration files. Also triggers proactively when a project is missing AGENTS.md.

review-agent-native

16
from diegosouzapw/awesome-omni-skill

Use this skill when reviewing code to ensure features are agent-native - that any action a user can take, an agent can also take, and anything a user can see, an agent can see. This enforces the principle that agents should have parity with users in capability and context.

quant-plan-reviewer

16
from diegosouzapw/awesome-omni-skill

Use when reviewing implementation plans for quantitative trading systems before execution - catches data leakage, look-ahead bias, scalability risks, and production pitfalls