Document Review
Improve brainstorm or plan documents through structured review.
Step 1: Get the Document
If a document path is provided: Read it, then proceed to Step 2.
If no document is specified: Ask which document to review, or look for the most recent brainstorm/plan in docs/brainstorms/ or docs/plans/.
Step 2: Assess
Read through the document and ask:
- What is unclear?
- What is unnecessary?
- What decision is being avoided?
- What assumptions are unstated?
- Where could scope accidentally expand?
- Is this technically feasible with the current architecture?
- Are there security implications in what's proposed?
These questions surface issues. Don't fix yet--just note what you find.
Step 3: Activate Review Lenses
Based on the document's content, activate specialized review perspectives. Scan for signals and apply matching lenses:
| Lens |
Signals |
What it checks |
| Product |
User-facing features, customer language, market claims, scope decisions |
Problem framing, value proposition clarity, whether scope matches stated goals |
| Design |
UI/UX references, user flows, wireframes, interaction descriptions |
Flow completeness, interaction gaps, accessibility considerations |
| Security |
Auth/authorization, API endpoints, PII, payments, tokens, encryption |
Auth model gaps, data exposure risks, missing threat considerations |
| Scope guardian |
Multiple priority tiers (P0/P1/P2), large requirement count (>8), stretch goals |
Scope creep, premature abstractions, features disguised as requirements |
| Adversarial |
>5 distinct requirements, explicit architectural decisions, high-stakes domains |
Unstated assumptions, optimistic estimates, single points of failure, missing failure modes |
Activate a lens when ANY of its signals match. Most documents trigger 1-2 lenses; brainstorm notes may trigger none. When a lens is active, weave its checks into the assessment and evaluation steps rather than running it as a separate pass.
Step 4: Evaluate
Score the document against these criteria:
| Criterion |
What to Check |
| Clarity |
Problem statement is clear, no vague language ("probably," "consider," "try to") |
| Completeness |
Required sections present, constraints stated, open questions flagged |
| Specificity |
Concrete enough for next step (brainstorm → can plan, plan → can implement) |
| YAGNI |
No hypothetical features, simplest approach chosen |
If invoked within a workflow (after /ia-brainstorm or /ia-plan), also check:
- User intent fidelity -- Document reflects what was discussed, assumptions validated
Step 5: Identify the Critical Improvement
Among everything found in Steps 2-4, does one issue stand out? If something would significantly improve the document's quality, this is the "must address" item. Highlight it prominently.
Step 6: Make Changes
Present your findings, then:
- Auto-fix minor issues (vague language, formatting) without asking
- Ask approval before substantive changes (restructuring, removing sections, changing meaning)
- Update the document inline--no separate files, no metadata sections
Simplification Guidance
Simplification is purposeful removal of unnecessary complexity, not shortening for its own sake.
Simplify when:
- Content serves hypothetical future needs, not current ones
- Sections repeat information already covered elsewhere
- Detail exceeds what's needed to take the next step
- Abstractions or structure add overhead without clarity
Don't simplify:
- Constraints or edge cases that affect implementation
- Rationale that explains why alternatives were rejected
- Open questions that need resolution
Step 7: Reader Test (Optional)
For standalone documents that must be self-contained (onboarding guides, ADRs, external-facing docs), dispatch a zero-context sub-agent to simulate a first-time reader. The sub-agent has no conversation history — it sees only what a future reader would see.
How to run the test:
- Predict 5-10 reader questions from the document's stated goals — one per major section or decision. Mix three kinds:
- Concrete retrieval: "What command sets up the dev environment?"
- Decision rationale: "Why did we pick X over Y?"
- Ambiguity probe: "Could a reader interpret in more than one way?"
- Dispatch a fresh sub-agent with the document attached and the questions. No prior context, no session history.
- Compare the sub-agent's answers against author intent. Also ask the sub-agent directly: "What feels ambiguous? What prior knowledge does this assume? Are there internal contradictions?"
Interpret results:
- Correct, confident answers → document is self-contained for that question.
- Wrong answer with high confidence → document actively misleads. Highest-priority fix.
- Hedged or "insufficient information" → the document has a gap the author didn't notice. Fill it.
- Sub-agent flags ambiguity the author didn't intend → reword for precision.
Skip for context-dependent docs (brainstorm notes, plan files, internal working docs) where the reader will always have prior context. The sub-agent test only adds value when the real reader has no other channel.
Step 8: Offer Next Action
After changes are complete, ask:
- Refine again - Another review pass
- Review complete - Document is ready
Iteration Guidance
After 2 refinement passes, recommend completion--diminishing returns are likely. If the user wants to continue, allow up to 4 passes total. After 4, stop and report "review converged -- further changes require new direction." Do not continue past 4 even on user request without a fresh framing.
Return control to the caller (workflow or user) after selection.
Constraints
- Fix targeted sections, don't rewrite the whole document. If the structure is fundamentally broken, surface the structural problem and ask for permission to restructure.
- Flag missing sections in your review, but don't add them. The user decides what to include.
- Keep changes minimal. If a paragraph needs tightening, tighten it. Don't expand scope.
- Review inline. No separate review files or metadata sections.
Success Criteria
- Document read and scored on all four quality criteria
- Relevant review lenses activated and checks applied
- Critical improvements identified with specific suggestions
- User presented with clear next-action choice (refine or complete)
- Revised document saved if changes were approved
1---2name: document-review3description: Structural review of documents for gaps, clarity, completeness, and organization. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the next workflow step. For exploring new ideas from scratch, use brainstorming instead.4---56# Document Review78Improve brainstorm or plan documents through structured review.910## Step 1: Get the Document1112**If a document path is provided:** Read it, then proceed to Step 2.1314**If no document is specified:** Ask which document to review, or look for the most recent brainstorm/plan in `docs/brainstorms/` or `docs/plans/`.1516## Step 2: Assess1718Read through the document and ask:1920- What is unclear?21- What is unnecessary?22- What decision is being avoided?23- What assumptions are unstated?24- Where could scope accidentally expand?25- Is this technically feasible with the current architecture?26- Are there security implications in what's proposed?2728These questions surface issues. Don't fix yet--just note what you find.2930## Step 3: Activate Review Lenses3132Based on the document's content, activate specialized review perspectives. Scan for signals and apply matching lenses:3334| Lens | Signals | What it checks |35|------|---------|----------------|36| **Product** | User-facing features, customer language, market claims, scope decisions | Problem framing, value proposition clarity, whether scope matches stated goals |37| **Design** | UI/UX references, user flows, wireframes, interaction descriptions | Flow completeness, interaction gaps, accessibility considerations |38| **Security** | Auth/authorization, API endpoints, PII, payments, tokens, encryption | Auth model gaps, data exposure risks, missing threat considerations |39| **Scope guardian** | Multiple priority tiers (P0/P1/P2), large requirement count (>8), stretch goals | Scope creep, premature abstractions, features disguised as requirements |40| **Adversarial** | >5 distinct requirements, explicit architectural decisions, high-stakes domains | Unstated assumptions, optimistic estimates, single points of failure, missing failure modes |4142Activate a lens when ANY of its signals match. Most documents trigger 1-2 lenses; brainstorm notes may trigger none. When a lens is active, weave its checks into the assessment and evaluation steps rather than running it as a separate pass.4344## Step 4: Evaluate4546Score the document against these criteria:4748| Criterion | What to Check |49|-----------|---------------|50| **Clarity** | Problem statement is clear, no vague language ("probably," "consider," "try to") |51| **Completeness** | Required sections present, constraints stated, open questions flagged |52| **Specificity** | Concrete enough for next step (brainstorm → can plan, plan → can implement) |53| **YAGNI** | No hypothetical features, simplest approach chosen |5455If invoked within a workflow (after `/ia-brainstorm` or `/ia-plan`), also check:56- **User intent fidelity** -- Document reflects what was discussed, assumptions validated5758## Step 5: Identify the Critical Improvement5960Among everything found in Steps 2-4, does one issue stand out? If something would significantly improve the document's quality, this is the "must address" item. Highlight it prominently.6162## Step 6: Make Changes6364Present your findings, then:65661. **Auto-fix** minor issues (vague language, formatting) without asking672. **Ask approval** before substantive changes (restructuring, removing sections, changing meaning)683. **Update** the document inline--no separate files, no metadata sections6970### Simplification Guidance7172Simplification is purposeful removal of unnecessary complexity, not shortening for its own sake.7374**Simplify when:**75- Content serves hypothetical future needs, not current ones76- Sections repeat information already covered elsewhere77- Detail exceeds what's needed to take the next step78- Abstractions or structure add overhead without clarity7980**Don't simplify:**81- Constraints or edge cases that affect implementation82- Rationale that explains why alternatives were rejected83- Open questions that need resolution8485## Step 7: Reader Test (Optional)8687For standalone documents that must be self-contained (onboarding guides, ADRs, external-facing docs), dispatch a zero-context sub-agent to simulate a first-time reader. The sub-agent has no conversation history — it sees only what a future reader would see.8889**How to run the test:**90911. **Predict 5-10 reader questions** from the document's stated goals — one per major section or decision. Mix three kinds:92 - Concrete retrieval: "What command sets up the dev environment?"93 - Decision rationale: "Why did we pick X over Y?"94 - Ambiguity probe: "Could a reader interpret <specific phrase> in more than one way?"952. **Dispatch a fresh sub-agent** with the document attached and the questions. No prior context, no session history.963. **Compare the sub-agent's answers** against author intent. Also ask the sub-agent directly: "What feels ambiguous? What prior knowledge does this assume? Are there internal contradictions?"9798**Interpret results:**99100- Correct, confident answers → document is self-contained for that question.101- Wrong answer with high confidence → document actively misleads. Highest-priority fix.102- Hedged or "insufficient information" → the document has a gap the author didn't notice. Fill it.103- Sub-agent flags ambiguity the author didn't intend → reword for precision.104105Skip for context-dependent docs (brainstorm notes, plan files, internal working docs) where the reader will always have prior context. The sub-agent test only adds value when the real reader has no other channel.106107## Step 8: Offer Next Action108109After changes are complete, ask:1101111. **Refine again** - Another review pass1122. **Review complete** - Document is ready113114### Iteration Guidance115116After 2 refinement passes, recommend completion--diminishing returns are likely. If the user wants to continue, allow up to 4 passes total. After 4, stop and report "review converged -- further changes require new direction." Do not continue past 4 even on user request without a fresh framing.117118Return control to the caller (workflow or user) after selection.119120## Constraints121122- Fix targeted sections, don't rewrite the whole document. If the structure is fundamentally broken, surface the structural problem and ask for permission to restructure.123- Flag missing sections in your review, but don't add them. The user decides what to include.124- Keep changes minimal. If a paragraph needs tightening, tighten it. Don't expand scope.125- Review inline. No separate review files or metadata sections.126127## Success Criteria128129- Document read and scored on all four quality criteria130- Relevant review lenses activated and checks applied131- Critical improvements identified with specific suggestions132- User presented with clear next-action choice (refine or complete)133- Revised document saved if changes were approved