Claude-toolbox review-design

install
source · Clone the upstream repo
git clone https://github.com/serpro69/claude-toolbox
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/serpro69/claude-toolbox "$T" && mkdir -p ~/.claude/skills && cp -r "$T/klaude-plugin/skills/review-design" ~/.claude/skills/serpro69-claude-toolbox-review-design && rm -rf "$T"
manifest: klaude-plugin/skills/review-design/SKILL.md
source content

Design Review

Conventions

Read capy knowledge base conventions at shared-capy-knowledge-protocol.md.

Overview

Pre-implementation review gate that evaluates design documents produced by

design
before code is written. Sits between
design
(creates docs) and
implement
(executes them). Reviews two dimensions: document quality/structure (completeness, internal consistency, clarity, convention adherence) and technical soundness (architectural viability, edge cases, failure modes, trade-off analysis).

Review Modes

Standard Mode (
/kk:review-design
)

Reviews design documents in the main conversation context. Fast, single-pass review using the workflow below.

Isolated Mode (
/kk:review-design:isolated
)

Delegates detection to independent reviewers that did not participate in the design, then annotates their findings with author context. Two parallel reviewers: a

design-reviewer
sub-agent and
pal codereview
(external model in native format). Produces a report organized by agreement level with corroborated findings highlighted.

  • Cost: Higher (sub-agent + external model + annotation)
  • Isolation: True — reviewers have zero authorship bias or session context
  • Degradation: Graceful — if one reviewer fails, proceeds with the other; if both fail, suggests standard mode fallback
  • Best for: When extra rigor is worth the cost (before starting implementation of high-stakes features)

See review-isolated.md for the isolated workflow.

Finding Types

TypeCodeDescription
Incomplete Spec
INCOMPLETE
Section lacks sufficient detail for implementation
Internal Inconsistency
INCONSISTENT
Two parts of the docs contradict each other
Technical Risk
TECH_RISK
Architecture choice has unaddressed failure modes, scalability concerns, or edge cases
Missing Concern
MISSING
Cross-cutting concern is absent (error handling, migration, backwards compatibility)
Ambiguity
AMBIGUOUS
Requirements can be interpreted multiple ways, likely to cause implementation divergence
Structure Issue
STRUCTURE
Document doesn't follow project conventions — missing sections, vague subtasks

Severity Levels

LevelNameDescriptionAction
P0CriticalFundamental flaw — design will not work as described, or critical requirement is missingMust fix before implementation
P1HighSignificant gap — likely to cause rework or wrong implementationShould fix before implementation
P2MediumModerate concern — ambiguity or missing detail that could cause confusionFix or create follow-up
P3LowMinor — style, structure, or nitpickOptional

Workflow

Phases:

  1. Load documents — parse scope, locate feature directory, read in-scope docs
  2. Capy search — search
    kk:arch-decisions
    and
    kk:review-findings
    for prior context
  3. Document quality review — completeness, clarity, consistency, convention adherence
  4. Technical soundness review — viability, edge cases, trade-offs, scalability, testing strategy
  5. Self-check and confidence assessment — re-read, question assumptions, assign confidence
  6. Present findings with next steps

See review-process.md for the detailed step-by-step process.

Invocation

Standard mode — reviews

design.md
+
implementation.md
by default:

/kk:review-design [feature-name]

Standard mode with scope — review specific documents:

/kk:review-design [feature-name] design
/kk:review-design [feature-name] implementation
/kk:review-design [feature-name] tasks
/kk:review-design [feature-name] all
ScopeDocuments reviewed
(none)
design.md
+
implementation.md
(default)
design
design.md
only
implementation
implementation.md
only
tasks
tasks.md
only
all
design.md
+
implementation.md
+
tasks.md

Isolated mode with independent sub-agents:

/kk:review-design:isolated [feature-name]
/kk:review-design:isolated [feature-name] tasks