solution-audit

Audit product-to-implementation and architecture-to-code coherence

Audit documentation quality — accuracy, structure, and usefulness

Audit onboarding experience — setup clarity, prerequisites, time-to-first-success

View, compare, and analyze previous audit reports

Comprehensive UX audit — CLI ergonomics, textual quality, learnability, and workflow friction

Deep analysis agent for product-to-implementation and architecture-to-code coherence. Use this agent when thorough cross-referencing between documentation, architecture decisions, and actual code is needed to detect drift, ghost features, boundary violations, and structural misalignment. <example> Context: User suspects docs don't match implementation user: "Check if our README promises match what's actually implemented" assistant: "I'll use the coherence-analyzer agent to cross-reference documentation with actual code." </example> <example> Context: User wants to verify architecture integrity user: "Are our module boundaries being respected in the code?" assistant: "I'll use the coherence-analyzer agent to trace imports and check boundary violations." </example>

Orchestrates comprehensive solution audits across all quality dimensions. Use this agent when a full, multi-dimensional quality assessment is needed, combining coherence analysis, documentation review, onboarding evaluation, and UX inspection into a unified report with prioritized findings. <example> Context: User wants a complete quality check of their project user: "Run a full audit of this project" assistant: "I'll use the solution-auditor agent to perform a comprehensive multi-dimensional audit." </example> <example> Context: User is preparing for release and wants quality validation user: "Check if this project is ready for release" assistant: "I'll use the solution-auditor agent to assess release readiness across all quality dimensions." </example> <example> Context: User inherited a codebase and wants to understand its state user: "Give me a complete quality assessment of this codebase" assistant: "I'll use the solution-auditor agent for a thorough multi-dimensional analysis." </example>

Specialized agent for comparing spec/blueprint documents against actual implementation. Detects implementation drift, ghost features, and undocumented capabilities. Use this agent when comparing a spec to code, reviewing a blueprint for implementation gaps, running /blueprint-review, or asked to "check spec vs code", "find gaps in the implementation", "review this spec", "spec drift", "blueprint gap analysis". <example> Context: User wants to verify implementation matches spec user: "Check if our implementation matches the spec in docs/spec.md" assistant: "I'll use the spec-reviewer agent to compare the spec against the current implementation." <commentary>Spec vs implementation comparison triggers spec-reviewer.</commentary> </example> <example> Context: Blueprint review session initiated by /blueprint-review user: "/blueprint-review docs/v2-blueprint.md" assistant: "Running blueprint review. Dispatching spec-reviewer to analyze spec gaps." <commentary>One of 3 parallel agents in /blueprint-review workflow.</commentary> </example>

Deep UX analysis agent covering CLI ergonomics, textual communication quality, and learnability. Use this agent when a thorough user experience review is needed, examining command-line interfaces, user-facing text, error messages, workflow friction, and overall learnability from multiple angles. <example> Context: User wants to improve their CLI tool's user experience user: "Is my CLI user-friendly? What should I improve?" assistant: "I'll use the ux-reviewer agent for a comprehensive UX analysis." </example> <example> Context: User is concerned about error messages and help text user: "Review the quality of our error messages and help output" assistant: "I'll use the ux-reviewer agent to analyze all user-facing text." </example> <example> Context: User wants to reduce friction in the user workflow user: "Where are the friction points in our user workflow?" assistant: "I'll use the ux-reviewer agent to map the workflow and identify friction." </example>

This skill should be used when the user asks to "audit architecture", "check architecture drift", "find module coupling", "detect boundary violations", "review code structure", "check dependency direction", or needs to verify that declared architecture matches actual code organization and dependencies.

This skill should be used when the user asks to "audit CLI UX", "check command ergonomics", "review CLI help output", "evaluate command-line interface", "check flag consistency", "audit CLI discoverability", or needs to assess the usability, ergonomics, and consistency of a command-line interface.

This skill should be used when the user asks to "audit documentation", "check doc quality", "find broken links", "review README", "check if docs are up to date", "assess documentation structure", or needs to evaluate whether documentation is accurate, useful, and well-organized beyond mere existence.

This skill should be used when the user asks to "audit learnability", "check workflow friction", "assess learning curve", "review user workflow", "find friction points", "evaluate cognitive load", "check progressive complexity", or needs to evaluate how learnable a solution is and whether its workflow minimizes unnecessary friction.

This skill should be used when the user asks to "audit onboarding", "check setup experience", "test quickstart", "evaluate time-to-first-success", "review installation steps", "assess new user experience", or needs to evaluate how easy it is for a new user to go from zero to first meaningful result.

3 hooks across 3 events