Table of Contents
Unified Review Orchestration
Intelligently selects and executes appropriate review skills based on codebase analysis and context.
Quick Start
# Auto-detect and run appropriate reviews
/full-review
# Focus on specific areas
/full-review api # API surface review
/full-review architecture # Architecture review
/full-review bugs # Bug hunting
/full-review tests # Test suite review
/full-review all # Run all applicable skills
Verification: Run pytest -v to verify tests pass.
When To Use
- Starting a full code review
- Reviewing changes across multiple domains
- Need intelligent selection of review skills
- Want integrated reporting from multiple review types
- Before merging major feature branches
When NOT To Use
- Specific review type known
- Test-review
- Architecture-only focus - use
architecture-review
- Specific review type known
Review Skill Selection Matrix
| Codebase Pattern |
Review Skills |
Triggers |
Rust files (*.rs, Cargo.toml) |
rust-review, bug-review, api-review |
Rust project detected |
API changes (openapi.yaml, routes/) |
api-review, architecture-review |
Public API surfaces |
Test files (test_*.py, *_test.go) |
test-review, bug-review |
Test infrastructure |
| Makefile/build system |
makefile-review, architecture-review |
Build complexity |
| Mathematical algorithms |
math-review, bug-review |
Numerical computation |
| Architecture docs/ADRs |
architecture-review, api-review |
System design |
| General code quality |
bug-review, test-review |
Default review |
Workflow
1. Analyze Repository Context
- Detect primary languages from extensions and manifests
- Analyze git status and diffs for change scope
- Identify project structure (monorepo, microservices, library)
- Detect build systems, testing frameworks, documentation
2. Select Review Skills
# Detection logic
if has_rust_files():
schedule_skill("rust-review")
if has_api_changes():
schedule_skill("api-review")
if has_test_files():
schedule_skill("test-review")
if has_makefiles():
schedule_skill("makefile-review")
if has_math_code():
schedule_skill("math-review")
if has_architecture_changes():
schedule_skill("architecture-review")
# Default
schedule_skill("bug-review")
Verification: Run pytest -v to verify tests pass.
3. Execute Reviews
Dispatch selected skills concurrently via the Agent tool.
Use this mapping to resolve skill names to agent types:
| Skill Name |
Agent Type |
Notes |
| bug-review |
pensive:code-reviewer |
Covers bugs, API, tests |
| api-review |
pensive:code-reviewer |
Same agent, API focus |
| test-review |
pensive:code-reviewer |
Same agent, test focus |
| architecture-review |
pensive:architecture-reviewer |
ADR compliance |
| rust-review |
pensive:rust-auditor |
Rust-specific |
| code-refinement |
pensive:code-refiner |
Duplication, quality |
| math-review |
general-purpose |
Prompt: invoke Skill(pensive:math-review) |
| makefile-review |
general-purpose |
Prompt: invoke Skill(pensive:makefile-review) |
| shell-review |
general-purpose |
Prompt: invoke Skill(pensive:shell-review) |
Rules:
- Never use skill names as agent types (e.g.,
pensive:math-review is NOT an agent)
- When
pensive:code-reviewer covers multiple domains, dispatch once with combined scope
- For skills without dedicated agents, use
general-purpose and instruct it to invoke the Skill tool
- Maintain consistent evidence logging across all agents
- Track progress via TodoWrite
4. Integrate Findings
- Consolidate findings across domains
- Identify cross-domain patterns
- Prioritize by impact and effort
- Generate unified action plan
Review Modes
Auto-Detect (default)
Automatically selects skills based on codebase analysis.
Focused Mode
Run specific review domains:
/full-review api → api-review only
/full-review architecture → architecture-review only
/full-review bugs → bug-review only
/full-review tests → test-review only
Full Review Mode
Run all applicable review skills:
/full-review all → Execute all detected skills
Quality Gates
Each review must:
- Establish proper context
- Execute all selected skills successfully
- Document findings with evidence
- Prioritize recommendations by impact
- Create action plan with owners
Deliverables
Executive Summary
- Overall codebase health assessment
- Critical issues requiring immediate attention
- Review frequency recommendations
Domain-Specific Reports
- API surface analysis and consistency
- Architecture alignment with ADRs
- Test coverage gaps and improvements
- Bug analysis and security findings
- Performance and maintainability recommendations
Integrated Action Plan
- Prioritized remediation tasks
- Cross-domain dependencies
- Assigned owners and target dates
- Follow-up review schedule
Modular Architecture
All review skills use a hub-and-spoke architecture with progressive loading:
pensive:shared: Common workflow, output templates, quality checklists
- Each skill has
modules/: Domain-specific details loaded on demand
- Cross-plugin deps:
imbue:proof-of-work, imbue:diff-analysis/modules/risk-assessment-framework
This reduces token usage by 50-70% for focused reviews while maintaining full capabilities.
Exit Criteria
- All selected review skills executed
- Findings consolidated and prioritized
- Action plan created with ownership
- Evidence logged per structured output format
Supporting Modules
- Review workflow core - standard 5-step workflow pattern for all pensive reviews
- Output format templates - finding entry, severity, action item templates
- Quality checklist patterns - pre-review, analysis, evidence, deliverable checklists
Troubleshooting
Common Issues
If the auto-detection fails to identify the correct review skills, explicitly specify the mode (e.g., /full-review rust instead of just /full-review). If integration fails, check that TodoWrite logs are accessible and that evidence files were correctly written by the individual skills.
1---2name: unified-review3description: 'Use this skill when orchestrating multiple review types. Use when general4 review needed without knowing which specific skill applies, full multi-domain review5 desired, integrated reporting needed. Do not use when specific review type known6 - use bug-review, test-review, etc. DO NOT use when: architecture-only focus - use7 architecture-review.'8category: orchestration9tags:10- review11- orchestration12- code-quality13- analysis14- multi-domain15tools:16- skill-selector17- context-analyzer18- report-integrator19usage_patterns:20- auto-detect-review21- full-review22- focused-review23complexity: intermediate24estimated_tokens: 40025progressive_loading: true26dependencies:27- pensive:shared28- imbue:proof-of-work29- imbue:structured-output30orchestrates:31- pensive:rust-review32- pensive:api-review33- pensive:architecture-review34- pensive:bug-review35- pensive:test-review36- pensive:makefile-review37- pensive:math-review38metadata:39 source: https://skillmd.com/skills/micsapp/unified-review40---4142## Table of Contents4344- [Quick Start](#quick-start)45- [When to Use](#when-to-use)46- [Review Skill Selection Matrix](#review-skill-selection-matrix)47- [Workflow](#workflow)48- [1. Analyze Repository Context](#1-analyze-repository-context)49- [2. Select Review Skills](#2-select-review-skills)50- [3. Execute Reviews](#3-execute-reviews)51- [4. Integrate Findings](#4-integrate-findings)52- [Review Modes](#review-modes)53- [Auto-Detect (default)](#auto-detect-(default))54- [Focused Mode](#focused-mode)55- [Full Review Mode](#full-review-mode)56- [Quality Gates](#quality-gates)57- [Deliverables](#deliverables)58- [Executive Summary](#executive-summary)59- [Domain-Specific Reports](#domain-specific-reports)60- [Integrated Action Plan](#integrated-action-plan)61- [Modular Architecture](#modular-architecture)62- [Exit Criteria](#exit-criteria)636465# Unified Review Orchestration6667Intelligently selects and executes appropriate review skills based on codebase analysis and context.6869## Quick Start7071```bash72# Auto-detect and run appropriate reviews73/full-review7475# Focus on specific areas76/full-review api # API surface review77/full-review architecture # Architecture review78/full-review bugs # Bug hunting79/full-review tests # Test suite review80/full-review all # Run all applicable skills81```82**Verification:** Run `pytest -v` to verify tests pass.8384## When To Use8586- Starting a full code review87- Reviewing changes across multiple domains88- Need intelligent selection of review skills89- Want integrated reporting from multiple review types90- Before merging major feature branches9192## When NOT To Use9394- Specific review type known95 - use bug-review96- Test-review97- Architecture-only focus - use98 architecture-review99- Specific review type known100 - use bug-review101102## Review Skill Selection Matrix103104| Codebase Pattern | Review Skills | Triggers |105|-----------------|---------------|----------|106| Rust files (`*.rs`, `Cargo.toml`) | rust-review, bug-review, api-review | Rust project detected |107| API changes (`openapi.yaml`, `routes/`) | api-review, architecture-review | Public API surfaces |108| Test files (`test_*.py`, `*_test.go`) | test-review, bug-review | Test infrastructure |109| Makefile/build system | makefile-review, architecture-review | Build complexity |110| Mathematical algorithms | math-review, bug-review | Numerical computation |111| Architecture docs/ADRs | architecture-review, api-review | System design |112| General code quality | bug-review, test-review | Default review |113114## Workflow115116### 1. Analyze Repository Context117- Detect primary languages from extensions and manifests118- Analyze git status and diffs for change scope119- Identify project structure (monorepo, microservices, library)120- Detect build systems, testing frameworks, documentation121122### 2. Select Review Skills123```python124# Detection logic125if has_rust_files():126 schedule_skill("rust-review")127if has_api_changes():128 schedule_skill("api-review")129if has_test_files():130 schedule_skill("test-review")131if has_makefiles():132 schedule_skill("makefile-review")133if has_math_code():134 schedule_skill("math-review")135if has_architecture_changes():136 schedule_skill("architecture-review")137# Default138schedule_skill("bug-review")139```140**Verification:** Run `pytest -v` to verify tests pass.141142### 3. Execute Reviews143144Dispatch selected skills concurrently via the Agent tool.145Use this mapping to resolve skill names to agent types:146147| Skill Name | Agent Type | Notes |148|---|---|---|149| bug-review | `pensive:code-reviewer` | Covers bugs, API, tests |150| api-review | `pensive:code-reviewer` | Same agent, API focus |151| test-review | `pensive:code-reviewer` | Same agent, test focus |152| architecture-review | `pensive:architecture-reviewer` | ADR compliance |153| rust-review | `pensive:rust-auditor` | Rust-specific |154| code-refinement | `pensive:code-refiner` | Duplication, quality |155| math-review | `general-purpose` | Prompt: invoke `Skill(pensive:math-review)` |156| makefile-review | `general-purpose` | Prompt: invoke `Skill(pensive:makefile-review)` |157| shell-review | `general-purpose` | Prompt: invoke `Skill(pensive:shell-review)` |158159**Rules:**160- Never use skill names as agent types (e.g., `pensive:math-review` is NOT an agent)161- When `pensive:code-reviewer` covers multiple domains, dispatch once with combined scope162- For skills without dedicated agents, use `general-purpose` and instruct it to invoke the Skill tool163- Maintain consistent evidence logging across all agents164- Track progress via TodoWrite165166### 4. Integrate Findings167- Consolidate findings across domains168- Identify cross-domain patterns169- Prioritize by impact and effort170- Generate unified action plan171172## Review Modes173174### Auto-Detect (default)175Automatically selects skills based on codebase analysis.176177### Focused Mode178Run specific review domains:179- `/full-review api` → api-review only180- `/full-review architecture` → architecture-review only181- `/full-review bugs` → bug-review only182- `/full-review tests` → test-review only183184### Full Review Mode185Run all applicable review skills:186- `/full-review all` → Execute all detected skills187188## Quality Gates189190Each review must:1911. Establish proper context1922. Execute all selected skills successfully1933. Document findings with evidence1944. Prioritize recommendations by impact1955. Create action plan with owners196197## Deliverables198199### Executive Summary200- Overall codebase health assessment201- Critical issues requiring immediate attention202- Review frequency recommendations203204### Domain-Specific Reports205- API surface analysis and consistency206- Architecture alignment with ADRs207- Test coverage gaps and improvements208- Bug analysis and security findings209- Performance and maintainability recommendations210211### Integrated Action Plan212- Prioritized remediation tasks213- Cross-domain dependencies214- Assigned owners and target dates215- Follow-up review schedule216217## Modular Architecture218219All review skills use a hub-and-spoke architecture with progressive loading:220221- **`pensive:shared`**: Common workflow, output templates, quality checklists222- **Each skill has `modules/`**: Domain-specific details loaded on demand223- **Cross-plugin deps**: `imbue:proof-of-work`, `imbue:diff-analysis/modules/risk-assessment-framework`224225This reduces token usage by 50-70% for focused reviews while maintaining full capabilities.226227## Exit Criteria228229- All selected review skills executed230- Findings consolidated and prioritized231- Action plan created with ownership232- Evidence logged per structured output format233## Supporting Modules234235- [Review workflow core](modules/review-workflow-core.md) - standard 5-step workflow pattern for all pensive reviews236- [Output format templates](modules/output-format-templates.md) - finding entry, severity, action item templates237- [Quality checklist patterns](modules/quality-checklist-patterns.md) - pre-review, analysis, evidence, deliverable checklists238239## Troubleshooting240241### Common Issues242243If the auto-detection fails to identify the correct review skills, explicitly specify the mode (e.g., `/full-review rust` instead of just `/full-review`). If integration fails, check that `TodoWrite` logs are accessible and that evidence files were correctly written by the individual skills.