Nm Pensive Unified Review
by @athola
Orchestrates multi-domain review (code, arch, tests, security) in a single pass
clawhub install nm-pensive-unified-reviewπ About This Skill
name: unified-review description: | Orchestrate multiple review types into a single multi-domain review with integrated reporting version: 1.9.4 triggers: - review - orchestration - code-quality - analysis - multi-domain metadata: {"openclaw": {"homepage": "https://github.com/athola/claude-night-market/tree/master/plugins/pensive", "emoji": "\ud83e\udd9e", "requires": {"config": ["night-market.pensive:shared", "night-market.imbue:proof-of-work", "night-market.imbue:structured-output"]}}} source: claude-night-market source_plugin: pensive
> Night Market Skill β ported from claude-night-market/pensive. For the full experience with agents, hooks, and commands, install the Claude Code plugin.
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-reviewFocus 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
pytest -v to verify tests pass.When To Use
When NOT To Use
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
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")
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:
pensive:math-review is NOT an agent)pensive:code-reviewer covers multiple domains, dispatch once with combined scopegeneral-purpose and instruct it to invoke the Skill tool4. Integrate Findings
Deferred capture for backlog findings: Findings that are triaged to the backlog (out-of-scope for the current review or deferred by the team) should be preserved so they are not lost between review cycles. For each finding assigned to the backlog, run:
python3 scripts/deferred_capture.py \
--title "" \
--source review \
--context "Review dimension: . "
The bug-review, api-review,
architecture-review).
This runs automatically after the action plan is finalised,
without prompting the user.
Review Modes
Auto-Detect (default)
Automatically selects skills based on codebase analysis.Focused Mode
Run specific review domains:/full-review api β api-review only/full-review architecture β architecture-review only/full-review bugs β bug-review only/full-review tests β test-review onlyFull Review Mode
Run all applicable review skills:/full-review all β Execute all detected skillsQuality Gates
Each review must: 1. Establish proper context 2. Execute all selected skills successfully 3. Document findings with evidence 4. Prioritize recommendations by impact 5. Create action plan with owners
Deliverables
Executive Summary
Domain-Specific Reports
Integrated Action Plan
Modular Architecture
All review skills use a hub-and-spoke architecture with progressive loading:
pensive:shared: Common workflow, output templates, quality checklistsmodules/: Domain-specific details loaded on demandimbue:proof-of-work, imbue:diff-analysis/modules/risk-assessment-frameworkThis reduces token usage by 50-70% for focused reviews while maintaining full capabilities.
Exit Criteria
Supporting Modules
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.
β‘ When to Use
π‘ Examples
# Auto-detect and run appropriate reviews
/full-reviewFocus 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
pytest -v to verify tests pass.π Tips & Best Practices
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.