skills.rest
daudaudinang
daudaudinangCOMMUNITY
Explore all skills by this author →
GitHub

review-implement

Review implemented code against plans using four personas and output machine verdicts.

Updated Apr 14, 2026
Search Tags:#evidence#review#code-quality#code-review#multi-persona#verdict#plan-compliance
One-click install
npx skills add https://github.com/daudaudinang/vibecode --skill review-implement
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review-implement
Source: https://github.com/daudaudinang/vibecode/tree/main/.agents/skills/review-implement
Command: npx skills add https://github.com/daudaudinang/vibecode --skill review-implement

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Review quality for implemented code against plans by coordinating four mandatory personas to ensure evidence-based verdicts and auditability.

Core Features & Use Cases

  • Boundary Check — Verify no Do NOT Modify files were changed and that changes stay within scope.
  • Implementation Coverage Check — Ensure delivered code aligns with the plan, ACs, and spec baseline.
  • Multi-Persona Code Review — Concurrent assessments from Senior PM, Senior UI/UX Designer, Senior Developer, and System Architecture.
  • Finding Validation — Require evidence and context validation for every finding to justify machine verdicts.
  • Scoring & Output — Produce quantitative scores and a machine-ready status (PASS/NEEDS_REVISION/FAIL) for automation pipelines.
  • Execution Modes — Supports Standard mode for first-time reviews and Fast mode for iterative reviews, based on workflow history.

Quick Start

Invoke the review with /lp:review-implement <plan_file_path> to start the multi-persona code review against the specified plan.

Frequently Asked Questions about review-implement

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate multi-persona code review for implemented plan changes?▼

Multi-persona code review automation coordinates concurrent assessments from Senior PM, UI/UX, Developer, and Architecture roles to validate implemented changes against plan baselines. It generates evidence-based machine verdicts with quantitative scores and standardized statuses for CI/CD integration.

How does evidence-based finding validation work in automated code review?▼

Evidence-based finding validation requires verified context and proof to justify every machine verdict generated during code review. This mechanism ensures auditability by enforcing that no PASS, NEEDS_REVISION, or FAIL status is produced without supporting evidence from the implementation diff.

What is the best way to check implementation coverage against acceptance criteria?▼

Implementation coverage verification checks delivered code alignment against the plan, acceptance criteria, and spec baseline. This process ensures the implementation fulfills all requirements before producing a machine-ready status for the automation pipeline.

Can I use fast mode for iterative code reviews instead of standard mode?▼

Fast mode supports iterative code reviews based on workflow history, while standard mode handles first-time reviews. Both modes apply boundary checks, coverage verification, and multi-persona assessments to output standardized results into the pipeline.

Does the code review workflow enforce boundary checks for Do NOT Modify files?▼

Boundary checks verify that no Do NOT Modify files were changed and that all code changes stay within the defined scope. This enforcement prevents unauthorized modifications during the multi-persona review process.

How to output machine-ready PASS or FAIL verdicts from a code review pipeline?▼

Machine-ready verdicts output standardized PASS, NEEDS_REVISION, or FAIL statuses alongside quantitative scores after multi-persona code review completes. These results integrate directly into automation pipelines for automated quality gating.

Related Skills

Explore More Software Engineering Skills→
KohlexKohlex

plan-review-gate

Enforce two-stage spec-then-quality review on PLANs before wave-collection.

Official
Advanced
FrekiManagarmFrekiManagarm

Verification & Quality Assurance

Compute truth scores and run correctness, security, performance, and documentation checks with JSON reports and Git rollback.

Community
Advanced
denis-pingindenis-pingin

fixme-review-code

Review code changes against plan and spec with cited evidence.

Community
Advanced
llmh333llmh333

springboot-verification

Run Maven or Gradle verification loops with tests, coverage, and CVE scans.

Community
Intermediate