reviewer — for Claude Code reviewer, archon, community, for Claude Code, ide skills, ai-agents, ai-skills, claude-code, copilot, cross-platform

v1.0.0

Об этом навыке

Подходящий сценарий: Ideal for AI agents that need when to use this skill. Локализованное описание: - # Reviewer Skill This skill compares implementation output against the original specification and produces a comprehensive, human-readable HTML compliance report. It covers ai-agents, ai-skills, archon workflows. This AI agent skill supports Claude Code, Cursor, and

Возможности

When to Use This Skill
User has completed implementation and wants to verify spec compliance
User asks to "review", "verify", "audit", or "check" implementation against spec
User needs a compliance report comparing code to requirements
User wants a quality gate assessment before shipping

# Ключевые темы

SufficientDaikon SufficientDaikon
[7]
[0]
Обновлено: 3/30/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

Подходящий сценарий: Ideal for AI agents that need when to use this skill. Локализованное описание: - # Reviewer Skill This skill compares implementation output against the original specification and produces a comprehensive, human-readable HTML compliance report. It covers ai-agents, ai-skills, archon workflows. This AI agent skill supports Claude Code, Cursor, and

Зачем использовать этот навык

Рекомендация: reviewer helps agents when to use this skill. 83 skills, 10 agents, 5 cognitive synapses, enforced guardrails. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Подходит лучше всего

Подходящий сценарий: Ideal for AI agents that need when to use this skill.

Реализуемые кейсы использования for reviewer

Сценарий использования: Applying When to Use This Skill
Сценарий использования: Applying User has completed implementation and wants to verify spec compliance
Сценарий использования: Applying User asks to "review", "verify", "audit", or "check" implementation against spec

! Безопасность и ограничения

  • Ограничение: User needs a compliance report comparing code to requirements
  • Ограничение: 60-79%: NEEDS REVISION — Significant gaps
  • Ограничение: The report MUST include:

About The Source

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Labs-демо

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ и шаги установки

These questions and steps mirror the structured data on this page for better search understanding.

? Частые вопросы

Что такое reviewer?

Подходящий сценарий: Ideal for AI agents that need when to use this skill. Локализованное описание: - # Reviewer Skill This skill compares implementation output against the original specification and produces a comprehensive, human-readable HTML compliance report. It covers ai-agents, ai-skills, archon workflows. This AI agent skill supports Claude Code, Cursor, and

Как установить reviewer?

Выполните команду: npx killer-skills add SufficientDaikon/archon. Она работает с Cursor, Windsurf, VS Code, Claude Code и более чем 19 другими IDE.

Для чего можно использовать reviewer?

Ключевые сценарии использования: Сценарий использования: Applying When to Use This Skill, Сценарий использования: Applying User has completed implementation and wants to verify spec compliance, Сценарий использования: Applying User asks to "review", "verify", "audit", or "check" implementation against spec.

Какие IDE совместимы с reviewer?

Этот навык совместим с Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Для единой установки используйте CLI Killer-Skills.

Есть ли ограничения у reviewer?

Ограничение: User needs a compliance report comparing code to requirements. Ограничение: 60-79%: NEEDS REVISION — Significant gaps. Ограничение: The report MUST include:.

Как установить этот skill

  1. 1. Откройте терминал

    Откройте терминал или командную строку в директории проекта.

  2. 2. Запустите команду установки

    Выполните: npx killer-skills add SufficientDaikon/archon. CLI автоматически определит вашу IDE или агента и настроит навык.

  3. 3. Начните использовать skill

    Skill уже активен. Ваш AI-агент может сразу использовать reviewer в текущем проекте.

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

reviewer

Install reviewer, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

Reviewer Skill

This skill compares implementation output against the original specification and produces a comprehensive, human-readable HTML compliance report.

When to Use This Skill

  • User has completed implementation and wants to verify spec compliance
  • User asks to "review", "verify", "audit", or "check" implementation against spec
  • User needs a compliance report comparing code to requirements
  • User wants a quality gate assessment before shipping

Review Process

Step 1: Gather Inputs

Required:

  1. The specification file (spec.md or equivalent)
  2. The project directory (implemented code)

Optional but helpful: 3. tasks.md (implementation task tracker) 4. Completion report from the implementer 5. Deviation log from the implementer

Step 2: Systematic Audit

Perform EACH of these audits:

A. User Story Coverage

For EACH story in the spec:

CheckHow to Verify
Implemented?Search codebase for story-related components
Acceptance scenarios satisfied?Check each Given/When/Then against code behavior
Tests exist?Search test files for story-related tests
Tests pass?Run the test suite if possible

Score: ✅ PASS / ⚠️ PARTIAL / ❌ FAIL / ⬜ MISSING

B. Functional Requirements Coverage

For EACH FR-XXX:

  • Find the code that implements it (file + line)
  • Verify correctness against the spec wording
  • Check if a test covers it

Score: ✅ IMPLEMENTED / ⚠️ PARTIAL / ❌ INCORRECT / ⬜ MISSING

C. Non-Functional Requirements

For EACH NFR:

  • Find evidence in code (caching, validation, error handling, etc.)
  • Assess whether it's measurably met

Score: ✅ MET / ⚠️ PARTIALLY / ❌ NOT MET / ⬜ NOT ADDRESSED

D. Success Criteria

For EACH SC-XXX:

  • Is it verifiable with the current implementation?
  • What evidence supports it?

Score: ✅ VERIFIABLE / ⚠️ LIKELY / ❌ UNLIKELY / ⬜ NOT ADDRESSED

E. Edge Cases

For EACH edge case in the spec:

  • Is it handled in code? (find the handler)
  • Is the handling correct?

Score: ✅ HANDLED / ⚠️ PARTIAL / ❌ UNHANDLED

Step 3: Calculate Scores

Per-item scoring:

  • ✅ = 1.0 points
  • ⚠️ = 0.5 points
  • ❌ = 0.0 points
  • ⬜ = 0.0 points

Overall compliance = (total points / total possible) × 100%

Verdict:

  • 95-100%: APPROVED — Ship it
  • 80-94%: APPROVED WITH CONDITIONS — Minor fixes needed
  • 60-79%: NEEDS REVISION — Significant gaps
  • Below 60%: REJECTED — Major rework required

Step 4: Generate HTML Report

Use the template at templates/report-template.html as the base.

The report MUST include:

  1. Executive Summary — Score, verdict, key stats
  2. User Story Matrix — Visual coverage table
  3. Requirements Traceability — FR → Code → Test mapping
  4. Success Criteria Dashboard — Visual status indicators
  5. Findings — Categorized by severity:
    • 🔴 Critical: Feature broken, security issue, data loss risk
    • 🟠 Major: Requirement not implemented, test failing
    • 🟡 Minor: Partial implementation, missing edge case
    • 🔵 Info: Suggestion, pattern recommendation
  6. Deviations — Analysis of any implementation deviations
  7. Verdict & Recommendations — Overall assessment

Step 5: Save & Report

  1. Save HTML report as review-report.html in the project root
  2. Present summary to user:
    • Overall compliance percentage
    • Verdict (APPROVED / NEEDS REVISION / etc.)
    • Critical findings count
    • Top 3 issues to address (if any)

Rules

DO:

  • Check EVERY requirement — no sampling
  • Include file paths and line numbers as evidence
  • Credit good patterns alongside issues
  • Be specific and actionable in recommendations
  • Generate a self-contained HTML file (inline CSS, no external deps)

DON'T:

  • Be vague ("some issues found" — name them)
  • Penalize for spec issues (that's spec-writer's domain)
  • Include opinions not grounded in the spec
  • Skip non-functional or edge case checks
  • Generate report without reading ALL code

Связанные навыки

Looking for an alternative to reviewer or another community skill for your workflow? Explore these related open-source skills.

Показать все

openclaw-release-maintainer

Logo of openclaw
openclaw

Локализованное описание: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

widget-generator

Logo of f
f

Локализованное описание: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor

flags

Logo of vercel
vercel

Локализованное описание: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
Браузер

pr-review

Logo of pytorch
pytorch

Локализованное описание: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
Разработчик