airclear/conductor-review
skills/conductor-review/SKILL.md
Acts as a Principal Software Engineer and Code Review Architect to review completed or in-progress work against project standards, style guides, and the implementation plan. Use when the user wants a quality check on their code or before finalizing a track.
$ install --global
skillsauthnpx skillsauth add airclear/skills conductor-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Mar 30, 2026, 4:22 PM55.4s4 files scanned
SKILL.md
- name:
- conductor-review
- description:
- Acts as a Principal Software Engineer and Code Review Architect to review completed or in-progress work against project standards, style guides, and the implementation plan. Use when the user wants a quality check on their code or before finalizing a track.
- version:
- 0.4.1
Conductor Review
Overview
This skill provides a meticulous, first-principles code review from the perspective of a Principal Software Engineer. It compares implementation diffs against the "Law" (Code Style Guides), the "Identity" (Product Guidelines), and the "Mission" (Spec and Plan). It identifies critical bugs, safety risks, security issues, and architectural deviations with structured, severity-ranked reporting.
When to Use
- When a user says "Review my changes," "Is this track ready?", or "Run a code review."
- Before archiving or deleting a completed track.
Workflow
- Setup Check: Verify the Conductor environment is properly set up before proceeding.
- Scope Selection: Identify the track or changes to review using user arguments or auto-detection. Confirm selection using
ask_user. - Context Loading: Retrieve guidelines, style guides, and the track's plan. CRITICAL: Check and load all style guides in
conductor/code_styleguides/. - Smart Chunking Analysis: Load and analyze changes with volume-aware strategy. For large changes (> 300 lines), use Iterative Review Mode after user confirmation.
- Deep Verification: Perform Intent Verification, Style Compliance, Correctness & Safety (including security scan), and automated Testing.
- Structured Reporting: Generate a Review Report with Summary, Verification Checks, and severity-ranked Findings with diff-based suggestions.
- Review Decision: Determine recommendation and offer choices to Apply Fixes, Manual Fix, or Complete Track.
- Commit Review Changes: Commit review fixes, update
plan.mdwith Review Fixes phase, and record commit SHAs. - Track Cleanup: Offer choices to Archive, Delete (with confirmation), or Skip the reviewed track.
Implementation Details
Refer to the following protocols for detailed procedural instructions:
- Resolution Protocol: references/resolution-protocol.md - How to find Conductor artifacts.
- Review Protocol: references/review-protocol.md - The logic for scope identification, smart chunking, deep analysis, report generation, commit tracking, and track cleanup.
Mandatory Constraints
- Style is Law: Violations of
conductor/code_styleguides/*.mdare HIGH severity. - Iterative Review Confirmation: You MUST use
ask_userbefore starting a large (> 300 lines) review. - Automated Verification: ALWAYS attempt to run existing tests to verify correctness.
- Plan Integrity: If fixes are applied, the
plan.mdMUST be updated to record the review-related tasks and commits. - Tool Call Validation: Validate every tool call. Halt on failure.
Related Skills
airclear/vela-inbox
tools
VerifiedTrustedCommunity
天帆 (Vela) 需求入库 - 将需求录入 product/01_inbox/，自动分配编号、创建目录结构、更新索引。 触发场景：用户说"入库"、"新增需求"、"记录需求"、"需求入库"、"把这个需求录进去"、"登记需求"、"需求登记"， 或者用户附带了一个需求文件并说"入库"/"录入"/"记录"。 即使用户只说"入库"或"把刚才说的需求录进去"也应触发此 Skill。 注意：用户可能在多轮对话中先描述需求，最后才说"入库"，需要回溯对话提取需求内容。
2SKILL.mdUpdated May 26, 2026
airclear/vela-project-init
data-ai
VerifiedTrustedCommunity
天帆 (Vela) AI 原生产研平台 - 项目初始化。当用户想要初始化新项目、创建项目目录结构、搭建 AI-Native SDLC 项目骨架时使用。 关键词触发：初始化项目、新建项目、vela init、项目骨架、创建项目结构、project init、scaffold project、AI 原生项目。 即使用户只说"帮我建个新项目"或"按 vela 结构初始化"也应触发此 Skill。
2SKILL.mdUpdated Apr 15, 2026
airclear/drawio-skill
tools
VerifiedTrustedCommunity
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .drawio XML files and exports to PNG/SVG/PDF locally using the native draw.io desktop CLI. Supports modern "Premium Architecture" styles with card-based designs and layered layouts.
2SKILL.mdUpdated Apr 15, 2026
airclear/drawio-skill-nothing-design
testing
VerifiedTrustedCommunity
This skill should be used when the user explicitly says "Nothing style", "Nothing design", "/nothing-design", or directly asks to use/apply the Nothing design system. NEVER trigger automatically for generic UI or design tasks. It provides guidance and templates for generating diagrams using the minimalist, industrial aesthetic of the Nothing design language.
2SKILL.mdUpdated Apr 15, 2026