ワンクリックでManusで任意のスキルを実行

$pwd:

code-review

Name: Code Review
Author: redai-infra

// Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, Python anti-patterns, and ML/distributed training issues. Tailored for the Relax reinforcement learning framework.

Manusで実行

$ git log --oneline --stat

stars:402

forks:40

updated:2026年4月14日 11:46

ファイルエクスプローラー

6 ファイル

SKILL.md

readonly

name	code-review
description	Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, Python anti-patterns, and ML/distributed training issues. Tailored for the Relax reinforcement learning framework.

Code Review Expert

Perform a structured review of the current git changes with focus on SOLID principles, architecture, removal candidates, security risks, and Python-specific issues. Tailored for the Relax project (PyTorch distributed training, Ray actors, ML pipeline code).

Default to review-only output unless the user asks to implement changes.

For project structure, coupling points, and key files, see AGENTS.md.

Severity Levels

Level	Name	Description	Action
P0	Critical	Security vulnerability, data loss risk, correctness bug, training corruption	Must block merge
P1	High	Logic error, significant SOLID violation, performance regression, gradient issues	Should fix before merge
P2	Medium	Code smell, maintainability concern, minor SOLID violation, missing type hints	Fix in this PR or create follow-up
P3	Low	Style, naming, documentation, minor suggestion	Optional improvement

Workflow

1) Preflight Context

Use git status -sb, git diff --stat, and git diff to scope changes.
If needed, use rg or grep to find related modules, usages, and contracts.
Identify entry points, ownership boundaries, and critical paths (training loop, loss computation, checkpoint saving).

Edge cases:

No changes: Ask if they want to review staged changes or a specific commit range.
Large diff (>500 lines): Summarize by file first, then review in batches.
Cross-package changes: When multiple relax/ subpackages are modified, verify import compatibility first.

2) SOLID + Architecture Smells

Load references/solid-checklist.md for specific prompts.
When you propose a refactor, explain why it improves cohesion/coupling and outline a minimal, safe split.
If refactor is non-trivial, propose an incremental plan instead of a large rewrite.

3) Removal Candidates + Iteration Plan

Load references/removal-plan.md for template.
Identify code that is unused, redundant, or feature-flagged off.
Distinguish safe delete now vs defer with plan.

4) Security and Reliability Scan

Load references/security-checklist.md for coverage.
Check for: command injection, path traversal, pickle deserialization, secret leakage, race conditions, distributed race conditions.
Call out both exploitability and impact.

5) Python-Specific Quality Scan

Load references/code-quality-checklist.md for coverage.
Check for: missing type hints, exception handling issues, resource management, mutable defaults, import problems.

6) ML/Training-Specific Scan

Load references/python-ml-checklist.md for coverage.
Check for: shape/dtype/device mismatches, gradient issues, memory leaks, distributed training bugs, numerical stability.

7) Output Format

## Code Review Summary

**Files reviewed**: X files, Y lines changed
**Overall assessment**: [APPROVE / REQUEST_CHANGES / COMMENT]

---

## Findings

### P0 - Critical
(none or list)

### P1 - High
1. **[file:line]** Brief title
   - Description of issue
   - Suggested fix

### P2 - Medium
...

### P3 - Low
...

---

## Removal/Iteration Plan
(if applicable)

Clean review: If no issues found, state what was checked and any residual risks.

8) Next Steps Confirmation

After presenting findings, ask user how to proceed:

Fix all - Implement all suggested fixes
Fix P0/P1 only - Address critical and high priority issues
Fix specific items - User specifies which issues to fix
No changes - Review complete

Important: Do NOT implement any changes until user explicitly confirms.

Resources

File	Purpose
`solid-checklist.md`	SOLID smell prompts and refactor heuristics for Python
`security-checklist.md`	Python security and runtime risk checklist
`code-quality-checklist.md`	Python-specific error handling, performance, boundary conditions
`removal-plan.md`	Template for deletion candidates and follow-up plan
`python-ml-checklist.md`	PyTorch/ML-specific issues for distributed training

related-skills.json

同じリポジトリ

perf-doctor.md

from "redai-infra/Relax"

Diagnose Relax training launch scripts for misconfigured flags that hurt performance (time/MFU) or waste GPU memory (cards needed). Use when user asks to review/audit/check a training script, mentions "perf doctor", suspects a config is slow or OOM-prone, or wants a sanity check before launching. Produces a two-section markdown report (Performance + Memory) with cited flags, severity, and concrete fixes.

2026-05-29402

relax-dev-debug.md

from "redai-infra/Relax"

Develop and debug the Relax reinforcement learning project. Use this skill whenever modifying code in the relax/ directory, or running remote training jobs on a Ray cluster for validation. Also use it when the user mentions training, debugging training runs, submitting Ray jobs, or fixing training errors.

2026-05-14402

ssh-ray-cluster.md

from "redai-infra/Relax"

Connect to a remote Ray cluster head node via SSH (paramiko) to execute commands, check cluster status, inspect logs, and debug training jobs. Use this skill when the user asks to SSH into a remote machine, check Ray cluster status, or run remote commands on the Ray head node.

2026-05-14402

creating-skills.md

from "redai-infra/Relax"

Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context injection and subagent execution.

2026-04-14402

debug-hang.md

from "redai-infra/Relax"

自动排查 Ray 调度的分布式训练任务 hang 问题。使用当训练任务无响应、资源利用率异常、任务长时间无进度时。自动收集集群状态、任务调用栈、Actor 状态，分析阻塞链条并定位根因。

2026-04-14402

doc-writer.md

from "redai-infra/Relax"

Write and maintain bilingual (English + Chinese) documentation for the Relax project. Use when user asks to create, update, or translate documentation pages. Ensures format correctness (VitePress, sidebar config, bilingual parity) and content correctness (matches actual codebase, no fabricated features).

2026-04-14402

package.json

"author": "redai-infra"

"repository": "redai-infra/Relax"

GitHub リポジトリを開く Creator のリポジトリを見る

$ install --global

$ download --local

Manusで実行

$ useful --forSOC

ソフトウェア品質保証アナリスト・テスターコンピュータ・数学職15-1253L4

name	code-review
description	Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, Python anti-patterns, and ML/distributed training issues. Tailored for the Relax reinforcement learning framework.

Code Review Expert

Default to review-only output unless the user asks to implement changes.

For project structure, coupling points, and key files, see AGENTS.md.

Severity Levels

Level	Name	Description	Action
P0	Critical	Security vulnerability, data loss risk, correctness bug, training corruption	Must block merge
P1	High	Logic error, significant SOLID violation, performance regression, gradient issues	Should fix before merge
P2	Medium	Code smell, maintainability concern, minor SOLID violation, missing type hints	Fix in this PR or create follow-up
P3	Low	Style, naming, documentation, minor suggestion	Optional improvement

Workflow

1) Preflight Context

Use git status -sb, git diff --stat, and git diff to scope changes.
If needed, use rg or grep to find related modules, usages, and contracts.
Identify entry points, ownership boundaries, and critical paths (training loop, loss computation, checkpoint saving).

Edge cases:

No changes: Ask if they want to review staged changes or a specific commit range.
Large diff (>500 lines): Summarize by file first, then review in batches.
Cross-package changes: When multiple relax/ subpackages are modified, verify import compatibility first.

2) SOLID + Architecture Smells

Load references/solid-checklist.md for specific prompts.
When you propose a refactor, explain why it improves cohesion/coupling and outline a minimal, safe split.
If refactor is non-trivial, propose an incremental plan instead of a large rewrite.

3) Removal Candidates + Iteration Plan

Load references/removal-plan.md for template.
Identify code that is unused, redundant, or feature-flagged off.
Distinguish safe delete now vs defer with plan.

4) Security and Reliability Scan

Load references/security-checklist.md for coverage.
Check for: command injection, path traversal, pickle deserialization, secret leakage, race conditions, distributed race conditions.
Call out both exploitability and impact.

5) Python-Specific Quality Scan

Load references/code-quality-checklist.md for coverage.
Check for: missing type hints, exception handling issues, resource management, mutable defaults, import problems.

6) ML/Training-Specific Scan

Load references/python-ml-checklist.md for coverage.
Check for: shape/dtype/device mismatches, gradient issues, memory leaks, distributed training bugs, numerical stability.

7) Output Format

## Code Review Summary

**Files reviewed**: X files, Y lines changed
**Overall assessment**: [APPROVE / REQUEST_CHANGES / COMMENT]

---

## Findings

### P0 - Critical
(none or list)

### P1 - High
1. **[file:line]** Brief title
   - Description of issue
   - Suggested fix

### P2 - Medium
...

### P3 - Low
...

---

## Removal/Iteration Plan
(if applicable)

Clean review: If no issues found, state what was checked and any residual risks.

8) Next Steps Confirmation

After presenting findings, ask user how to proceed:

Fix all - Implement all suggested fixes
Fix P0/P1 only - Address critical and high priority issues
Fix specific items - User specifies which issues to fix
No changes - Review complete

Important: Do NOT implement any changes until user explicitly confirms.

Resources

File	Purpose
`solid-checklist.md`	SOLID smell prompts and refactor heuristics for Python
`security-checklist.md`	Python security and runtime risk checklist
`code-quality-checklist.md`	Python-specific error handling, performance, boundary conditions
`removal-plan.md`	Template for deletion candidates and follow-up plan
`python-ml-checklist.md`	PyTorch/ML-specific issues for distributed training

code-review

Code Review Expert

Severity Levels

Workflow

1) Preflight Context

2) SOLID + Architecture Smells

3) Removal Candidates + Iteration Plan

4) Security and Reliability Scan

5) Python-Specific Quality Scan

6) ML/Training-Specific Scan

7) Output Format

8) Next Steps Confirmation

Resources

このリポジトリの他の Skills

このリポジトリの他の Skills

Code Review Expert

Severity Levels

Workflow

1) Preflight Context

2) SOLID + Architecture Smells

3) Removal Candidates + Iteration Plan

4) Security and Reliability Scan

5) Python-Specific Quality Scan

6) ML/Training-Specific Scan

7) Output Format

8) Next Steps Confirmation

Resources