review

Dual review with Claude and Codex for quality verification. Use for step or task review.

1,995 stars

Best use case

review is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Dual review with Claude and Codex for quality verification. Use for step or task review.

Teams using review should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/review/SKILL.md --create-dirs "https://raw.githubusercontent.com/bfly123/claude_code_bridge/main/claude_skills/review/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/review/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How review Compares

Feature / AgentreviewStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Dual review with Claude and Codex for quality verification. Use for step or task review.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

Unified review skill for step-level and task-level review.

For full instructions, see `references/flow.md`

Related Skills

ping

1995
from bfly123/claude_code_bridge

Test connectivity with AI provider (gemini/codex/opencode/droid/claude).

tr

1995
from bfly123/claude_code_bridge

Execute current step in AutoFlow workflow. Use when running /tr or continuing task execution.

tp

1995
from bfly123/claude_code_bridge

Create a task plan with collaborative design. Use when starting a new task or running /tp.

pend

1995
from bfly123/claude_code_bridge

View latest reply from AI provider (gemini/codex/opencode/droid/claude).

mounted

1995
from bfly123/claude_code_bridge

Report which CCB providers are mounted (session exists AND daemon is online). Outputs JSON.

file-op

1995
from bfly123/claude_code_bridge

Delegate file I/O to Codex via FileOpsREQ protocol. Use when Claude needs Codex to modify files.

cping

1995
from bfly123/claude_code_bridge

Test connectivity with AI provider (gemini/codex/opencode/droid/claude).

continue

1995
from bfly123/claude_code_bridge

Attach the newest context-transfer Markdown from the current project's ./.ccb/history/ into Claude using @file. Use when the user types /continue or asks to resume with the latest transfer file in this project.

autonew

1995
from bfly123/claude_code_bridge

Send /new to a provider's pane to start a new session without context injection.

ask

1995
from bfly123/claude_code_bridge

Async via ask, end turn immediately; use when user explicitly delegates to any AI provider (gemini/codex/opencode/droid); NOT for questions about the providers themselves.

all-plan

1995
from bfly123/claude_code_bridge

Collaborative planning using abstract roles (designer + inspiration + reviewer).

comprehensive-review-full-review

31392
from sickn33/antigravity-awesome-skills

Use when working with comprehensive review full review