โณ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

code-review

mfielding92@mfielding92โญ 22 starsยท last commit 3mo agoยท 0 open issues

Review code changes for quality, security, and correctness. Use when the user says "review this PR", "review these changes", "check my code", "look at what I changed", or after implementing a feature. Produces a severity-organized report.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

โ€”/10

// RATINGS

โญGitHub Stars
โญโญ 22 on GitHubGitHub โ†—

Growing

๐ŸŸขProSkills Score
โ€”
๐Ÿ“

Not yet listed on ClawHub or SkillsMP

// README

๐Ÿฆ€ ClawedBack ๐Ÿฆ€

Your Personal AI Assistant โ€” Runs in Claude Code

Runs in Claude Code Port of OpenClaw License: AGPL v3

Skills Tool Compat ClawHub Security Scan Install Modes

A clean-room port of OpenClaw that runs inside Claude Code 17 skills ยท 5 agents ยท 3 install modes ยท ClawHub compatible

Multi-channel AI assistant with web chat, file sharing, voice messages, scheduled tasks, webhook ingestion, approval workflows, and a skill marketplace โ€” all running inside Claude Code. Clone, setup, chat. ๐Ÿฆ€


๐Ÿฆ€ What Is This?

ClawedBack is a clean-room reimplementation of the OpenClaw personal AI assistant platform, rebuilt from the ground up to run inside Claude Code.

Important: ClawedBack is a port, not a fork. It resembles OpenClaw in spirit and functionality โ€” a multi-channel, self-hosted AI assistant with tool execution, automation, and approval workflows โ€” but is an entirely separate codebase with a different architecture. No OpenClaw code was used. ๐Ÿฆ€

Where OpenClaw is a TypeScript monolith with a WebSocket gateway, ClawedBack flips the script: Claude Code IS the agent runtime. It's Claude Code skills.

๐Ÿฆ€ Setup

Use of this project is subject to Anthropic's Terms of Service.

Prerequisites

  • Python 3.11+
  • tmux (sudo apt install tmux)

Step 1: Install Claude Code

curl -fsSL https://claude.ai/install.sh | bash

Step 2: Clone and enter the project

git clone https://github.com/reedmayhew18/ClawedBack.git
cd ClawedBack

Step 3: Start in tmux

tmux new -s clawedback

Step 4: Choose your install mode and launch Claude

Best for trying it out, development, or personal use. Safest option.

claude
# then: /oc-setup โ†’ choose Mode A
  • Python venv inside the project folder
  • Runs as your normal user
  • Claude asks permission before risky operations (add --dangerously-skip-permissions to allow autonomous functionality)

Best for a dedicated server or VM where the assistant needs elevated access.

sudo -E "$(command -v claude || echo ~/.local/bin/claude)"
# then: /oc-setup โ†’ choose Mode B
  • Python venv inside the project folder (same as A)
  • Runs as root for full system access
  • Commands for the regular user: sudo -u <username> <command>
  • Still asks permission before destructive operations (add --dangerously-skip-permissions for autonomous mode โ€” run the IS_SANDBOX=1 lines from Mode C first if using this flag)

Best for sandboxes, VMs, or containers designated for ClawedBack. Not for machines with important data. ๐Ÿฆ€

# Set sandbox flag (both user and root)
echo 'export IS_SANDBOX=1' >> ~/.bashrc && source ~/.bashrc
sudo bash -c 'echo "export IS_SANDBOX=1" >> /root/.bashrc'

# Start Claude as root with no permission prompts
sudo -E "$(command -v claude || echo ~/.local/bin/claude)" --dangerously-skip-permissions
# then: /oc-setup โ†’ choose Mode C
  • System Python directly (--break-system-packages), no venv
  • Root with --dangerously-skip-permissions โ€” Claude can do anything without asking
  • Maximum capability, zero guardrails

WARNING: Only use Mode C on a system that is fully backed up, sandboxed, or designated for this purpose. Claude will have unrestricted root access with no confirmation prompts.

Step 5: Run the setup wizard

/oc-setup

The wizard handles everything: installs dependencies, starts the server, generates your auth token, offers voice (Whisper) setup, and begins polling. Open the URL it gives you, paste the token, and start chatting. ๐Ÿฆ€

To detach tmux (keeps ClawedBack running): Ctrl+B, then D To reattach later: tmux attach -t clawedback

If the tmux session died (reboot, crash, etc.), start a new one and resume:

tmux new -s clawedback
cd /path/to/ClawedBack
claude    # (or sudo -E ... for root modes)

Then run:

/start

This ensures the server is up, creates the polling cron job, and runs one poll cycle. Run /start whenever you restart Claude Code. ๐Ÿฆ€

If the config file is missing (deleted or corrupted), use /oc-resume instead โ€” it auto-detects and rebuilds the config.

To pull the latest updates from GitHub:

/oc-update

This fetches upstream changes, shows what's new, and applies them โ€” preserving your data/, auth token, config, and any custom skills you've installed. If server files changed, it automatically restarts the server. ๐Ÿฆ€


๐Ÿฆ€ Features

โœ… Implemented

  • ๐ŸŒ Web chat interface โ€” dark theme, mobile-responsive, full markdown rendering
  • ๐Ÿ“Ž File uploads โ€” drag-and-drop, analyze any file type
  • ๐Ÿ“ Organized file system โ€” date-based storage with temporary share links
  • ๐ŸŽค Voice messages โ€” recorded in-browser, transcribed with Whisper (CPU or GPU)
  • ๐Ÿ” Token auth โ€” auto-generated or custom, single-user security
  • ๐Ÿ—„๏ธ Message queue โ€” SQLite with WAL mode, CLI interface for skills
  • ๐Ÿ“ก SSE streaming โ€” fetch-based with auth header, cross-device sync
  • โœ… Read receipts โ€” green checkmark when Claude reads your message
  • ๐Ÿ”’ SSL/HTTPS โ€” --ssl flag, custom cert paths, or free Let's Encrypt via /oc-ssl
  • ๐Ÿค– 17 custom skills โ€” routing, sessions, approvals, automation, webhooks, file sharing, updates
  • โฐ Scheduled tasks โ€” reminders, recurring jobs, cron expressions
  • ๐Ÿ”— Webhook ingestion โ€” receive events from GitHub, CI, custom services
  • โœ‹ Approval gates โ€” single gates and multi-step workflow chains with crash recovery
  • ๐Ÿงฉ Skill marketplace โ€” browse ClawHub, import with security scanning
  • ๐Ÿ” Security scanning โ€” mandatory audit of imported skills (subagent-isolated, 5-category scan)
  • ๐Ÿ“บ Channel registry โ€” extensible adapter system for future platforms
  • ๐Ÿ”„ Self-updating โ€” /oc-update pulls latest while preserving config/data
  • ๐Ÿฉบ Self-healing resume โ€” /oc-resume auto-detects setup if config is missing
  • ๐Ÿ–ฅ๏ธ Three install modes โ€” user, root, or full root with no guardrails

๐Ÿ”ฎ Planned

  • ๐Ÿฆ€ Browser automation (Playwright)
  • ๐Ÿฆ€ Device nodes (remote command execution)
  • ๐Ÿฆ€ TTS voice responses

๐Ÿฆ€ Tool Compatibility (19/23 Matched)

OpenClaw has 23 built-in tools. Claude Code matches 19 of them out of the box โ€” and the 4 missing are all API wrappers that can be built as skills. Full mapping in [.claude/skills/oc-hub/references/tool-mapping.md](.claude/s

// HOW IT'S BUILT

// FILES

2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

  • .claude/skills/code-review/SKILL.md3.0 KBupstream โ†—
    ---
    name: code-review
    description: Review code changes for quality, security, and correctness. Use when the user says "review this PR", "review these changes", "check my code", "look at what I changed", or after implementing a feature. Produces a severity-organized report.
    argument-hint: "[file path, branch, or PR number]"
    context: fork
    agent: Explore
    allowed-tools: Read, Grep, Glob, Bash(git *)
    ---
    
    # Code Review
    
    Produce a severity-organized review report covering security, correctness, and quality for code changes.
    
    ## Goal
    Identify issues in code changes, organized by severity (Critical > Warnings > Suggestions), with specific file:line references and fix suggestions for every finding. Done when the report is presented to the user.
    
    ## Context
    Before reviewing, read CLAUDE.md and any linter/formatter config files (.eslintrc, pyproject.toml, .prettierrc, etc.) to understand project conventions. Do not flag style issues already handled by configured tooling.
    
    ## Process
    
    ### Step 1: Identify Changes
    - If `$ARGUMENTS` specifies a file, branch, or PR: use that scope
    - If `$ARGUMENTS` is empty: run `git diff main...HEAD`. If that returns nothing, ask: "What should I review โ€” a branch, specific files, or uncommitted changes?"
    - Identify all modified files and understand the scope
    
    **CHECKPOINT:** Present the identified files and diff scope. Confirm this is the correct review target before proceeding.
    
    ### Step 2: Understand Context
    - Read the modified files fully (not just the diff)
    - Understand what the code is supposed to do
    - Check for related test files
    
    ### Step 3: Review Checklist
    
    **Critical (must fix before merge):**
    - Security vulnerabilities (injection, XSS, exposed secrets, missing auth checks)
    - Data loss risks (destructive operations without confirmation, missing transactions)
    - Race conditions or concurrency issues
    - Breaking changes to public APIs without migration path
    
    **Warnings (should fix):**
    - Missing error handling for external calls (network, file I/O, DB)
    - Missing input validation at system boundaries
    - Duplicated logic that should be shared
    - Performance issues (N+1 queries, unnecessary allocations in loops)
    - Missing or inadequate test coverage for new behavior
    
    **Suggestions (nice to have):**
    - Naming improvements for clarity
    - Simplification opportunities
    - Better patterns available in the framework
    
    ### Step 4: Report
    For each finding:
    1. **File and line reference**: `path/to/file.ts:42`
    2. **What's wrong**: One sentence
    3. **Why it matters**: Impact if not fixed
    4. **How to fix**: Specific suggestion with code example
    
    Organize findings by severity: Critical first, then Warnings, then Suggestions.
    
    ## Output
    Report is presented inline in the conversation, organized by severity. Offer to save to `.claude/memory/review-YYYY-MM-DD.md` if the user wants a record.
    
    ## What NOT to Flag
    - Style issues handled by linters/formatters
    - Opinions about code organization without concrete benefit
    - "I would have done it differently" without a clear improvement
    - Missing documentation on self-explanatory code
    
  • README.mdupstream โ†—

    Contents are not inlined in the catalog. Open the upstream file.

Plain-text copy, no login: /skill-bundles/mfielding92-clawedback-claude-skills-code-review.md

// REPO STATS

22 stars
0 open issues
Last commit: 3mo ago