MCP App StoreMCP App Store
from dgk-claude16
Run an automated, background code review using a Z.AI (GLM) model to surface security issues, style problems, and PR diffs for staged or uncommitted changes.
This skill runs a GLM-based code review (default: glm-4.7-flash) on the current session's changes. It can review staged changes, uncommitted diffs, or PR diffs, producing prioritized findings and suggested fixes. The recommended execution calls the glm-review CLI in background mode so reviews run asynchronously and results can be validated and acted on afterward.
Use this skill after making code changes when you want an automated review before committing or merging: for security checks, stylistic suggestions, PR diff reviews, or a focused audit (e.g., "보안 집중"). It is especially useful in multi-agent or CI-assisted workflows where diffs must be collected reliably.
glm-review CLI)--diff-file, --mode pr|staged), and the required background flags (run_in_background=true, dangerouslyDisableSandbox=true).Agents that can call shell/CLI tools (Claude Code, Cursor, Codex-style agents) can use this skill. It is intended for environments that support running glm-review and background execution.
A code review skill that runs Z.AI's GLM models on git diffs to surface security and style issues. The SKILL.md is detailed and well-structured but written entirely in Korean, limiting its audience. It instructs agents to run with dangerouslyDisableSandbox=true, which is a notable security concern. No bundled scripts — relies entirely on the external glm-review CLI. Practical only for users already in the Z.AI ecosystem.
glm-review CLI (requires npm install -g glm-review)The dangerouslyDisableSandbox=true instruction is a meaningful security concern (-28 deduction applied). However, this appears to be a legitimate code review tool rather than malicious — the sandbox bypass is likely needed for git operations. The skill is well-documented with clear error handling, but its niche audience (Korean-speaking Z.AI users) and heavy external dependency limit its broad usefulness.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
TradeOS
Natural-language driven CEX trading and portfolio management for agents: API key vaulting, multi-exchange orders, DCA, arbitrage scanning, alerts and security r
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.