⚙️ DevOps & CI/CD

Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server crashes, token leaks, code rewrites. Works with Claude Code, Clawdbot, Cursor. Install once, enforce forever.

Prevent Terraform/OpenTofu hallucinations by diagnosing and fixing failure modes: identity churn, secret exposure, blast-radius mistakes, CI drift, and compliance gate gaps. Use when generating, reviewing, refactoring, or migrating IaC and when building delivery/testing pipelines.

Safe OpenClaw upgrades with snapshot, pre-flight checks, controlled upgrade steps, post-verification, and emergency rollback. Never lose your working system to a bad update again.

DeFi protocol monitoring with alerts for TVL drops, capital rotation, hacks, bridge surges, unlocks, and revenue. Runs checks on demand or scheduled.

Prevent OpenClaw config changes from crashing the gateway. Auto-backup, schema validation, critical field checks, and auto-rollback. Use before any config.apply, config.patch, or openclaw.json edit.

Autonomous quality engineering swarm that forges production-ready code through continuous behavioral verification, exhaustive E2E testing, and self-healing fix loops. Combines DDD+ADR+TDD methodology with BDD/Gherkin specifications, 7 quality gates, defect prediction, chaos testing, and cross-context dependency awareness. Architecture-agnostic - works with monoliths, microservices, modular monoliths, and any bounded-context topology.

Opinionated guide for building dApps on Arbitrum using Stylus (Rust) and/or Solidity. Covers local devnode setup, contract development, testing, deployment, and React frontend integration with viem. Use when starting a new Arbitrum project, writing Stylus or Solidity contracts, deploying to Arbitrum, or building a frontend that interacts with Arbitrum contracts.

Add or update asynchronous Telegram bot accounts in OpenClaw. Use when user asks to add multiple Telegram bots, run bots in parallel, or asks OpenClaw to guide BotFather-based provisioning. Enforces username pattern Nebutra[three digits]_bot and philosopher-style English bot names.

Comprehensive application log investigation workflow that reads logs end-to-end, correlates signals with code paths and runtime context, and identifies evidence-backed issues with impact and remediation steps. Use when users ask to analyze logs, investigate incidents, find root causes from log records, explain recurring warnings/errors, or check whether logs reveal hidden system problems.

Guide the agent to submit code changes or prepare a release. Use when the user asks to commit, submit, push, tag, or release changes, or says 提交/送出/提交變更. Default to a commit+push only workflow when the user does not explicitly request versioning. Use release workflow only when the user asks for version/tag/release work.

Container-based development for isolated, reproducible environments. Use when running npm commands, installing packages, executing code, or managing project dependencies. Trigger phrases include "npm install", "run the build", "start the server", "install package", or any code execution request.

Build production-ready MCP servers using FastMCP framework with proven patterns for tools, resources, prompts, OAuth authentication, and comprehensive testing. Use this when creating FastMCP-based MCP servers with features like Google OAuth, multiple resource types, testing with FastMCP Client, or complex tool implementations.

Complete Neon Serverless Postgres documentation. Covers serverless setup, branching, autoscaling, integrations (Vercel, Drizzle, Prisma), connection pooling, extensions, and best practices.

A powerful RSS subscription manager and reader. Use it to (1) Import/export OPML files, (2) Manage RSS feeds (add, remove, categorize), (3) Validate feed connectivity, (4) Schedule periodic updates via cron, (5) Fetch and summarize articles with a progressive disclosure approach.

Use when setting up or configuring code quality tools (formatters, linters, type checkers, dependency scanners) for a repository. Also use when adding visual accessibility automation or security baseline scanning. Do not use for general coding or when tools are already configured.

Output sanitization for agent responses - prevents accidental secret leaks

Generate and repair VS Code-compatible tldraw `.tldr` files from diagram JSON. Use when asked to build or update architecture diagrams from JSON, fix blank tldraw canvas issues in VS Code, or enforce current tldraw schema compatibility.

Use when preparing a release, publishing a package, bumping a version, or configuring public repository metadata. Also use when verifying a published package. Do not use for general development or non-release tasks.

Orchestrates agent workflow for non-trivial tasks: plan-first mode, subagent use, self-improvement loops, verification before done, and autonomous bug fixing. Use for any task with 3+ steps, architectural decisions, bug reports, or when the user corrects the agent. Ensures plans go in tasks/todo.md, lessons in tasks/lessons.md, and changes stay minimal and provably correct.

Use when user wants to check GitHub trending projects, compare daily/weekly/monthly ranking changes, or generate trending reports. Triggers include "GitHub trending", "hot projects", "trending report", "trending changes", "热门项目", "趋势报告".