DevOps

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Code refactoring patterns and techniques for improving code quality without changing behavior. Use for cleaning up legacy code, reducing complexity, or improving maintainability.

Write internal communications using company formats. Use when writing status reports, leadership updates, company newsletters, FAQs, incident reports, project updates, or any internal communications.

Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Automated code review for pull requests using specialized review patterns. Analyzes code for quality, security, performance, and best practices. Use when reviewing code changes, PRs, or doing code audits.

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

Generates a structured skill template based on provided specifications.

This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.

Invoke IMMEDIATELY via python script to stress-test decisions and reasoning. Do NOT analyze first - the script orchestrates the critique workflow.

生成结构化 git 变更报告（JSON + Markdown）。使用此技能当用户提到"git 变更"、"commit 摘要"、"代码审查"、"release note"、"近期改动"、"每日摘要"，或需要分析指定 commit 区间的代码变更。包含三元组结构（设计意图、核心代码、影响范围）的语义化报告，适用于代码审查、发布说明、团队同步、CI/CD 等场景。

Guide for implementing features in ClaudeBar following architecture-first design, TDD, rich domain models, and Swift 6.2 patterns. Use this skill when: (1) Adding new functionality to the app (2) Creating domain models that follow user's mental model (3) Building SwiftUI views that consume domain models directly (4) User asks "how do I implement X" or "add feature Y" (5) Implementing any feature that spans Domain, Infrastructure, and App layers

Guide for making improvements to existing ClaudeBar functionality using TDD. Use this skill when: (1) Enhancing existing features (not adding new ones) (2) Improving UX, performance, or code quality (3) User asks "improve X", "make Y better", or "enhance Z" (4) Small enhancements that don't require full architecture design For NEW features, use implement-feature skill instead.

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Triggers include "browse", "navigate to", "go to website", "extract data from webpage", "screenshot", "web scraping", "fill out form", "click on", "search for on the web". When taking actions be as specific as possible.

Eliminate component hedging anti-patterns that mask infrastructure failures. Build systems that fail loudly when broken instead of limping along in degraded states. Critical for production reliability and operational visibility.

Advanced LLM prompt engineering expertise for crafting highly effective prompts, system messages, and tool descriptions with Claude-specific techniques

Detect explicit user_id parameters in functions to identify potential opportunities for using ambient context. This is an investigation tool that flags instances for human review, not a prescriptive analyzer.

DO NOT COMMIT unless user explicitly tells you to. Use this skill EVERY SINGLE TIME before creating a git commit. Provides mandatory commit message format, staging rules, and post-commit summary requirements for the MIRA project

Conduct thorough dependency audits to identify redundant code, unused features, and improper usage patterns. Examines each import to ensure we're leveraging existing capabilities rather than reinventing functionality.

Write pytests that test real public interfaces with actual components, no mocking, and precise assertions. MIRA-specific patterns. Use when creating or reviewing tests.

Augmented cognition layer that makes users smarter by connecting conversations to their persistent knowledge tree. Use proactively when topics arise that might have prior knowledge, and when users ask to remember, recall, search, or organize. Triggers on technical discussions, decision-making, project work, "remember this", "recall", "what do I know about", or any knowledge request.