发现 Skills

Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. Includes architecture diagram generation, system design patterns, tech stack decision frameworks, and dependency analysis. Use when designing system architecture, making technical decisions, creating architecture diagrams, evaluating trade-offs, or defining integration patterns.

Use when you have a written implementation plan to execute in a separate session with review checkpoints. Alternative to subagent-driven development for batch execution.

Progressive Web Apps - service workers, caching strategies, offline support, Workbox

Native macOS/iOS app performance profiling via xctrace/Time Profiler and CLI-only analysis of Instruments traces. Use when asked to profile, attach, record, or analyze Instruments .trace files, find hotspots, or optimize native app performance without opening the Instruments UI.

Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup,

Pull issues, metrics, quality gates, and analysis data from SonarCloud. Use when checking code quality, security vulnerabilities, test coverage, technical debt, or CI/CD quality gates.

Comprehensive guide for Terraform code style, formatting, and best practices based on HashiCorp's official standards and Azure Verified Modules (AVM) requirements. Use when writing or reviewing Terraform configurations, formatting code, organizing files and modules, establishing team conventions, managing version control, ensuring code quality and consistency across infrastructure projects, or developing Azure Verified Modules.

Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, planning, writing, registration, and verification.

Repeatable, low-risk refactoring process for the Leidimen Hugo project: templates, SCSS, JS, and config

Trigger when any QMS document is created/updated/obsoleted and synchronization of the Master Document List (LMD) in `docs/_control/lmd.yml` is required; DO NOT trigger for changes that do not affect documents.

NestJS best practices and architecture patterns for building production-ready applications. This skill should be used when writing, reviewing, or refactoring NestJS code to ensure proper patterns for modules, dependency injection, security, and performance.

Execute inspection and validation of Vertex AI Agent Engine deployments, including Code Execution Sandbox, Memory Bank, A2A protocol compliance, and overall security posture. Generates production readiness scores. Use when asked to "inspect agent engine" or "validate deployment". Trigger with relevant phrases based on the skill's purpose.

Generate comprehensive test suites using Cascade. Activate when users mention "generate tests", "test coverage", "write unit tests", "create test suite", or "tdd assistance". Handles AI-powered test generation. Use when writing or running tests. Trigger with phrases like "windsurf test generation", "windsurf generation", "windsurf".

Graceful degradation protocol for single-agent operation. Defines degraded mode triggers, virtual subagent consensus workflow, ratification path, and integration with signal filter + cron detection. Use when the collective operates with limited agents and cannot achieve quorum.

Ensure all triad nodes work on a single shared codebase from Heretek-AI/openclaw. Use when work is fragmented across multiple repos/workspaces, nodes have divergent git states, or triad needs to enforce unified workspace path + remote + branch discipline.

Audit triad node files for integrity, sync state, and configuration drift. Use when Tabula Myriad needs to verify file consistency across TM-1/TM-2/TM-3, detect configuration divergence, or validate workspace sync state.

Drive self-directed growth through gap detection, anomaly detection, opportunity scanning, capability mapping, and auto-deliberation triggers. Use when Tabula Myriad needs to detect skill gaps, monitor anomalies, scan for opportunities, map capabilities to goals, or auto-create deliberation proposals.

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

Recursive prompt improvement with quality-driven iteration for Claude Code. Use when you need systematic, measurable improvement of LLM outputs through complexity routing, context extraction, and iterative refinement.

This skill should be used when the user asks to "run commands on a remote pane", "check remote pane output", "capture output from remote", "send commands to remote server", "tail logs on prod", "check disk space on staging", "run uptime across servers", "is my SSH connection alive", "read what's on the remote pane", or needs to interact with already-established SSH connections in tmux panes. Also activates when you are about to suggest the user manually SSH into a remote host to run a command, when a command needs to run on a remote machine, when troubleshooting requires executing something on a known remote host, or when you would otherwise tell the user to "run this on the server" or "SSH in and do X". Not for creating new connections (use the /remote command for that).

Refactor AGENTS.md instructions to follow progressive disclosure and AGENTS.md best practices. Use when asked to audit, reorganize, or split AGENTS.md into a minimal root file plus linked docs; includes contradiction checks, essential extraction, grouping, and deletion flags.

Orchestrate multi-step quantum chemistry workflows (geometry → frequency → excited state → benchmarking), manage batch calculations with QC gates at every step, and define standardized data interfaces for cross-agent collaboration with ChemicalExpert.

Generate a to-be customer journey map that describes the projected user experience for a product or feature. Use this skill whenever the user wants to map out user flows, design the intended customer experience, plan how users will navigate a product, or create journey documentation for a new or redesigned feature. Triggers on phrases like "customer journey", "user journey", "journey map", "user flow", "experience map", "how will the user interact with", or any request to design or document the intended path a user takes through a product.

A skill that creates a parallel development plan for multiple developers. It leverages git worktree-based branch strategies, task dependency analysis, critical path calculation, developer role assignment, and timeline creation. Use this skill when asking things like 'Create a parallel development plan', 'I want multiple people to develop simultaneously', 'I want to split work using worktree', or 'I want to maximize parallelization of development'. It can also start on-demand parallel tasks immediately for requests such as 'Fix XX in parallel', 'Do YY with worktree', or 'Add a parallel task'.