发现 Skills

Bug investigation and resolution workflow. Use when the user mentions: - "fix", "broken", "not working", "bug", "error", "issue", "failing" - debugging, troubleshooting, investigating problems - something that used to work but doesn't anymore - errors in console, build failures, test failures

Onboarding wizard that collects project details and fills all CUSTOMIZE markers across CLAUDE.md and rule files automatically.

Match BIM quantities to CWICR work items. Map element categories to cost codes, validate quantities, and generate cost-linked QTOs.

Build multi-agent AI systems for construction estimation. Use CrewAI/LangGraph to orchestrate specialized agents: QTO agent, pricing agent, validation agent. Automate complex estimation workflows.

This skill should be used when the user asks to "review a semantic model", "audit a semantic model", "check model quality", "optimize my model", "validate model design", "run a best practice check", "check AI readiness", "prepare model for Copilot", or mentions reviewing, auditing, or validating a Power BI semantic model against quality, performance, or best practice standards.

Monitor Proxmox infrastructure health and performance. Track node statistics, analyze resource utilization, and identify optimization opportunities across your cluster.

Manage device adoption and onboarding, maintain device inventory, and monitor device configurations across your UniFi Protect infrastructure.

Convert CSV/Excel/JSON data into a polished visual report page

Use this skill when the user asks to create an API route, add an endpoint, build a REST API, handle POST requests, create route handlers, stream responses, or needs guidance on Next.js API development in the App Router.

This skill should be used when the user asks about "Server Actions", "form handling in Next.js", "mutations", "useFormState", "useFormStatus", "revalidatePath", "revalidateTag", or needs guidance on data mutations and form submissions in Next.js App Router.

Query Polymarket: markets, prices, orderbooks, history.

Coordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.

Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.

Query the code graph database to understand component relationships, dependencies, and change impact. Use when the user asks to "find callers", "check dependencies", "what uses this", "show relationships", "find serializers", or when reading code and needing to understand what depends on a component before modifications.

Provides Home Assistant dashboard layout patterns using vertical-stack (top-to-bottom), horizontal-stack (side-by-side), grid (responsive multi-column), panel (full-screen), and nested layouts for complex designs. Use when asked to "arrange cards side by side", "create 3 column grid", "stack cards vertically", "full-screen panel view", or "responsive layout".

Manages complete feature implementation lifecycle through 10 stages: planning, TDD, naming, DRY, implementation, refactor, integration testing, E2E testing, real usage validation, and production monitoring. Use when implementing new features, significant changes, or onboarding to project workflow. Ensures Clean Architecture, fail-fast principles, ServiceResult pattern, and quality gates. Triggers on "implement feature X", "add functionality Y", "complete workflow for Z", "end-to-end implementation", or "production-ready feature".

Used before completing a task, delivering a major feature, or merging to verify the work meets requirements; or used when receiving code review feedback to address it with technical rigor rather than performative agreement.

Conduct Failure Mode and Effects Analysis (FMEA) for systematic identification and risk assessment of potential failures in designs, processes, or systems. Supports DFMEA (Design), PFMEA (Process), and FMEA-MSR (Monitoring & System Response). Uses AIAG-VDA 7-step methodology with Action Priority (AP) risk assessment replacing traditional RPN. Use when analyzing product designs for potential failures, evaluating manufacturing process risks, conducting proactive risk assessment, preparing for APQP/PPAP submissions, investigating field failures, or when user mentions "FMEA", "failure mode", "DFMEA", "PFMEA", "severity occurrence detection", "RPN", "Action Priority", "design risk analysis", or needs to identify and prioritize potential failure modes with their causes and effects.

Manage timed data refresh intervals for all dashboard panels. Handles pause-when-hidden, stale-data flush on visibility restore, and staggered refresh to avoid API bursts.

Generate properly-formatted SKILL.md files from extracted architectural patterns. Turns raw pattern descriptions into reusable skills that Scion can discover, select, and evolve.

Security review baseline — OWASP risks, authorization, input validation, SSRF/XSS/CSRF, secrets, secure logging/errors, and least privilege.

Trend Research — trend types, monitoring tools, brand fit, reaction speed, brand adaptation

Kubernetes manifests conventions — repository structure, Helm vs Kustomize, per-environment overlays, naming and labels, secrets/config, policy, validation, GitOps.

Use when bootstrapping or changing Python development tooling — uv dependency management, adding or removing dependencies, ruff formatting/linting, ty type checking, pytest configuration in `pyproject.toml`, pre-commit hooks, optional Makefile wrappers, or CI quality jobs.