发现 Skills

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions. Part of SuperNavigator App Layer.

Use this when any Mem9-related behavior is needed in Codex, and prefer this skill as the main Mem9 entrypoint. Use it to route to mem9-setup when the environment is missing MEM9_TENANT_ID, to mem9-recall for proactive retrieval, to mem9-store for proactive saving, or to perform direct curl CRUD operations for explicit memory management.

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Production deployment principles and decision-making.

Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.

Reference knowledge for diagnosing MSBuild build performance issues. Only activate in MSBuild/.NET build context. Use when builds are slow, to identify bottlenecks using binary log analysis. Covers timeline analysis, node utilization, expensive targets/tasks, Roslyn analyzer impact, RAR performance, and critical path identification. Works with binlog replay to text logs for data-driven analysis.

Configure OpenTelemetry distributed tracing, metrics, and logging in ASP.NET Core using the .NET OpenTelemetry SDK. Use when adding observability, setting up OTLP exporters, creating custom metrics/spans, or troubleshooting distributed trace correlation.

Make .NET projects compatible with Native AOT and trimming by systematically resolving IL trim/AOT analyzer warnings. USE FOR: making projects AOT-compatible, fixing trimming warnings, resolving IL warnings (IL2026, IL2070, IL2067, IL2072, IL3050), adding DynamicallyAccessedMembers annotations, enabling IsAotCompatible. DO NOT USE FOR: publishing native AOT binaries, optimizing binary size, replacing reflection-heavy libraries with alternatives. INVOKES: no tools — pure knowledge skill.

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (molecular weight (MW), LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with a simpler interface, use datamol (a wrapper around RDKit). Use RDKit for advanced control, custom sanitization, and specialized algorithms.

Apply worktree changes to the main repo for review. Use when done working in a worktree and ready for the user to review and commit. Triggers on apply changes, ready for review, done with changes, or when finishing implementation in a worktree.

Use when a codebase feels hard to change, test, or navigate — surface architectural friction, identify deeper module seams, and walk one candidate into a concrete refactoring direction.

Coordinates complex tasks via task-isolated subagents. Use when one objective is too large for a single agent or when independent work streams should run concurrently with minimal context bleed. One objective per subagent; summarize before returning to keep the main context window clean.

Use when a user reports a frontend bug, visual defect, or unexpected behavior in a Next.js/TypeScript application. Orchestrates a multi-phase QA pipeline — component mapping, diagnosis, fix, and regression testing — by classifying symptoms and dispatching to the appropriate specialist skill. Does not perform diagnosis or fixes directly; delegates all domain work to specialists. Not for backend-only issues, infrastructure problems, or build/deployment failures.

Get daily motivation with personalized encouragement, goal reminders, and momentum tracking

Calendar canvas for displaying events and picking meeting times. Use when showing calendar views or when users need to select available time slots.

RTL (Right-to-Left) CSS for Hebrew and Arabic. Use when building UIs that need RTL support, fixing RTL layout issues, or auditing CSS for RTL compliance.

Test the Ark Dashboard UI with Playwright

CodeIgniter 4 framework knowledge base. Provides CI4 MVC architecture, DDD integration, persistence, services, security (Shield auth, Filters authorization, CSRF), event system, queue (codeigniter4/queue jobs, workers, retry), infrastructure components (cache, HTTP client, email, throttler), testing, and antipatterns for CodeIgniter PHP projects.

Host and process metrics including CPU, memory, disk, network, containers, and process-level telemetry. Use when analyzing infrastructure health, resource utilization, process consumption, or host discovery. Also use when building timeseries queries for host metrics that feed into analytical workflows like anomaly detection, forecasting, or seasonality analysis. Trigger: "show hosts", "CPU usage", "memory utilization", "disk space", "high CPU", "host with most free disk", "top hosts by CPU", "top processes by memory", "Linux hosts in AWS", "what databases are running", "infrastructure costs by cost center", "hosts running EOL Java", "container monitoring", "listening ports", "process resource consumption", "CPU forecast", "memory anomaly", "host seasonality". Do NOT use for explaining existing queries, product documentation questions, Kubernetes pod/workload queries (use dt-obs-kubernetes), AWS cloud resource inventory (use dt-obs-aws), or service-level metrics (use dt-obs-services).

Use when creating or updating CLAUDE.md files for projects or subdirectories - covers top-level vs domain-level organization, capturing architectural intent and contracts, and mandatory freshness dates

Use when an approved spec / requirements doc exists and needs to become a bite-sized, TDD-structured implementation plan — prose markdown at `docs/plans/YYYY-MM-DD-<feature>.md` plus a YAML sidecar when the plan has ≥3 tasks, a human gate, or a loop. Trigger phrases: "write the implementation plan for this spec", "turn this design into tasks", "break this feature into TDD steps", "plan out how to build X from the spec", "I have a spec — what's the plan", "create the plan document", "scaffold tasks for this design", "give me a bite-sized plan", "convert the approved design into a plan", "plan the implementation of <feature>". Runs the plan-document reviewer loop and hands off to subagent-driven-development or executing-plans. Do NOT use when there is no approved spec yet (use brainstorming first), when executing an existing plan (use subagent-driven-development or executing-plans), or for single-edit bugfixes that don't need a multi-step plan.

Guide for implementing Tailwind CSS - a utility-first CSS framework for rapid UI development. Use when styling applications with responsive design, dark mode, custom themes, or building design systems with Tailwind's utility classes.

Formats citations and bibliographies in APA 7th, MLA 9th, Chicago, Harvard, and IEEE styles

Reviews code architecture for hexagonal patterns, checks dependency directions, and suggests improvements for ports and adapters separation. Activates when users work with services, repositories, or architectural patterns.