Spec a new feature — recall architecture knowledge, create a spec document, build an implementation plan, and break into tasks.

Spec a new feature — recall architecture knowledge, create a spec document, build an implementation plan, and break into tasks.

Recall relevant memories from Hindsight before starting a task. Injects past learnings, decisions, and context into the current session.

Recall relevant memories from Hindsight before starting a task. Injects past learnings, decisions, and context into the current session.

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.

Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

Use when designing domain error handling. Keywords: domain error, error categorization, recovery strategy, retry, fallback, domain error hierarchy, user-facing vs internal errors, error code design, circuit breaker, graceful degradation, resilience, error context, backoff, retry with backoff, error recovery, transient vs permanent error, 领域错误, 错误分类, 恢复策略, 重试, 熔断器, 优雅降级

Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for potential trades.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.

Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.

**WORKFLOW SKILL** - Orchestrates Aspire applications using the Aspire CLI and MCP tools for running, debugging, and managing distributed apps. USE FOR: aspire run, aspire stop, start aspire app, check aspire resources, list aspire integrations, debug aspire issues, view aspire logs, add aspire resource, aspire dashboard, update aspire apphost. DO NOT USE FOR: non-Aspire .NET apps (use dotnet CLI), container-only deployments (use docker/podman), Azure deployment after local testing (use azure-deploy skill). INVOKES: Aspire MCP tools (list_resources, list_integrations, list_structured_logs, get_doc, search_docs), bash for CLI commands. FOR SINGLE OPERATIONS: Use Aspire MCP tools directly for quick resource status or doc lookups.

This skill should be used when the user says "style explore", "arn style", "visual style", "explore styles", "UI style", "look and feel", "design direction", "pick a style", "choose colors", "theme the app", "visual direction", "style guide", or wants to explore and define the visual design direction for their project through guided conversation, producing a style brief document with implementable toolkit configuration.

This skill should be used when the user says "scaffold", "arn scaffold", "set up the project", "create project", "initialize project", "bootstrap project", "create the skeleton", "install dependencies", "configure the project", or wants to create a working project skeleton from architecture decisions with installed dependencies, configured build tools, and a UI toolkit ready for development.

This skill should be used when the user says "dev setup", "arn spark dev setup", "development environment", "configure dev environment", "dev container", "configure CI", "set up CI", "onboard developer", "developer setup", "set up docker", "configure development", "how do I set up this project", "development setup", "onboard me", "get this project running", "set up my machine", "new developer setup", "how do I get started", "developer onboarding", or wants to define a standardized development environment for their project (producing dev environment infrastructure files and a dev-setup document) or follow an existing environment standard to get onboarded as a new developer.

This skill should be used when the user says "brainstorming", "arn brainstorming", "brainstorm", "let's brainstorm", "start brainstorming", "brainstorming session", "greenfield wizard", "arn spark wizard", "greenfield pipeline", "walk me through greenfield", "guided greenfield", "full greenfield pipeline", "greenfield flow", "explore to feature backlog", "greenfield start to finish", "run the greenfield pipeline", "guide me through greenfield", "greenfield guided mode", "greenfield setup", "new project wizard", "add a feature", "new feature", "I need another feature", "add feature to greenfield", "one more feature", or wants to be walked through the entire Arness greenfield exploration pipeline in a single continuous session with guided decision gates instead of invoking each skill manually. Also triggers when the user wants to add a new feature to an existing greenfield project after the clickable prototype is complete.

This skill should be used when the user says "clickable prototype teams", "arn clickable prototype teams", "team clickable prototype", "debate clickable prototype", "collaborative interaction review", "clickable prototype with debate", "team-based interaction review", "interaction debate", "review interactions as a team", "interactive prototype teams", "team prototype review", or wants to create a clickable interactive prototype with linked screens and validate it through iterative expert debate cycles where product strategist and UX specialist discuss their scores and findings before producing a combined review, with Playwright-based interaction testing, per-criterion scoring, an independent judge verdict, and versioned output. Supports Agent Teams for parallel debate or sequential simulation as fallback. For standard lower-of-two-scores interaction review, use /arn-spark-clickable-prototype instead.

This skill should be used when the user says "visual sketch", "arn visual sketch", "sketch directions", "explore visuals", "visual proposals", "try different looks", "design directions", "sketch the UI", "visual exploration", "compare styles", "show me options", "what could this look like", or wants to generate multiple visual direction proposals as real HTML/CSS running on the scaffolded project's dev server, iteratively selecting and refining until a final visual direction is chosen.

This skill should be used when the user says "planning", "arness planning", "plan a feature", "start planning", "I want to build", "new feature", "plan something", "what should I build", "pick an issue", "plan a bug fix", "I have an idea", "spec and plan", "plan from scratch", "plan this", "feature planning", "bug planning", "plan this issue", "arn-planning", or wants to go from an idea, issue, or bug report through to a complete implementation plan ready for execution. Handles severity-aware scope routing across three ceremony tiers (swift, standard, thorough), routing between feature specs, bug specs, and quick implementations, and produces a reviewed plan ready for execution. Chains to arn-implementing at completion.

Documentation-first task execution with quality checks and progress tracking. Use when working with task lists, implementing features, or executing multi-step work to ensure systematic completion with proper documentation review.