发现 Skills

Implementation planner agent. Transforms specs into detailed, task-by-task implementation plans. Use when user says "burger plan", "create plan", "implementation plan", "break down tasks", or during burger-team Phase 3.

Electron main process and IPC development guidelines for Gemini-Subtitle-Pro. Use when working with IPC handlers, preload scripts, native integrations (ffmpeg, whisper, yt-dlp), file system operations, and desktop-specific features. Covers security requirements, IPC patterns, and cross-process communication.

Comprehensive guidance for training models in DataRobot, including project creation, AutoML configuration, feature engineering, and model selection. Use when training models, creating AutoML projects, or selecting models in DataRobot.

Systematic workflow for checking and responding to notifications. Use at session start and periodically. Covers prioritization, tone guidelines, and recording interactions.

Discover and recommend public skills from external registries (e.g. awesome lists, skill hubs). Use when the user is creating a new skill, importing a skill, or asking to find similar public skills. Maintains PUBLIC_SKILL_REGISTRY.urls and PUBLIC_SKILL_INDEX.yaml; returns top 5 similar matches with rich summaries and clear next actions.

Implement multiplayer games with Unity Netcode, Mirror, or Photon. Master client-server architecture, state synchronization, and lag compensation. Use for multiplayer features, networking issues, or real-time synchronization.

name: experimental-skill description: Claude skill in active development. Demonstrates the `stability: experimental` annotation with a partial frontmatter — common pattern for skills that are still...

Run a security baseline audit for web applications and APIs. Use when asked to assess auth and session handling, input validation, headers, CORS and CSRF, secret management, logging leakage, dependency risk, and pre-release security readiness.

Compatibility alias skill. Deprecated: use devops-engineer.

Design error experiences, structured logging, distributed tracing, alerting strategies, and user-facing error handling for production systems.

Game art principles: visual style selection, asset pipeline, and animation workflow.

Quality standards — a unified guide for code quality, design patterns, and anti-patterns. Includes SOLID principles, code-smell detection, and best practices.

What you can build and do with an always-on AI agent that has episodic memory. Covers concrete product ideas, workflows, emergent capabilities from persistence plus memory, and real-world examples of deployed persistent agents. Helps you go from 'I have the architecture' to 'here's what it actually does for me.' Activate on: 'what can an always-on agent do', 'persistent agent use cases', 'agent applications', 'proactive agent ideas', 'what to build with episodic memory', 'always-on agent product', 'personal AI assistant ideas', '/always-on-agent-applications'. NOT for: building the architecture (use always-on-agent-architecture), designing inputs (use always-on-agent-inputs), safety and privacy (use always-on-agent-safety).

Expert causal reasoning and mental model construction for diagnosis and prediction in complex domains

Classic software engineering text on project management, Brooks's Law, and the nature of software complexity

Polymarket CLOB API knowledge base for order management, WebSocket events, and trading operations. Use when working with order lifecycle (place, fill, cancel), debugging WebSocket USER_TRADE/USER_ORDER events, understanding API field mappings, or implementing trading logic.

Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.

Become a helpful co-worker in the workspace. Use it whenever you need to access, manage, or reference files.

Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.

Used when evaluating system architecture, platform design, or high‑level structures. Outputs a risk checklist.

Clean shutdown with in-flight job tracking, signal handlers, and buffer draining. Prevent data loss and corrupted state on process termination.

Guides creation of an AI token and cost-improvement plan—baseline audits, spend attribution, optimization-initiative backlog (prompt, context, model routing, RAG, agents), impact estimates, quality guardrails, measurement KPIs, and phased rollout with owners. Use when building a token-reduction roadmap, cost-optimization program, LLM unit-economics improvement plan, or executive brief on cutting inference spend without breaking evals—not for hands-on context layout implementation (ai-context-engineer), single-prompt rewrites (prompt-engineer), RAG pipeline build (ai-engineer), or AI ops cadence and vendor governance (ai-lead-ops). For end-to-end commercial/enterprise AI solution architecture before cost programs, use applied-ai-architect-commercial-enterprise. Empirical token studies and ablations: research-engineer-scientist-tokens.