全部能力

为 AI Config 创建、跟踪、检索、更新和删除自定义业务指标。涵盖完整生命周期：通过 API 定义指标类型，通过 SDK 上报事件，…

Show AgentOps work status.

为现有代码库接入 LaunchDarkly AI Config 跟踪功能。涵盖四层递进路径：托管运行器（managed runner）→ 提供商包（provider package）→ 自定义提取器（custom extractor）→ …

Build agents for legal document analysis, contract review, and compliance checking. Handles document parsing, risk identification, and legal research. Use when…

Evidence-based memory optimization from real usage patterns. Analyzes recall performance, identifies bottlenecks, suggests consolidation/pruning/enrichment, and tracks improvement over time via checkpoint Q&A.

Expert skill for writing FreeCAD Python scripts, macros, and automation. Use when asked to create FreeCAD models, parametric objects, Part/Mesh/Sketcher…

Use when writing concurrent Go code — goroutines, channels, mutexes, or thread-safety guarantees. Also use when parallelizing work, fixing data races, or…

Datadog docs lookup using docs.datadoghq.com/llms.txt and linked Markdown pages.

Use when running a dbt Fusion project with Astronomer Cosmos. Covers Cosmos 1.11+ configuration for Fusion on Snowflake/Databricks with ExecutionMode.LOCAL.…

Datadog 面向 AI 智能体的技能。核心监控、日志、链路追踪与可观测性。

Analyze and reclaim macOS disk space through intelligent cleanup recommendations. This skill should be used when users report disk space issues, need to clean…

Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample documents. Use this skill…

Expert brand strategy covering brand positioning, identity development, brand architecture, messaging frameworks, and brand governance. Use when developing brand positioning statements, creating messaging frameworks, auditing brand health metrics, building brand architecture models, or establishing brand governance guidelines.

Design and generate Convex database schemas with proper validation, indexes, and relationships. Use when creating schema.ts or modifying table definitions.

使用 data.diemeng.chat 提供的接口查询股票日线、分钟线、财务指标等数据，支持 A 股等市场。

Guide for using Recent Data (topics, resources, pages). Use when working with recently accessed items, implementing recent lists, or accessing session store…

Use when working with Go slices, maps, or arrays — choosing between new and make, using append, declaring empty slices (nil vs literal for JSON), implementing…

AI-powered job search pipeline built on Claude Code with 14 skill modes, Go dashboard, PDF generation, batch processing, and portal scanning.

Create flowcharts, sequence diagrams, state machines, class diagrams, Gantt charts, and mindmaps using simple text-based syntax. Best for process flows, API…

EXPERIMENTAL: Three-layer parallel meta-cognition analysis. Triggers on: /meta-parallel, 三层分析, parallel analysis, 并行元认知