Agent Skills Hub

dgame-dev

Expert assistant for the DGame Unity framework, facilitating development, architecture, hotfix, and resource management within the TEngine-based ecosystem.

autoresearch

Autonomous multi-team codebase improvement agent with specialized modes: narrow (goal-directed), broad (hypothesis-divergent), and sweep (quality-focused).

read-file

Read and analyze any data file (CSV, JSON, Parquet, Avro, Excel, etc.) or remote URL (S3, HTTPS) using DuckDB. Automatically detect file formats and preview/profile datasets.

cli

Prefect CLI skill for executing mutation operations like triggering deployments, canceling flow runs, and managing automations within your Prefect infrastructure.

goplaces

A modern CLI tool for querying Google Places API to perform text searches, retrieve place details, resolve addresses, and get reviews in human-readable or scriptable JSON formats.

sap-abap

Comprehensive ABAP development support for SAP systems, covering classic ABAP, ABAP Cloud, CDS views, RAP, EML, and modern syntax patterns.

synapse

Autonomous pattern detection and skill recommendation engine that monitors project memory, logs, and task lists to evolve your AI agent's capabilities automatically.

metrics-dashboard

Design comprehensive product metric dashboards, define KPIs, and establish monitoring plans with data-driven visualization, alert thresholds, and framework integration.

obsidian

Manage and automate your Obsidian knowledge base using a CLI tool to search, create, move, and refactor Markdown notes directly.

response-compliance

Run OpenResponses API compliance tests to validate schema adherence, streaming responses, and endpoint reliability for LobeHub integrations.

sound-effects

Generate professional-grade sound effects from text descriptions. Create audio textures, cinematic impacts, UI sounds, and ambient environments with precision control over duration, looping, and prompt adherence.

swift-review

Expert Swift code review for macOS/iOS. Detects memory leaks, threading bugs, concurrency issues, and accessibility gaps using parallel analysis agents.