发现 Skills

Guides users through designing multi-agent systems with LangGraph, from task breakdown to production-ready code with proper state communication.

Feature-Sliced Design (FSD) architecture methodology guide. A reference for frontend project directory structure, layer/slice/segment design, dependency rules, and Public API patterns.

Set up a new WireLog analytics project from scratch

Execute the implementation plan autonomously with intelligent atomic commits. Agent manages work order and git history.

Creates or updates PLAN.md based on session - auto-detects create vs update mode

Create and configure AI agents for Cursor (.cursor/agents/) and Claude Agent SDK programmatic definitions.

Production-grade Bootstrap 5.3 patterns for building modern, responsive web UIs in HTML and ASP.NET Core Razor Pages/Views. Use when creating or styling web pages, layouts, navigation, forms, cards, modals, tables, or any UI component with Bootstrap 5. Covers the grid system, responsive breakpoints, utility classes, color modes (dark/light), accessibility, and integration with ASP.NET Core tag helpers and Razor syntax. Trigger on any task involving Bootstrap CSS classes, responsive HTML layouts, Razor Page UI design, or front-end styling for .NET web applications.

Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing features for parallel development, establishing file ownership boundaries, or managing integration between parallel work streams.

Update RepoPrompt tool guidance based on MCP/CLI changes across versions. Two-phase workflow - invoke BEFORE upgrading (--pre), then AFTER upgrading (--post). Uses `~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh` to detect and diff changes (outputs to `~/.pi/agent/skills/repoprompt-tool-guidance-refresh/rp-tool-defs/`).

This skill provides comprehensive system administration and monitoring tools through the x-cmd CLI, including process management, macOS system utilities, network configuration, disk health monitoring, and storage analysis. Use this skill when you need to perform system administration tasks, monitor system performance, manage network configurations, or troubleshoot system issues from command-line interfaces.

Router skill for Anthropic platform-side features that sit above the raw Messages API: Agent Skills format (the spec for `.skill` packages used by platform-managed agents), MCP connectors hosted by Anthropic, tool use (computer use, code execution, bash tool, define-your-own tools), build-with-claude features (extended thinking, message batches, citations, Amazon Bedrock, Google Vertex, embeddings, fast mode, context editing), manage-claude operations (workload identity federation, billing, identity), and the Managed Agents product. Use when the user asks about: writing an Agent Skill `.skill` package, Anthropic's hosted MCP connector, the computer-use tool, the code_execution tool, bash tool, extended thinking, message batches, prompt caching strategy at the platform level, citations, deploying via Bedrock or Vertex, embeddings models, fast-mode behavior, context editing strategies, WIF setup, billing / cost reports, identity & SSO setup, or the Managed Agents product. Skip: raw POST /v1/messages requests (use anthropic-api), Claude Code CLI (use claude-code), Claude Agent SDK (use claude-agent-sdk), user-facing Claude Connectors directory (use claude-connectors).

Hera log detail query toolkit for querying log details by spaceId, storeId, tailName and time range. Use this when you need to query Hera log information programmatically.

Correct way to delegate tasks to Claude Code from Hermes Agent — via terminal tool with `-p` print mode. Do NOT use `--acp --stdio` (that's GitHub Copilot CLI, not Claude Code).

Complete guide to using and extending Hermes Agent — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference. Load this skill when helping users configure Hermes, troubleshoot issues, spawn agent instances, or make code contributions.

Songwriting craft, AI music generation prompts (Suno focus), parody/adaptation techniques, phonetic tricks, and lessons learned. These are tools and ideas, not rules. Break any of them when the art calls for it.

Xiaohongshu (Xiaohongshu/RED) public notes and user data analysis skill that queries note details, comments, user profiles, search, topics, product/recommendation content and recommendation feeds via the MaxHub API. Suitable for brand seeding analysis, KOL profiling, content ideation, competitor monitoring and comment insights. Read-only by default; agents should follow recipes to choose the note/user/search/comment flows, pass parameters using fields such as note_id/user_id/keyword, and avoid collecting personal data beyond authorized scope. All requests are sent to https://www.aconfig.cn.

Use when building, debugging, packaging, or publishing browser userscripts for Tampermonkey or ScriptCat, including GM APIs, metadata blocks, permission issues, @match/@grant/@connect setup, ScriptCat background or scheduled scripts, UserConfig blocks, or subscription workflows.

Use when the user wants to read their X (Twitter) bookmarks after explicit approval - tweets they have privately saved. Lists, searches, and exports bookmarks from a connected account. Read-only; requires an account connection.

Use when the user wants to read X (Twitter) Lists. Extracts list members, list followers, and the post feed of a list. Read-only.

API interface development specification for the leniu-yunshitang-core project. A guide to API development based on a four-layer architecture. Trigger scenarios: - Designing API interfaces for the leniu project - Implementing Controller layer code for leniu - Configuring interface permissions and parameter validation - Choosing interface return value types - Multi-client routing planning (Web/Mobile/Android) Applicable project: leniu-tengyun-core (Cloud Canteen project) Trigger keywords: API interface, Controller, LeResult, LeResponse, LeRequest, interface development, route prefix, paginated query, interface permissions

Automatically use this Skill when you need to implement real-time communication, message push, or online status management. Trigger scenarios: - Need server-to-client message push - Need two-way real-time communication (chat, collaboration) - Need to manage user online status - Need system notifications, order status changes, or other real-time pushes - Need to synchronize messages across multi-instance deployments Trigger words: WebSocket, SSE, real-time push, message notification, online status, bidirectional communication, Server-Sent Events, real-time communication, message push, SseEmitter, WebSocketUtils, SseMessageUtils

用于查询指定出发地到目的地的火车车次信息

Fetch and summarize web page content. 获取网页内容并生成摘要，支持提取网页标题、正文、关键信息。