发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
war-game-orchestrator
Business war-game orchestration capability for simulating competitive responses and testing strategic choices.
media-auto-publisher
Universal self-media article auto-publishing tool. Supports automated publishing workflows for six platforms: Baijiahao, Sohu, Zhihu, WeChat Official Accounts, Xiaohongshu, and Douyin. Uses Playwright to automate platform navigation and publishing, and supports account switching by managing cookies via storageState.
writing-agents
Use when creating new agents, editing existing agents, or defining specialized subagent roles for the Task tool
headless-godot
Headless Godot (4.2+) development rules: CLI conventions, export, scene editing via script, and testing. Use when running Godot CLI commands, editing .tscn via script, or exporting in headless mode.
beam-debug-issue-tasks
Debug failed/issue tasks from Beam.ai using Langfuse traces. Load when user says "debug issue tasks", "check failed tasks", "why did task fail", "task errors", "debug agent", or needs to investigate task failures.
Feasibility Analysis
This skill should be used when evaluating whether a feature, architecture, or approach is practical given the current codebase, team, and constraints. It scores the feasibility of a proposed implementation before committing to it, preventing investment in impractical solutions.
mcp-refactoring
Refactoring MCP tools for better LLM integration and usability
claude-code-expert
Deep specialist in Claude Code — Anthropic's CLI. Maximizes productivity using shortcuts, hooks, MCPs, advanced configurations, workflows, CLAUDE.md, memory files, sub-agents, permissions, and ecosystem integrations.
conductor-validator
Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.
fastapi-router-py
Create FastAPI routers following established patterns with proper authentication, response models, and HTTP status codes.
fixing-metadata
Audit and fix HTML metadata including page titles, meta descriptions, canonical URLs, Open Graph tags, Twitter cards, favicons, JSON-LD structured data, and robots directives. Use when adding or reviewing SEO and social metadata.
git-advanced-workflows
Master advanced Git techniques to maintain clean history, collaborate effectively, and recover from any situation with confidence.
interview-coach
Full job search coaching system — JD decoding, resume, storybank, mock interviews, transcript analysis, comp negotiation. 23 commands, persistent state.
llm-application-dev-ai-assistant
You are an AI assistant development expert specializing in creating intelligent conversational interfaces, chatbots, and AI-powered applications. Design comprehensive AI assistant solutions with natur
makepad-dsl
CRITICAL: Use for Makepad DSL syntax and inheritance. Triggers on: makepad dsl, live_design, makepad inheritance, makepad prototype, "<Widget>", "Foo = { }", makepad object, makepad property, makepad DSL syntax, makepad inheritance, makepad prototype, how to define makepad components
ml-pipeline-workflow
Complete end-to-end MLOps pipeline orchestration from data preparation through model deployment.
obsidian-markdown
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
pakistan-payments-stack
Design and implement production-grade Pakistani payment integrations (JazzCash, Easypaisa, bank/PSP rails, optional Raast) for SaaS with PKR billing, webhook reliability, and reconciliation.
recallmax
FREE — God-tier long-context memory for AI agents. Injects 500K–1M clean tokens, auto-summarizes with tone and intent preservation, compresses 14-turn history into ~800 tokens.
tool-design
Build tools that agents can use effectively, including architectural reduction patterns. Use when creating new tools for agent systems, debugging tool-related failures or misuse, or optimizing existing tool sets for better agent performance.
web-artifacts-builder
To build powerful frontend claude.ai artifacts, follow these steps:
create-codeql-query-unit-test-javascript
Create comprehensive unit tests for CodeQL queries targeting JavaScript code. Use this skill when you need to create, validate, or enhance test coverage for JavaScript CodeQL queries using the CodeQL Development MCP Server tools.
beef
Browser Exploitation Framework — hook browsers via XSS/injected JS and perform client-side attacks. Use when you have XSS on a target to pivot into browser-side attacks, session hijacking, and social engineering.
Agennext-agent-skills-cs-ceo-advisor
File path: ../../../agents/c-level/cs-ceo-advisor.md