发现 Skills

Disco Elysium PHYSICAL INSTRUMENT skill: brute force when needed. Activates for mass operations, full rewrites, 'rewrite this entire file', large-scale find-and-replace, or when surgical precision is less efficient than rebuilding.

Disco Elysium skill system for Cursor. Master character sheet coordinating 24 inner-voice skills across Intellect, Psyche, Physique, and Motorics. Use when the user mentions skills, character sheet, disco elysium system, or asks about the skill voice system.

Building effective fuzzing harnesses to maximize code coverage and vulnerability discovery through automated input generation

Unified patterns and templates for creating consistent Claude Code plugins. Use when creating new plugins, designing plugin architecture, implementing builder patterns, or standardizing plugin structure. Trigger keywords - "plugin SDK", "plugin template", "plugin pattern", "builder pattern", "plugin structure", "new plugin", "plugin architecture".

Use when JetBrains MCP tools are available (mcp__jetbrains__*) - enforces an IDE-native workflow with problem checking after file completion, and smart refactoring tools instead of grep/sed

Operate a user's Stingray crypto research account via REST API with a personal access token (sa_pat_...). Use when the user asks to check account status, research assets, manage watchlist or portfolio, create or adjust alerts, use web or Telegram or WhatsApp chat, manage referrals, check credits, or rotate API tokens. Do not use for PAT creation, billing, admin, or webhook operations.

Automate single-cell RNA-seq analysis with Scanpy or Seurat. QC, normalisation, clustering, DE analysis, and visualisation.

Debug AsyncRedux applications effectively. Covers printing the state with store.state, checking actionsInProgress(), using ConsoleActionObserver, using StateObserver for state change tracking, and tracking dispatchCount/reduceCount.

Guide Claude on building responsive Vaadin 25 layouts that adapt to different screen sizes. This skill should be used when the user asks to "make a layout responsive", "support mobile", "adapt to screen size", "use breakpoints", "use media queries", "use container queries", "responsive design", "mobile first", or needs help making a Vaadin Flow view work well on both desktop and mobile devices.

Use this skill when creating, modifying, or debugging ComfyUI custom nodes. Triggers on: 'ComfyUI custom node', 'ComfyUI node development', 'ComfyUI plugin', 'INPUT_TYPES', 'NODE_CLASS_MAPPINGS', 'RETURN_TYPES', 'define_schema', 'io.ComfyNode', or any request to build a new node for ComfyUI. Covers both V1 (current) and V3 (new) node APIs.

Ensure that Java types are documented with Javadoc comments and follow best practices for documentation.

Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.

Systematic compatibility analysis, migration guidance, and breaking change detection for dependency/framework upgrades. Auto-executes when the user clearly intends to upgrade, update, migrate, or modernize software dependencies, frameworks, packages, or technology stacks.

跨平台比价与购物推荐 / Cross-platform price comparison. 淘宝 / 京东 / 天猫 / 拼多多商品聚合搜索 + 拍图识物。需要先启用 ckjia-shopping MCP server 并配置 CKJIA_MCP_KEY 才能用。

Full security audit and enforcement for public repositories across 12 attack surfaces: git history, source code, docs, config, .gitignore recon, CI/CD, containers, dependencies, binaries, metadata, platform-specific (GitHub/GitLab), license compliance, and community surface. Provides fast-path and full 20-check audits, pre-commit hooks, CI gates, .gitignore generation, and history scrubbing. Use whenever pushing to a public remote, open-sourcing a repo, writing README/docs, configuring CI/CD or Dockerfiles, adding dependencies, or checking license compliance. Trigger on: push to GitHub, make repo public, open source this, set up the repo, write README, add CI/CD, create Dockerfile, set up pre-commit, add license, write SECURITY.md, secret leaks, credential rotation, .claude/ tracking, repo hygiene, security scanning, or is this safe to push, pre-oss, open source readiness, release audit, or open source audit. This is the gatekeeper between internal and public.

Generates comprehensive pytest test suites: happy path, edge cases, error conditions, fixture scaffolding, mock strategy, and async patterns. Analyzes function signatures, dependency chains, and complexity hotspots to produce runnable, parametrized test files. Triggers on: "generate tests", "write tests for", "test this function", "test this class", "create test suite", "what tests should I write", "pytest for", "unit tests for", "mock strategy for", "how to test", "test coverage for", "write a test file". Use this skill when given a Python function, class, or module and asked to produce tests.

Production patterns for the Tokio 1.48.0 async runtime, including task spawning, channels (mpsc, oneshot, broadcast, watch), synchronization primitives, graceful shutdown, and lifecycle management. Use this when spawning background tasks, managing concurrency, implementing graceful shutdown, or coordinating asynchronous work in Rust applications.

Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strategies, or building backtesting infrastructure.

Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.

Automate Sensibo tasks via Rube MCP (Composio). Always search tools first for current schemas.

Conservative, transparent, context-aware file reorganization for local folders with deterministic taxonomy, duplicate staging, report generation, profile modulation, and rollback safety. Use when a user asks to clean up or systematize a directory tree, reclassify inbox folders, create repeatable file-overhaul workflows, generate audit/plan/apply reports, generate custom reorg profiles, or undo a prior reorganization run.

Complete toolkit for web crawling and data extraction using Crawl4AI. This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.

Tool-neutral CLI agent rules for TI MSPM0 development with Code Composer Studio, CCS Theia, SysConfig, and DriverLib. Use when an agent needs to inspect or modify MSPM0 CCS projects, edit .syscfg configuration, avoid generated SysConfig files, use DriverLib APIs, validate SysConfig output, or work on NUEDC-style MSPM0 embedded firmware.

Use when building applications with Weavr for payments, cards, accounts, and identity verification. Covers both API integration and secure UI components.