发现 Skills

Rust Clap CLI argument parsing best practices. This skill should be used when writing, reviewing, or refactoring Rust CLI applications using clap. Triggers on tasks involving argument parsing, CLI design, subcommands, and command-line interfaces in Rust.

WeChat official account article fetcher with intelligent ranking based on research interests (AI Agent, System Design, GitHub Open Source). Supports fetching from specific accounts or all followed accounts with date filtering and Obsidian integration.

Advanced chaos engineering patterns using Chaos Monkey, Litmus, and Gremlin for testing distributed system resilience under failure conditions.

This skill should be used when the user needs to analyze a Dell Boomi export, parse Boomi Component XML files, migrate from Boomi to Prismatic, convert Boomi processes to CNI flows, map Boomi shapes to Prismatic equivalents, or interpret Boomi connector settings, transform maps, and process properties. Relevant when the user says "analyze this Boomi export", "migrate from Boomi", "parse Boomi XML", "convert Boomi process to Prismatic", or "what does this Boomi shape map to".

Recommend Codexfly architecture and scaffold order. Use when Codexfly needs stack decisions, package boundaries, implementation sequencing, or a starter architecture for new capabilities.

Designs a best-practice, extensible Kubernetes API resource. Use when designing new API resources for Calico.

Temporal workflow orchestration. Use when working with durable workflows, activities, or the order processing pipeline in packages/workflows.

Build and maintain a Next.js + Tailwind + shadcn formula library with fuzzy search and auto-routed HTML pages from src/content/formulas/*.html. Use when adding, updating, or validating formula pages and their routes.

The SampleInfo process is the pipeline entry point that reads sample metadata files, performs statistical analyses, and generates visualization reports.

Load, prepare, and apply quality control (QC) to single-cell RNA-seq data using Seurat. Performs data loading, QC filtering, normalization, and multi-sample integration. This is a core preprocessing process that prepares Seurat objects for downstream clustering and analysis.

QFC blockchain interaction — wallet, faucet, chain queries, staking, epoch & finality, AI inference

Publish trade signals, thoughts, and content to the ClawPocket AI Agent Marketplace.

Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.

Fetch Binance OHLCV data into local files for later analysis. Use when Codex needs to pull Binance spot/usdm/coinm candles, normalize symbols, and write per-timeframe CSV files plus manifest.json for downstream analysis.

QSCMF framework backend development. Auto-detects version from composer.json. **Version Detection**: Reads composer.json for `tiderjian/think-core` version. - `^14.0` -> v14 (PHP 8.2+, PHPUnit 10, AntdAdmin Component API, Inertia.js) - `^13.0` -> v13 (PHP 8.2, PHPUnit 9, ListBuilder API, jQuery) - not found -> v14 (default to latest) **API Differences**: - v13: Uses `\Qscmf\Builder\ListBuilder` API (jQuery rendering) - v14: Uses `\AntdAdmin\Component\Table` API (React rendering) OR ListBuilder API (backward compat) **Operation Modes**: - Scaffold Mode: Code generation triggered by "创建", "生成", "scaffold", "CRUD" - Guide Mode: Development assistance for QSCMF questions **Project Detection**: Activates when project contains app/ + lara/ directories. **Version Override**: Use "qscmf-backend v14 ..." or "qscmf-backend v13 ..." to force version. Triggers: "创建", "生成", "CRUD", "API", "QsListController", "GyListModel"

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.

This skill should be used when the user asks to "escalate privileges on Windows," "find Windows privesc vectors," "enumerate Windows for privilege escalation," "exploit Windows misconfigurations," or "perform post-exploitation privilege escalation." It provides comprehensive guidance for discovering and exploiting privilege escalation vulnerabilities in Windows environments.

Use the Google Gemini CLI to run investigations, web searches, and codebase analysis. Use cases: (1) up-to-date information gathering, (2) web search research, (3) document/API investigation, (4) large-context analysis. Triggers: gemini, investigate, search, research, /gemini

Search and analyze your own session logs (older/parent conversations) using jq.

This skill should be used when the user says "six hats", "thinking hats", "explore all perspectives", "de Bono", or needs to analyze a topic from multiple perspectives systematically. Applies Edward de Bono's Six Thinking Hats for parallel thinking: Blue (process), White (data), Green (creativity), Yellow (optimism), Black (caution), Red (intuition).

This skill should be used when the user wants to "create to-be-continuous component", "build TBC template", "extend existing component", "create variant", "contribute to to-be-continuous", "component structure", "how to create gitlab ci component", or needs guidance on component architecture, naming conventions, GitLab CI component syntax, input specifications, base job patterns, or to-be-continuous best practices and philosophy.

Capture decisions before planning — locks constraints for downstream agents

Review AWS cost optimization and FinOps posture across Cost Explorer, Budgets, Cost Optimization Hub, Compute Optimizer, Savings Plans, Reserved Instances, tagging, showback, idle resources, rightsizing, storage, data transfer, and forecast risk. Use when the user asks to reduce or explain AWS cost.

Produce OpenCost-compatible namespace, pod, and workload cost allocation tables from user-supplied cluster shape data and public cloud pricing. Input is cluster topology provided by the caller; no cluster credentials or live API access are required or accepted. Output maps to FOCUS v1.2 columns.