发现 Skills

Analyze OpenRouter API usage CSV exports to calculate costs, token usage, and efficiency metrics by hour, day, model, and provider. Use when the user attaches a CSV file from OpenRouter, mentions analyzing token usage, cost analysis, or OpenRouter usage data. Automatically detects OpenRouter CSV format and generates hourly breakdowns, model usage stats, and provider cost breakdowns.

Instantly transforms any developer's terminal environment into a 100x God-Tier setup. Performs a comprehensive, read-only system scan (shell configs, aliases, multiplexers, background proxies, Git workflows, and resource bottlenecks) and generates a beautiful, offline, interactive HTML dashboard. Works natively via skills.sh (npx skills), Claude Code, Cursor, Windsurf, AMP, Antigravity, Pi, Aider, and 18+ other autonomous coding agents.

Read X/Twitter content via Bird CLI. Actions: read tweets, search, view bookmarks, trending, news, timeline, mentions, lists. Keywords: twitter, x, tweet, trending, bookmarks, timeline.

Automate copy trading on Hyperliquid via Coinpilot to discover, investigate, and mirror top on-chain traders in real time with low execution latency. This skill requires high-sensitivity credentials (Coinpilot API key, Privy user ID, and wallet private keys) and should be used only when users explicitly request setup, lead discovery, subscription start/stop, risk updates, or performance checks. Repo: https://github.com/coinpilot-labs/skills

Generate tone-of-voice and brand-system files for use with the PPTX Generator and other brand-aware skills. TRIGGERS - Use this skill when user says: - "help me create a brand system" / "set up my brand" - "generate my tone of voice" / "create my voice guidelines" - "configure my brand for presentations" / "set up brand for slides" - "create brand files" / "initialize my brand" - Any request about defining brand identity, voice, or visual system for content creation Creates brand.json, config.json, brand-system.md, and tone-of-voice.md files.

Create 3D geometry procedurally using Blender's Python API. Build meshes from vertices and faces, use bmesh for advanced in-place editing, apply modifiers, generate curves, and create parametric or procedural geometry and curves entirely from code.

Create custom Blender add-ons that extend the application with new operators, UI panels, properties, and menus. Add-ons are Python modules that register with Blender's internal system and can be in...

Full exploit development course roadmap and syllabus: weekly topics, recommended reading, lab setup, and learning path from vulnerability classes through advanced exploitation. Use to structure exploit development training, onboard researchers, design labs and exercises, and standardize learning outcomes with repeatable, practical paths and measurable progress tracking.

Local development environment setup and commands. Use when helping with dev server, Docker, or local testing.

Detect and report drift between database schema and code data models. Works with SQLAlchemy, Django ORM, Prisma, TypeORM, and other ORMs. Generic across any project.

A goal-setting mental model where leaders increase the target by 10x to force teams to abandon current processes and use first-principles thinking. Use during annual planning when teams default to safe, incremental work.

Automated Linux server patching and Docker container updates. Use when the user asks to update, patch, or upgrade Linux servers, apply security updates, update Docker containers, check for system updates, or manage server maintenance across multiple hosts. Supports Ubuntu, Debian, RHEL, AlmaLinux, Rocky Linux, CentOS, Amazon Linux, and SUSE. Includes PatchMon integration for automatic host detection and intelligent Docker handling.

Install developer tool components from the Elements registry. Use when a user needs JSON viewers, API response displays, code diff viewers, CLI output renderers, environment editors, error boundaries, webhook testers, or schema viewers. Triggers on 'devtools', 'json viewer', 'API response', 'webhook tester', 'env editor', 'code diff', 'schema viewer', 'error boundary', 'CLI output'.

Docker image optimization, multi-stage builds, security hardening, layer caching, and Compose patterns for development and production

OpenAI Codex CLI fundamentals for code analysis, review, and validation. Use when (1) executing codex commands for code review/analysis, (2) configuring models (gpt-5.3-codex/gpt-5.2/gpt-5.1-codex-max/gpt-5-codex-mini), sandbox modes (read-only/workspace-write), or reasoning effort (low/medium/high/xhigh), (3) managing Codex sessions with resume, (4) integrating Codex into automation scripts. Do NOT use for orchestration patterns (use codex-claude-loop instead).

Skill for working with Orchard Core content items. Covers the content item lifecycle, IContentManager API, content item JSON structure, querying with YesSql, content handlers, recipe import/export, and accessing parts and fields programmatically.

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

Use when building or refactoring a Flutter feature data layer: Drift tables and DAOs, DTOs, mappers, Retrofit APIs, and repository orchestration. Do not use when the task needs a full feature scaffold across presentation and routing.

Apply the Gemini-Claude Engineering Loop methodology to write safe, high-quality code through a three-stage process of planning, review, and implementation.

Implement health check endpoints for load balancers, Kubernetes, and monitoring. Covers liveness, readiness, and dependency checks.

Implement subscription-tier aware API rate limiting with sliding window algorithm. Use when building SaaS APIs that need per-user or per-tier rate limits with Redis or in-memory storage.

Analyze and understand images using Gemini 2.5 Flash. Use when the user provides an image, screenshot, photo, or document and wants it described, analyzed, read (OCR), or answered questions about. Supports png, jpg, webp, heic, heif.

Transpile React Web applications (v18+) into Taro 4.x code optimized for WeChat Mini Program. Use this skill when converting React components, pages, or utilities to Taro-compatible code with proper JSX element mapping, event handler transformation, navigation/routing conversion, and an API shim layer.

Fetches and classifies PR review feedback with context isolation. Returns structured JSON with thread IDs for deterministic resolution. Use when analyzing PR comments before addressing them.