发现 Skills

Expert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies. Use PROACTIVELY when the user asks about market opportunity, TAM/SAM/SOM, financial projections, unit economics, competitive landscape, team planning, startup metrics, or business strategy for pre-seed through Series A startups.

Expert Terraform/OpenTofu specialist mastering advanced IaC automation, state management, and enterprise infrastructure patterns. Handles complex module design, multi-cloud deployments, GitOps workflows, policy as code, and CI/CD integration. Covers migration strategies, security best practices, and modern IaC ecosystems. Use PROACTIVELY for advanced IaC, state management, or infrastructure automation.

Develop plugins for IDA Pro in Python, using idiomatic patterns, lessons, and tricks, including the Python Domain API (ida-domain). Use when creating both GUI (Qt) and background plugins for inspecting and rendering things program structure, functions, disassembly, cross-references, and strings.

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Use this skill when the user asks to review the security of plugins, scan plugins for vulnerabilities, or audit installed plugins. Also suggest this skill when you notice a new plugin has been added.

Expert developer skill for implementing real-time voice and video interactions using the Google Gemini Live API. This skill should be used when implementing bidirectional audio streaming, voice conversations with interruption handling, real-time transcription, function calling in live sessions, session management, or voice customization.

Fast workflow for small changes, bug fixes, and UI tweaks that don't require full feature development. Uses sub-agent orchestration with model selection (Sonnet 4.5 orchestrator, Haiku 4.5 workers) for efficient context management. Handles styling adjustments, minor functionality fixes, and quick improvements while maintaining project quality standards.

TypeScript/JavaScript development workflow for the apps/ directory. Use when modifying TypeScript code in xrpl-grpc-server or JavaScript in eth-contracts.

Reference documentation for getting started with Claude Code -- installation on macOS, Linux, Windows, and WSL, quickstart walkthrough, authentication (Claude Pro/Max/Teams/Enterprise/Console/cloud providers), credential management, system requirements, updates, uninstallation, the agentic loop, built-in tools, sessions, checkpoints, and permission modes. Use when answering questions about installing, setting up, logging in, or understanding how Claude Code works.

Reference documentation for running Claude Code programmatically via CLI (`claude -p`) and on the web (claude.ai/code) — covers structured output, streaming, tool auto-approval, session continuation, cloud environments, network access, teleporting sessions, and CI/CD patterns.

Generate a short script, character voices, and an optional teaser for a mini drama.

Use this skill when users need to audit, detect, or remediate Identification and Authentication Failures (OWASP A07:2021) on Google Cloud Platform. This includes auditing Identity-Aware Proxy (IAP) configuration, enforcing multi-factor authentication (MFA), detecting brute force attack vectors, configuring Cloud Armor rate limiting, reviewing API key rotation and session management, checking Identity Platform and reCAPTCHA Enterprise enablement, and monitoring authentication-related Security Command Center findings. Activate for GCP authentication hardening, brute force protection, MFA enforcement, rate limiting configuration, or OWASP A07 compliance.

Professional PDF Report Generator

Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use --skip to bypass). 3 modes: search, creative, wild. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.

Generate comprehensive plans for new features by exploring the codebase, synthesizing approaches, validating with spikes, and decomposing into beads. Use when asked to plan a feature, create a roadmap, or design an implementation approach.

Standards for ARC, Weak/Unowned References, and Capture Lists

Skill imported from holybell15/ai-first-framework

Control smart home devices via Home Assistant: lights, climate, media, covers, scenes, sensors, automations, and more. 34 tools with readOnly and domain-level safety guards.

This skill should be used when reviewing, auditing, or improving existing Claude Code skills to ensure they follow Anthropic best practices, have proper structure, use current domain-specific patterns, and include all necessary resources. It analyzes skill quality, identifies gaps, suggests improvements, and can automatically enhance skills with updated best practices. Trigger terms include review skill, audit skill, improve skill, enhance skill, update skill, check skill quality, skill best practices, fix skill, optimize skill, validate skill structure.

Design and generation workflow for new project assets (portraits, icons, arena art). Use when the implementation requires a visual resource that does not yet exist in `assets/`.

Ultimate Home Assistant skill - complete administration, wireless protocols (Zigbee/ZHA/Zigbee2MQTT, Z-Wave JS, Thread, Matter), ESPHome device building, advanced troubleshooting, performance optimization, security hardening, custom integration development, and professional dashboard design. Covers configuration, REST API, automation debugging, database optimization, SSL/TLS, Jinja2 templating, and HACS custom cards. Use for any HA task.

Configure MQTT brokers (Mosquitto, EMQX) for IoT messaging, device communication, and smart home integration. Manage topics, QoS levels, authentication, and bridging. Use when setting up IoT messaging, smart home communication, or device-to-cloud connectivity. (project)