发现 Skills

A finalization skill that generates or modifies a final Markdown research report based on existing research materials or drafts. Use in these situations: ① you already have deep-research outputs (`synthesis.md`, `plan.json`, `sub_reports/*.md`) and need to produce the final `report.md`; ② you have an existing report, draft, or manuscript path and need rewriting, rephrasing, polishing, compressing, expanding, restructuring, strengthening the summary, or adding tables/figures; ③ during the finalization stage you need to proactively plan and insert Markdown tables, Mermaid diagrams, AI concept illustrations, or other visual elements. For final-doc generation and targeted document editing only; not for doing research from scratch, research planning, online evidence gathering, multi-dimensional research, or generating `synthesis.md`. If the user only requests “deep research/research/write a research report” without existing materials, prefer `sn-deep-research`.

Renames projects and content with dense, meaningful ontological titles that describe essence and function. Combines 3-4 words using separator conventions (- for compound/close words, -- for distant concepts). Provides translations to Latin and Greek. Use when naming projects, repositories, systems, or concepts.

Checks for updates to remote GH site for palladius/gemini-cli-custom-commands. Use Ruby code to check for newer/older version.

Implement OAuth 2.1 / OIDC authentication using Better Auth with MCP assistance. Use when setting up a centralized auth server (SSO provider), implementing SSO clients in Next.js apps, configuring PKCE flows, or managing tokens with JWKS verification. Uses Better Auth MCP for guided setup. NOT when using simple session-only auth without OAuth/OIDC requirements.

Provides comprehensive guidance for Kubernetes including pods, services, deployments, ingress, and cluster management. Use when the user asks about Kubernetes, needs to deploy applications to Kubernetes, configure Kubernetes resources, or manage Kubernetes clusters.

Provides comprehensive guidance for Lime ECharts including chart creation, configuration, data visualization, and interactive charts. Use when the user asks about Lime ECharts, needs to create charts, visualize data, or work with ECharts features.

Provides comprehensive guidance for ProcessOn mind mapping including mind map creation, node management, and collaboration. Use when the user asks about ProcessOn mind maps, needs to create mind maps, organize ideas, or collaborate on mind maps.

Synthesize outputs from multiple AI models into a comprehensive, verified assessment. Use when: (1) User pastes feedback/analysis from multiple LLMs (Claude, GPT, Gemini, etc.) about code or a project, (2) User wants to consolidate model outputs into a single reliable document, (3) User needs conflicting model claims resolved against actual source code. This skill verifies model claims against the codebase, resolves contradictions with evidence, and produces a more reliable assessment than any single model.

Use when editing ComfyUI workflow JSON, adding nodes, wiring connections, modifying workflows, adding ControlNet/LoRA/upscaling to a workflow, or submitting workflows to ComfyUI.

Self-contained app generator — invoke this skill directly, do not decompose into sub-steps. Generates React web apps with the Fireproof database. Use when creating new web applications, adding components, or working with local-first databases. Ideal for quick prototypes and single-page apps that need real-time data sync.

Webhook testing, schedule validation, event-driven triggers, and polling mechanism testing for n8n workflows. Use when testing how workflows are triggered.

Create a plan to migrate platforms or runtimes. Use when a senior developer needs a phased migration approach.

Improve and rewrite user prompts to reduce ambiguity and improve LLM output quality. Use when a user asks to optimize, refine, clarify, or rewrite a prompt for better results, or when the request is about prompt optimization or prompt rewriting.

Comprehensive guide to GPG commit signing. Set up, configure, and troubleshoot GPG commit signing. Fix GPG signing errors, configure passphrase caching, verify commit signatures. Use when working with Git commit signing, GPG keys, commit verification, signature verification, GPG configuration, or when encountering GPG signing errors. Covers Windows (Gpg4win), macOS (GPG Suite), Linux (gnupg), and WSL installation and setup.

Use this skill when the user says "show my unread emails", "what's in my inbox", "summarize my email", "check my inbox", "what emails do I have", "triage my inbox", or wants a quick summary of unread Gmail messages. Covers sender, subject, date, labels, and custom search queries.

This skill should be used when the user wants to add a service from a template, find templates for a specific use case, or deploy tools like Ghost, Strapi, n8n, Minio, Uptime Kuma, etc. For databases (Postgres, Redis, MySQL, MongoDB), prefer the database skill.

Azure Web PubSub Service SDK for Python. Use for real-time messaging, WebSocket connections, and pub/sub patterns.

Develop, test, build, and deploy Godot 4.x games. Includes GdUnit4 for GDScript unit tests and PlayGodot for game automation and end-to-end testing. Supports web and desktop exports, CI/CD pipelines, and deployment targets such as Vercel, GitHub Pages, and itch.io.

Help users navigate career changes and pivots. Use when someone is considering a new role, transitioning into product management, evaluating job offers, taking a sabbatical, or feeling stuck in their current position.

Best practices for Remotion - Video creation in React

Extracts structured sales discovery insights from a prospect call transcript that is already in context. Use this skill whenever the user wants to analyze a transcript for technical environment details, vulnerability management maturity, compliance posture, or pain points — e.g. "extract insights from this transcript", "pull discovery notes from the call", "what did we learn about their environment", "summarize findings from the meeting", "fill in my discovery template", or any variation where the user wants structured qualification data from a call they just had or retrieved. Always use this skill even if the user just pastes a raw transcript or says "what did we learn" — if a transcript is in context and they want structured discovery output, this applies.

Workflow to review authentication and authorization flows (sessions, tokens, RBAC/ABAC) and produce fix guidance.

Common testing mistakes to avoid for reliable, maintainable tests

Comprehensive macOS development guidance including Swift 6+, SwiftUI, SwiftData, architecture patterns, AppKit bridging, and macOS 26 (Tahoe) APIs. Use for macOS code review, best practices, UI review, or platform-specific features.