发现 Skills

For complex state: encapsulate multiple interacting variables, stateful algorithms, backtracking search state.

For memory efficiency: use with large or infinite sequences; supports early termination and pipeline processing without materializing all data.

For rule-based systems: store rules as data, easier to add/modify than if-elif chains, simplification tables, configuration.

Generate structured meeting minutes from meeting notes and chat records. Use this skill when users ask to summarize meetings, create meeting minutes, organize meeting notes, or document meeting outcomes. Supports extracting meeting information, participants, discussion points, decisions, action items, and to-do lists. Outputs in Markdown format with clear structure and actionable items.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents. Drop-in replacement for bd/Beads with simpler architecture. Use for: tracking issues/beads with dependencies, creating bugs/features/tasks, planning specs, implementing features from specs, code reviews, committing code, creating PRs, loading coding guidelines (TypeScript, Python, TDD, golden testing, Convex, monorepo patterns), code cleanup, research briefs, architecture docs, agent handoffs, and checking out third-party library source code. Invoke when user mentions: tbd, beads, bd, shortcuts, issues, bugs, tasks, features, epics, todo, tracking, specs, planning, implementation, validation, guidelines, templates, commit, PR, pull request, code review, testing, TDD, test-driven, golden testing, snapshot testing, TypeScript, Python, Convex, monorepo, cleanup, dead code, refactor, handoff, research, architecture, labels, search, checkout library, source code review, or any workflow shortcut.

Skill for listing devices, reading status, and executing commands on SmartThings IoT devices. Use this when the user asks you to interact with their smart home.

Complete production-ready guide for Motion Canvas with ESM/CommonJS workarounds, full setup templates, and troubleshooting for programmatic video creation using TypeScript

Use when a team is deflecting blame to external factors or a leader is micromanaging—shifts from permission-seeking to intent-stating using Willink's Extreme Ownership and Marquet's Leader-Leader model.

When the user wants to create technical content for developers including blog posts, tutorials, and documentation. Trigger phrases include "write a blog post," "technical article," "developer content," "tutorial," "devrel content," "dev blog," "technical writing," or "content for developers."

Strategic guidance on AI scaling laws, capability trajectories, and building products at the frontier of AI capabilities. Use when users ask about AI scaling trends, capability forecasting, planning AI product development timelines, understanding pretraining vs reinforcement learning phases, interpreting AI benchmark improvements, deciding when to build AI products that don't quite work yet, or strategizing around rapidly advancing AI capabilities. Also triggers for questions about task horizon doubling, Jevons paradox in AI, or how to position products for future model improvements.

End-to-end AI writing workflow for WeChat Official Account articles. A complete automated pipeline from trending topic discovery, in-depth research, Six Thinking Hats analysis, writing, to publishing drafts to the WeChat draft box. Trigger phrases: "write a WeChat article", "write using workflow", "help me write a WeChat article", "use AI to write for WeChat"

Use this skill when the user asks about current events, real-time information, recent news, live scores, financial data, price updates, recent changes, or any question that may require up-to-date web information. This skill first determines if web search is necessary using Gemini, then attempts Google Search Grounding via Gemini, and automatically falls back to Tavily if any failure occurs.

Use when Openclaw needs to test or operate GoHome (Home Assistant clone) via gRPC discovery, metrics, and Grafana.

Detects and fixes CS0618 obsolete API warnings in .NET builds. The compiler is the authoritative source for what your project actually triggers — it catches transitive obsoletions, overload-resolution surprises, and project-local [Obsolete] attributes that static inspection cannot see. Pair with dotnet-inspect@0.7.8+ for the static / pre-build view.

Backend development with Kotlin, Spring Boot, REST APIs. Use for backend, api, service, kotlin, rest tags. Provides validation commands, testing patterns, and blocker scenarios.

Create and deploy production-ready MCP servers on Cloudflare Workers. Use when building a Workers-hosted MCP server with auth, billing, and operational guardrails.

Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).

Enforces secure coding practices. Required after all code implementations to run CodeGuard security check. Covers input validation, secrets management, and OWASP countermeasures.

Implement or extend a user-facing workflow in a web application, integrating with existing backend APIs. Use when the feature is primarily a UI/UX change backed by existing APIs, affects only the web frontend, and requires following design system, routing, and testing conventions.

Compress and simplify prompts to preserve meaning while reducing use of context

PRD validation workflow. Load when user asks to validate, check, or review a PRD for completeness. Do NOT load for PRD creation or editing.

Act as an active outline partner who develops structure collaboratively. Use when developing, iterating, or improving story outlines. Generates scene beats, character arcs, plot structures, and exploratory prose samples. Contrasts with story-collaborator which drafts finished prose.

Structure scenes and control pacing using scene-sequel rhythm. Use when individual scenes work but don't accumulate, when pacing feels off (too rushed or too slow), when transitions feel mechanical, or when readers can follow but aren't compelled forward. Based on Dwight Swain's Goal-Conflict-Disaster and Reaction-Dilemma-Decision structure.