Register the current Claude Code session under Session Kit and pre-allocate the durable archive + ledger that other session-kit skills depend on. Use when the user says "/checkin", "register this session", "set up session kit here", "start a session", or starts working in a scratch / unfilled cwd and wants explicit…
Write 5-6 genuinely different ad angles for one offer (different who, different pain, different promise), each ready to become its own Meta ad. Use when launching, or when testing has killed your current angles.
One poll-and-act step for the ticket enhancer. Enhances every open draft ticket that still needs work. A human LGTM is the only comment that marks a ticket ready. Use when invoked as /enhancer-loop, typically from task run or wrapped in /loop for repeated polling.
The shared vocabulary and discipline for designing deep modules. Use when shaping a module's interface, placing a seam, making code testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Control Planchette, the terminal IDE this session may be running in: list its terminals, open one, send a prompt to another agent, wait for it to finish, and read its output. Use only when the user explicitly asks to inspect or drive Planchette terminals, or to hand work to another agent beside this one. Do not use…
Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The don't do the work yourself rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
A workflow for analysing court judgments written in Chinese. It starts when a user asks to analyse a judgment or provides the judgment text, case number, or a judgment link.
A hand-drawn-style template for turning technical articles or code into narrated animated videos. It uses scenes, speech, animation, and captions to explain one topic in a vertical video.
A Chinese-language writing guide modeled on patterns found in 176 public articles by the WeChat writer “数字生命卡兹克.” It helps produce long-form technology commentary, explainers, and investigative-style articles with a conversational voice.
Swift concurrency for macOS — actors, @MainActor, Task/TaskGroup, AsyncStream, Sendable, strict concurrency migration, and AppKit bridging patterns (DispatchQueue, NSRunLoop, XPC service concurrency). Use when writing async Swift code that interacts with AppKit, daemons, or XPC services on macOS.
Mentor mode for learning-focused sessions. Guides the user through concepts, architecture, and hands-on experimentation using targeted code snippets — no full code generation. Activate when the user wants to learn deeply rather than just get things done fast.
Autonomous industry research agent that produces professional research reports (.docx). Begins with a brief interactive intake to confirm scope and collect background, then autonomously conducts comprehensive desk research (web search, data gathering, analysis) and delivers a polished Word report for human review. Use…
A tool for turning articles into HTML that can be pasted into or sent to WeChat Official Accounts, China’s publishing platform for public messages. It supports formatting workflows and, when credentials are configured, managing drafts and publishing through WeChat’s official API.
A tool for turning a software project's code and user interface into project documents. It can produce documents such as requirements, design, testing, operations, and deployment guides.
Convert PDFs to accurate Markdown for AI reading using pdf-inspector (Rust) — smart text/scanned classification, per-page OCR routing, page markers, and context-size chunking. Cross-platform (macOS/Linux/Windows).
Canonical Go coding standards and best practices. Use when writing, reviewing, or refactoring Go code. Covers formatting, naming, errors, functions, structs, interfaces, and testing conventions.
Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, permissions, system prompts, planning, goals, context…
The data layer for every app - TanStack Query v5 for all client-side reads and writes. queryOptions/mutationOptions factories, query key design, Next.js App Router prefetch + hydration, mutations, invalidation, and optimistic updates. Use whenever a component reads data, writes data, or a cache goes stale.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: