Productivity

Deploys, runs and troubleshoots the Claude Memory Sync server (Node + Postgres on Railway), an encrypted version store with concurrency control that holds Claude Code configuration from several machines. Use when the user asks to deploy or update the memory sync server, authorize or revoke a machine (CLIENT_PUBLIC_KEYS), check database size or history, reset the history (e.g. when rotating the SYNC_KEY), or investigate 401/409/413/415/429/503 errors seen by clients.

>- Draft or create GitHub Task issues using the repo's task template. Use when the user asks for a task issue, chore, or concrete work item that is not a bug or full feature, or when type is task in issue frontmatter.

Faz deploy, opera e diagnostica o server do Claude Memory Sync (Node + Postgres na Railway), um armazém de versões cifradas com controle de concorrência que guarda a configuração do Claude Code de vários PCs. Use quando o usuário pedir para subir ou atualizar o server do memory sync, autorizar ou revogar um PC (CLIENT_PUBLIC_KEYS), ver o tamanho ou o histórico do banco, zerar o histórico (ex.: ao trocar a SYNC_KEY), ou investigar erros 401/409/413/415/429/503 vistos pelos clientes.

>- Plan and create GitHub subtasks linked to a parent issue. Use when breaking down an issue, generating subtask markdown, or creating child issues with gh and "Related to #N" links.

Moves an in-flight project's agent-skills working files (SPEC.md, tasks/plan.md, tasks/todo.md, CONSTRAINTS.md, …) from the upstream root paths to the team paths in .claude-work/. Use when a project started before agent-skills-jksim was installed, or when root working files and .claude-work/ both exist.

把业务流程渲染成 Mermaid 源码 + 自包含交互式 HTML 流程图（零依赖、纯离线，不请求任何 CDN）。用于把用户口述或文档里的流程、SOP、生产链路、复盘时间线画成能点的图：节点可点开看时间/负责人/说明，支持搜索筛选、明暗主题、导出 SVG/PNG，并同时产出可粘进飞书/语雀/GitHub 的 Mermaid 代码。当用户说"把流程画出来/画个流程图/可视化工作流/整理成流程"时使用。

Create or improve a reusable personal workflow skill when repeated work needs specific instructions beyond ordinary model knowledge.

Makes the most expensive model in a session the senior decision-maker, keeping its reasoning for intent, architecture, decomposition, tradeoffs, final review, and synthesis while cheaper agents handle discovery, implementation, tests, logs, and verification. Use when the active agent is Fable or another top-tier model, or when asked to "act as chief agent", "delegate the grunt work", or "save the expensive model for decisions".

Inspects a project's discovered agent instructions (AGENTS.md, CLAUDE.md, GEMINI.md) and skill definitions for static wiring problems, without loading, changing, or enabling them, and reports which installed skills are rarely or never called in local session logs. Use when asked "why isn't my skill loading", "check my agent setup", "diagnose skill discovery", "audit AGENTS.md and skills", or "which skills do I never use".

Use when the user invokes $amap-maps-mcp, mentions Amap Maps, or asks for supported Amap Maps workflows.

>- Install and drive Cursor-Chrome (local agent Chromium). Use when the user says "install this", "hey install this", "set this up", pastes github.com/T3ckfr3ak1/cursor-chrome-public, or says "use cursor chrome" / "cursor-chrome" / agent browser / handoff / Play Console upload. Prefer Cursor-Chrome over IDE browser. Install: INSTALL.md + npm run install:agent. Drive: THREAD-PROTOCOL.md beside this skill. Anti-secrecy: agents cannot hide/minimize (403); humans park via taskbar/tray only.

Record DION meetings on Windows, transcribe recordings locally, and create Russian Markdown minutes. Use for meeting recording, stopping recording and processing existing recordings.

Examines raw stakeholder input (transcripts, briefs, emails, feature ideas) into epics and candidate user stories published to the tracker; when scope exceeds a single session, opens a decision map and resolves one decision per session.

Configures a workspace for refinement workflows: operating mode (with or without code), local markdown tracker, publishing conventions, and agent instructions block in AGENTS.md or CLAUDE.md. Run once per workspace.

Have Grok Bot do work on its cloud computer (it operates the desktop like a person, by screen, mouse and keyboard) while Claude decides each next step, starting Grok Bot if it isn't running. Use when the user wants Grok Bot to do something, asks about a task sent to Grok Bot, or asks to set up, check or repair Claude2GrokBot.

Use when a Claude2GrokBot wake request starts you (webhook body type "claude2grokbot.wake") or the user says "check Claude2GrokBot": claim the tasks Claude queued, do them, and upload the results.

Run the full pre-PR checklist (make check, secret scan, docs, diff review) before opening or updating a pull request. Use before creating a PR or when asked if work is ready.

Use when an open-ended task should be raised from task-level to outcome-level, when results must be verified by something other than the model that produced them, or when a crew of tool-bearing subagents is needed. Compiles the request into <invariant + falsifiable verifier + environment manifest>, runs an outside-judge ladder with per-claim verdicts, and makes subagents do the work rather than role-play it. Skip for tight specs with fixed acceptance criteria, trivial tasks, or crunch situations - adding harder goals there only adds risk.

把杂乱的会议记录、语音转录文字整理成结构化会议纪要。当用户发来会议记录、聊天记录或转录文本并说"整理成纪要"时使用。

Capture architectural decisions as numbered ADR markdown files in docs/adr/ with context, alternatives considered, consequences, and an index README. Use when the user says 'record this decision' or 'ADR this', chooses between frameworks or databases, discusses trade-offs, or asks why the codebase is shaped this way.

>- Use this when choosing a tool, library, framework, CLI, MCP server, or agent skill for a task: first look in the user's own GitHub stars and in official vendor skill catalogs, then recommend well-known, actively maintained options with reasons.

Analyzes Android apps to identify key user workflows for AppFunctions such as creating a note, playing media, or sending an automated or AI agent triggered message, voice commands, or system shortcuts, without needing to open the app UI. Generates Kotlin code to expose these workflows to the Android system, allowing agents to discover and execute them on-device. Also refines KDoc documentation to ensure AI agents correctly understand and use the provided functionality.

Scan a Go project structure and generate/update README.md with package overviews, dependencies, and usage notes.

End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for large multi-phase projects, prefer the GSD workflow and use this inside phases.