Productivity

Build AI-powered software with TypeSafe's Jev, called through OpenRouter with an OpenRouter API key. TypeSafe provides small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.

Create, restructure, review, audit, or fact-check Markdown documentation and module READMEs using audience-first hierarchy, one home per fact, tutorial/reference separation, progressive user-to-developer detail, executed-operation fact-checking, and the slop checklist. Use for new or revised docs, docs-tree organization, documentation-quality audits, and bilingual documentation structure.

Open this for a long or multi-stage task with the context-editor mod: when to open and close stages, how to compress a finished block, the optimization mark, the telemetry, and what "Later, your context_…" or [context-editor] rows mean.

让 agent 吸取教训：踩过的坑写进硬盘，下次不再踩。在开始一个非平凡任务前调用，用 `mem` 查这类任务以前的决策和坑；在犯错被纠正、查明一个问题的原因、或做出一个决定之后调用，用 `mem add` + `mem build` 把教训沉淀下来。Use before starting a task to look up past lessons, and after a mistake, correction, or decision to record the lesson.

Connect to and operate SRE Agent (sreagent.app) from an AI coding agent. Covers connecting the MCP server (https://sreagent.app/api/mcp) with an API key or personal token, which of its 294 tools to call and in what order, destructive-call rules (confirm), the fix handoff loop (get_fix_brief, report_fix_result), plan gates and rate limits, and the REST configuration API, inbound webhooks and Terraform export. Use when the task mentions SRE Agent, alerts, investigations, runbooks, SLOs, on-call, self-healing or a fix handoff on that platform.

Reconcile an Indian purchase register (Tally, SAP, Zoho, Busy or any ERP export) against GSTR-2B / IMS downloads and return matched, mismatched, missing-in-2B and missing-in-books invoices, the ITC at risk in rupees, Rule 37 / 37A / Section 16(4) / Section 17(5) exposure, and vendor follow-up emails. Ends with a CLAIM / CLAIM-WITH-HOLD / DO-NOT-FILE verdict for the GSTR-3B. Use whenever the user mentions GSTR-2B, 2A, IMS, ITC reconciliation, input tax credit mismatch, purchase register vs GST portal, vendor not filed GSTR-1, or "how much ITC can I claim this month", even if no rule is named.

Work in a fold project. Use it for tasks, workspaces, proposals, reviews, requests and messages: register an agent, find and claim tasks, edit files in a task workspace, open and review proposals, integrate them, turn requests into tasks, and read and send messages through the fold MCP tools.

>- Read Jira issues, links, comments and the issue XML, and read Confluence pages (search, body, diff a local file against a page), via the Atlassian REST token. Read-only. Use when a ticket's live status, links or comments are needed, to export a ticket's XML into its data/changes/<ticket>/ folder, or to compare a local doc with its Confluence page.

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.

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.

>- 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.

>- 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".

>- 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.

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

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.