Productivity

>- Ships an app clone live on the user's own domain: a preflight gate (tests green, parity must-haves done, rebrand sweep clean, listing linted, legal pages up), production database and env vars, the host, DNS records for the domain and for email, Stripe live mode, OAuth redirects, monitoring, and mobile builds to TestFlight and Play. Use when the user says "deploy it", "ship it", "put it live", "connect my domain", "go to production", "publish the app", or after /replica-launch.

>- Builds the backend of an app clone: auth, database migrations and access rules, payments with Stripe, email, background jobs and third-party integrations through official APIs only, plus a security checklist. Use when the user says "add login", "set up auth", "wire up the database", "add payments", "connect Stripe", "add Google Calendar", "send emails", "backend for my clone", or when /replica-build is running on fake data.

Use when a change needs an independent code review before it moves on - a finished task, a feature branch, a pull request, or work-in-progress changes since a given ref - in any programming language. Pins the exact diff, gathers intent and constraints, and dispatches a read-only reviewer that returns separate verdicts and evidence-backed findings.

Turn a pasted task or ticket description into a concrete implementation plan for this repo.

Work with Projects in the Obsidian PARA vault and their pairs in the task app — list the active projects, create a project (folder plus a project in the task app), summarize where a project stands, or add a task to a project in the task app (Todoist, for example). Use when the user says "list projects", "show projects", "what am I working on", "create a project", "new project", "project overview", "project status", "add a task", "какие проекты", "список проектов", "покажи проекты", "что у меня в работе", "заведи проект", "новый проект", "саммари по проекту", "обзор проекта", "что по проекту", "статус проекта", "где я по проекту", "добавь задачу", "заведи задачу".

Work with Archive in the Obsidian PARA vault — put a finished or abandoned project (folder and its project in the task app, such as Todoist) or a note into the archive, list what is already there, or restore something back into an active folder. Use when the user says "archive this", "move to archive", "close the project", "what is in the archive", "show the archive", "restore from the archive", "заархивируй", "перенеси в архив", "закрой проект", "что в архиве", "покажи архив", "верни из архива", "восстанови проект".

Work with the inbox of the PARA vault, which lives in the task app's inbox — capture a raw thought into it, list what is sitting there unprocessed, or process captures one by one into their proper PARA folder. Use when the user wants to capture a note, mentions their task app's inbox (Todoist «Входящие», for example), or says "capture this", "add to the inbox", "what is in the inbox", "process the inbox", "запиши", "закинь в инбокс", "что в инбоксе", "покажи инбокс", "разбери инбокс", "разгреби инбокс".

Save something to the right place in the user's AI file system. Use when they say "remember this", "save that", "note that I prefer...", "from now on...", run /ai-file-system:remember, or at the end of a task when something lasting was learned.

Build the user's AI file system, one organized folder of plain-text files (AGENTS.md, CLAUDE.md, CURRENT.md, context files and workspaces) that Claude and Codex read at the start of every task. Use when someone says "set up my file system", "build my OS", "set up my AI folder", "organize my AI", or runs /ai-file-system:setup. Interviews them, optionally imports their ChatGPT or Claude history, builds and verifies the files, and shows them how to use it every day.

Read-only root-cause investigation for one explicitly assigned GitHub Issue; returns a durable diagnosis to the Issue and Scheduler, without editing code, opening a PR, reviewing a PR, or creating tasks.

Plan and run essential manual regression tests for the current branch against an already running application stack. Use when asked to verify affected application workflows end to end.

Orchestrates end-to-end delivery of a task-breakdown backlog with parallel worker agents that run implement-task and spike-task, then shepherds every PR to merge on main - stacking PRs on unmerged dependencies, addressing worthwhile review comments and CI failures, restacking branches as PRs merge, gating work behind spike decisions, and keeping the tracker and local tasks file in sync.

Implements one ticket (from the team's tracker such as Linear, or a local tasks file) as the smallest complete change, test-first from its acceptance criteria, and opens a PR for review; can also address review feedback on that PR. Use only when a specific ticket (such as ENG-123 or T-04) is named for implementation, by the user or by the deliver-project orchestrator.

知识蒸馏闭环工作流：把一本书/长视频/播客蒸馏成可执行 Skill（生成），画出房规 SVG 图（出图），再做逐字回源审计与四闸判态（验证），全绿才编译交付。Use when the user says "拆书"/"蒸馏一本书"/"把这本书做成 skill"/"蒸馏后审计"/"distill this book into skills"/"audit the distilled skills"，或要对已有 cangjie 产物跑回源审计/配图。NOT for 单纯书摘要、读后感、作者人设扮演。

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Run Claude Code development through implementation, checks and optional Codex review. Use when Claude is asked to implement a feature, fix a bug, refactor, or change configuration. Make sure to use this skill for every authorized development task, even outside another skill. Excludes planning-only, explanation and review-only requests.

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.