serejaris

Break a plan, spec, or PRD into independently-grabbable task files using tracer-bullet vertical slices.

Turn the current conversation into a PRD file in the project folder — no interview, just synthesis of what you've already discussed.

Фейбл руки-агенты — ручной режим оркестрации, где Fable не пишет код, а пишет спеки в тела GH issues и раздаёт готовые задачи рукам: кодинг, код-ревью, gh-операции, CLI-механика, DoD-верификация и укладка файлов — Codex; разведка, чтение и скауты — Grok-воркеры через Orca. Вызывается пользователем явно, не моделью.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Use when you want several genuinely different design directions to choose from instead of one design you will iterate on — a page or UI redesign, a hero, a landing, a thumbnail layout — or a live/stream design bake-off where an audience votes. Triggers on "дай варианты дизайна", "несколько вариантов на выбор", "редизайн", "design options", "design bake-off", "/parallel-design-variants".

Use when need to sync session work into GitHub issues OR query status of an existing track across repos. Two modes — write (end-of-session sync: find issues, update body, work-record comment, parent epic + W-label + Project placement) and read (status lookup across repos with parent/W-label/Project health). Triggers on "/manager", "sync session", "обнови issues", "синкни сессию", "зафиксируй прогресс", "статус задачи", "что по <track>", "есть ли issue по", "track status", "what about <track>".

Use when capturing ONE new idea the user voices and wants recorded — "save this idea", "I have an idea", "log this idea", "/idea", "idea: ...". Creates a provenance-tracked folder (one folder per idea) in your ideas repo, dedups against an index, optionally mirrors to a GitHub Project view filtered by label:idea. NOT for mining ideas out of transcripts/meetings (use a dedicated extraction skill) and NOT for dated work tasks (use an issue tracker / the manager skill). Triggers also in Russian: «запиши идею», «у меня идея», «зафиксируй идею».

Проводит структурированный сеанс дивергенции вокруг конкретной продуктовой проблемы или возможности. Встроены SCAMPER (7 ракурсов), 5 Whys для поиска корневой причины, кросс-доменное вдохновение, ограничивающие инновации, обратный брейншторм и матрица Impact/Effort для отбора. На выходе — ≥10 идей с детально проработанным Top-3. User-invoked only — do NOT auto-trigger. Triggers on /pm-brainstorm, "идеи для продукта", "продуктовый брейншторм", "дивергенция идей", "How Might We", "SCAMPER", "product brainstorm", "feature ideas".

Use when transitioning from retro to weekly plan, prioritizing backlog, choosing outcomes for the week, or when user says "план на неделю", "планирование", "W13 plan", "outcomes", "приоритизация". Runs after weekly-retro skill.

Use when preparing for, running, or closing a live meeting with an AI assistant dashboard. Triggers on "meeting copilot", "live copilot", "prepare for a call", "update copilot", "close the session", or requests to turn transcript chunks into meeting questions, topic maps, decisions, and follow-ups.

Use when conducting weekly retrospective, reviewing past week, or when user says "retro", "weekly retro", "week review". Triggers at end of week or start of new week.

Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on "/ris-draft", "сделай blueprint", "технический чертёж", "архитектурная схема", "инженерная схема", "blueprint diagram", "engineering blueprint", "technical spec sheet", "architecture diagram", "system flow diagram".

Use when ranking a list of requirements, features, or backlog items using RICE / ICE / MoSCoW / Kano. Built-in decision tree picks the right framework based on data availability and decision context. Output is a transparent matrix, 2×2 Impact/Effort quadrant, and a Sprint allocation proposal. User-invoked only — do NOT auto-trigger. Triggers on "/ris-prioritize", "приоритизация", "ранжируй бэклог", "RICE-анализ", "prioritize requirements", "RICE", "ICE", "MoSCoW", "Kano", "rank backlog".

Use when need to sync session work into GitHub issues OR query status of an existing track across repos. Two modes — write (end-of-session sync: find issues, update, create with parent epic + W-label) and read (status lookup across repos). Triggers on "/ris-manager", "sync session", "обнови issues", "синкни сессию", "зафиксируй прогресс", "статус задачи", "что по <track>", "есть ли issue по", "track status", "what about <track>".

Use when managing Paperclip AI agent companies - creating tasks, managing agents, approving hires, running heartbeats, or any Paperclip control-plane operations via CLI or REST API. Triggers on "paperclip", "задача агенту", "одобри найм", "heartbeat", "запусти агента".

Use when auditing a product, business, or project ecosystem — analyzing data sources, decision loops, bottlenecks, and implementation contours. Triggers on "аудит продукта", "product audit", "data audit", "аудит данных", "аудит бизнеса", "проанализируй экосистему", "аудит систем".

Use when tuning numbers in majesty-clone, changing sim/data.js, or investigating balance complaints (class dies too fast, economy starves, game too easy/hard, win unreachable)

Use when adding or changing game mechanics in majesty-clone (new hero class, building, monster, flag type, behavior) — before writing any code for the feature

Use when verifying that a majesty-clone feature or fix actually works — after any sim/render/UI change, before commit or deploy

Use when an experiment in this repo is done and the user asks to post about it to the vibecoders chat — "запость в чат", "отчёт в вайбкодеры", "расскажи в чате что сделал", "отправь в вайбкодеров". Covers both the voice (микроотчёт нейрочела) and the send mechanics (tg-telethon userbot).

Use when given a claude.ai/chat/<uuid> link and asked to get, fix, or deploy its code/artifact, or when any data from the user's logged-in claude.ai session is needed (no public API exists for user chats). Also covers "artifact had an error" requests — the error is often the artifact sandbox, not the code.

Use when converting Markdown documents, reports, or any text content into a Telegram Rich Message for delivery via a bot. Triggers: "send markdown to Telegram", "convert doc to rich message", "publish report to bot", "format markdown for sendRichMessage", "telegram rich message from file". Produces an InputRichMessage JSON object ready for Telegram Bot API 10.1 sendRichMessage.

Use when sending daily or weekly digests, community summaries, status reports, or newsletters through a Telegram bot as one structured rich message instead of a wall of plain text. Triggers: "send weekly digest", "post summary to channel", "newsletter via bot", "community report", "daily status update", "format report as rich message".

Use when sending structured or richly formatted messages from a Telegram bot — tables, section headings, collapsible blocks, photo galleries, maps, math formulas, audio, or streaming AI responses. Also use for understanding rich message types and limits when plain sendMessage with parse_mode HTML/Markdown is not sufficient.

Use when streaming LLM or AI-generated replies to Telegram in real time (ChatGPT-style progressive output in a bot), showing a model thinking indicator, or delivering token-by-token text as an animated rich message draft that finalizes into a permanent message.

Default execution-planning skill for almost any non-trivial repo task. Turns a raw task, feature request, PRD, or project brief into durable execution docs: `plans.md`, `status.md`, and `test-plan.md` (or existing repo equivalents), then proposes execution before starting. Use by default unless the user clearly wants a trivial one-shot answer, pure discussion, or no planning.

Universal blog post pipeline. 7-phase workflow with research, deaification, and deploy. Use when asked to write a blog post, create an article, or produce content for a blog.

Deploy, redeploy, or debug the SubTrack Telegram bot project `serejaris/vibecoding_11` on Railway. Use when the user asks to make the bot work 24/7, fix Railway deploy errors, set Railway variables, diagnose `BOT_TOKEN не найден`, resolve Telegram `Conflict: terminated by other getUpdates request`, or verify the live `@ris_subtrack_bot` runtime.