The single ROUTER for every data need. Load this skill BEFORE any backtest, data-fetch, or research task to pick the best available source/tool, honour auth (env) requirements, and avoid ban-risk providers.

Unified Minions skill for both deterministic shell jobs and LLM subagent orchestration. Replaces the older `gbrain-jobs` routing intent. Use when: submitting gbrain jobs, shell/background tasks, spawning subagents, checking progress, steering running work, pausing/resuming, parallel fan-out. One durable, observable, steerable queue interface. Also carries the durable-execution doctrine for any operation expected to exceed ~2 minutes: capability ladder, deadman checks that verify the result was reported, and content-addressed stage checkpoints for expensive pipelines.

Design and author DeepTutor skills (SKILL.md packages). Use when the user wants to create a new skill, improve an existing skill, or asks how skills work.

Run initial NanoClaw setup. Use when user wants to install NanoClaw, configure it, or go through first-time setup. Triggers on "setup", "install", "configure nanoclaw", or first-time setup requests.

Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".

Build a complete Nature-style Chinese PPTX presentation from a scientific paper, preprint, PDF, article text, figure legends, or reading notes. Use for journal club, group meeting, thesis seminar, paper sharing, conference or defense decks, and Chinese requests such as 论文做PPT、论文汇报、组会PPT、文献汇报、学术汇报、做幻灯片、读书报告PPT. It classifies paper type, builds an evidence-led story, selects key figures, writes Chinese slide content and speaker notes, creates the actual .pptx, and runs corrective QA for complete figure crops, stable alignment, text overflow, and de-templated Chinese academic expression. Also trigger when improving weak paper-to-PPT output with cropped figures, loose alignment, obvious AI-style wording, or heavy manual rework.

Reference for `just`, the command runner. Use when working in a project with a `justfile` or when the user mentions `just` or `justfile`.

Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling, triggers, ad blockers, and quota/billing scenarios.

Manage PostHog subscriptions — scheduled email, Slack, or webhook deliveries of insight or dashboard snapshots, optionally with an AI-written summary attached to each delivery. Use when the user wants to subscribe to an insight or dashboard, get an AI summary attached to those deliveries, check existing subscriptions, change delivery frequency, add or remove recipients, or stop receiving updates.

Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.

Run ClickHouse `system.query_log` analysis via the internal Metabase API. Use when investigating slow queries, materialization candidates, per-team query performance, ClickHouse cost or memory issues, or any system.query_log question. Covers prod-us and prod-eu, SSO-gated cookie auth via `hogli`, and ready-to-run query patterns.

Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production. Use when investigating latency, event loss, Kafka backpressure, Redis issues, rate limiting, Envoy proxy issues, or any capture health question. Covers prod-us and prod-eu environments.

Build or refactor a Tool-channel provider (PagerDuty, Opsgenie, future incident/alerting tools) to be endpoint-routed: per-subscriber secrets encrypted on the channel endpoint resource, a stateless provider that resolves routing from channelData at send time, SKIPPED steps when no endpoint exists, and the full API/worker/dashboard/docs/playground surface. Starts with a mandatory provider-docs discovery gate. Use when refactoring Opsgenie to the PagerDuty model, adding a new tool provider, or touching pagerduty_service channel endpoints.

Add a new chat channel's layer-1 setup guide — the in-dashboard <Channel>SetupGuide that walks a developer through connecting the channel itself (create app/bot → save credentials → install/verify → send first message) with live connection detection — in apps/dashboard, following the existing Slack, MS Teams, and Telegram guides. Use when a new agent channel needs its numbered setup stepper, credential drawer wiring, and connectedAt polling under components/agents.

Build a new channel Connect button (e.g. WhatsApp, Discord, LINE) in @novu/js and @novu/react following the existing SlackConnectButton, MsTeamsConnectButton, and TelegramConnectButton pattern. Use when adding connect/disconnect UI for a new chat channel/provider to the SDK — covering the SolidJS core component, the React wrapper, the channelConnections (OAuth) vs channelEndpoints (deep-link) data layer, the component registry, and package exports.

Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from descriptions, background music, soundtrack generation, voice cloning, or any audio synthesis task.

Use when working on, reviewing, or extending GitNexus's CFG/taint/PDG subsystem (the `--pdg` layers), or when reasoning about source→sink data-flow findings. Examples: "How does taint analysis work here?", "Why didn't explain find this flow?", "Add a new sink/source", "Review the interprocedural taint code".

Track Airflow Improvement Proposal (AIP) implementation progress by comparing Confluence specs against codebase evidence. Use when asked to assess, report on, or compare AIP status.

Test a half-formed idea in a questioning conversation, with different personas probing its weak points, until the user can act on it or drop it with confidence. Optionally writes a short brief for planning skills to build on. Use when the user says 'forge an idea', 'pressure-test this idea', 'stress-test my thinking', or 'harden this idea'

Add an interactive demo to the Remotion documentation. Use when creating a new <Demo> component for docs pages.