Undertone0809

Use when the user asks how Rudder works; needs current Rudder docs, exact behavior, commands, contracts, APIs, or source evidence; asks to create, hire, or configure Rudder agents; or asks to scaffold, develop, or verify Rudder plugins. For explicit creation…

Use when inspecting, preparing, executing, recovering, or verifying Rudder releases across npm, GitHub Releases, Desktop assets, tags, dist-tags, changelogs, install smoke, stable/canary promotion, rollback, and release workflow failures. Use for both…

Use for independent review of Rudder implementations, UI workflows, proposals, agent work, or final handoffs. Judges first-principles intent, raw-request and correction adherence, functional trust, adversarial risk, product taste, and evidence integrity;…

Use for Rudder's root-level delivery lifecycle when work spans implementation, review, black-box acceptance, integration, or handoff and candidate/source/runtime/data identity can drift. It captures raw intent and corrections, freezes an acceptance packet,…

Use when Rudder Desktop or its development shell will not launch, gets stuck at login/account gate, has pending device approval or local-session exchange, returns 401 during update, points at the wrong instance, hits migration-journal/schema-history…

Create and iteratively improve local web products from natural-language requests, then prepare them to run as Rudder Apps. Use Rudder's maintained scaffold for new websites and preserve the existing stack for Next.js, React, Vue, Astro, SvelteKit, Nuxt, and…

Use when creating realistic Rudder mock, demo, seed, fixture, screenshot, test, CSV, JSON, SQL, TypeScript, or scenario data for local development, demos, screenshots, product explanations, and workflow validation.

Gather and cite evidence before reaching a conclusion.

Use when the user wants to stress-test, review, or rewrite a public post, tweet, thread, launch announcement, founder update, or product narrative through multiple critical audience perspectives. Run an independent multi-agent editorial room that separates…

Use when the user wants to set up or run a B2B cold email outreach workflow: onboard a new campaign, explain the workflow to a first-time user, decide where campaign state should live, research target companies and decision makers, draft personalized…

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or…

Query, summarize, export, create, and edit a user's flomo memos through local desktop auth and the flomo API, without Chrome UI automation. Use for fast memo lookup, tag filtering, markdown export, attachment/image metadata reads, lightweight memo creation,…

Use when the user asks for Claude Code /insights-like reporting for Codex, wants to analyze recent Codex sessions, audit usage patterns, find repeated workflows, identify friction points, or decide which skills/automations should be created or improved from…

Generate technical documentation in the style of garrytan/gstack - featuring hook-first narrative, reasoning transparency, specific metrics, and conversational tone. Use when user asks for "gstack style README", detailed technical docs with reasoning, or…

Use for desktop or system screenshots when the user wants an app, window, region, or whole-desktop capture and no tool-specific capture fits. Prefer app/window capture over full-screen for desktop apps.

Analyze the user through their flomo notes using guided lenses such as overview, ACT, compounding flywheel, action guide, blind spots, and MBTI-style pattern reading. Use this whenever the user asks what their flomo notes say about them, wants self-analysis…

Analyze the user through their flomo notes using guided lenses such as overview, ACT, compounding flywheel, action guide, blind spots, and MBTI-style pattern reading. Use this whenever the user asks what their flomo notes say about them, wants self-analysis…

Query, summarize, export, create, and edit a user's flomo memos through local desktop auth and the flomo API, without Chrome UI automation. Use when the user wants fast memo lookup, tag filtering, markdown export, lightweight memo creation, or direct text…

Convert flomo memos from local desktop auth/API into grouped Markdown files for AI/NotebookLM reading, plus human-readable Markdown tag statistics with tree totals. Use when a user asks to export flomo notes to Markdown, split memos by month/quarter/year,…

Query, insert, edit, and delete user's flomo memos through the flomo Web UI using Chrome MCP tools (no official API required). flomo is also a user's first-person context source for inferring recent state, active concerns, and value signals from recent memos…

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or…

Build and revise reusable AI skills for local agents. Use this when the user says: create a skill, rewrite SKILL.md, or benchmark a skill description.