This skill should be used when the user asks to "clear the board", "reset the guild", "start fresh", "wipe the board", "clear all tasks", "reset the board", or wants to remove all current work from the guild board and start over.

The most valuable understanding lives where credible sources **disagree**. Consensus is comfortable; contradiction is where the real questions are — and the angle nobody covered is often the gap in the entire field. This skill maps disagreement, agreement, and blind spots across any set of viewpoi

This skill should be used when the user says "end session", "wrap up", "I'm done for today", "close the session", "session complete", "log off", "signing off", "finish the session", "that's it for today", "done for now", "calling it a day", "let's wrap up", "save the session", "session summary", or any phrase indicating they are ending or wrapping up their current work session. Spawns the session-tracker:logger agent to record the session.

**Simon Sinek, *Start With Why* (2009).** "People don't buy *what* you do; they buy *why* you do it." Most messages start at the outside of the circle — *What* we make — and never reach the center. Inspiring ones start at the center and work out: **Why → How → What.**

This skill should be used when the user asks to "list request monitoring", "show monitoring jobs", "what monitoring is running", "show active schedules", "list cron jobs", or "what's scheduled". Lists all active request monitoring cron jobs in the current session.

This skill should be used when the user asks to "add a requirement", "new requirement", "I need a feature", "add to the guild", "create requirement", "queue a feature", "I want to build", or wants to add a new work item to the guild board. Creates a requirement stub and a product-owner task to gather the full details.

**Barbara Minto (McKinsey).** Busy decision-makers don't want your reasoning journey — they want the conclusion, then the support if they choose to dig. So invert the natural order: **state the answer first, then the grouped arguments, then the data underneath.** Ideas form a pyramid where every l

Pre-loaded QA discipline for the qa-strategist and qa-tester agents. Covers the five QA pillars (validation over verification, disconfirmation, empiricism, the oracle problem, risk-based triage), the hybrid oracle rule for testing existing products, the layered oracle resolution order, the what-if input/state/sequence catalog, and the exploration-vs-automation distinction. Load this skill before planning or running any QA pass. Trigger phrases include "qa mindset", "what-if testing", "test strategy", "oracle", "exploratory testing", "regression strategy".

This skill should be used when the user asks to "start request monitoring", "monitor requests", "watch requests", "start watching for requests", "auto-process requests", "check requests every hour", or "start the orchestrator on a schedule". Schedules the Project Orchestrator to automatically check requests/todo/ every hour and process any pending request files.

This skill should be used when the user asks to "stop request monitoring", "stop watching requests", "cancel request monitoring", "stop the orchestrator schedule", or "stop-request-monitoring {job-id}". Cancels the hourly request monitoring cron job that was started by start-request-monitoring.

Use this skill when the user wants deep, PhD-level, multi-perspective research on a topic and says things like "storm research <topic>", "run STORM on <topic>", "deep research <topic>", "research <topic> from every angle", "multi-perspective deep dive", "give me a PhD-level briefing on <topic>", "research <topic> properly", "I need to really understand <topic>", or "brief me on <topic> before I decide/invest/write/present". Orchestrates five expert persona agents, a contradiction map, a synthesized cited briefing, and an adversarial peer review. Inspired by Stanford's STORM method.

Most communication fails not because the idea is weak but because it is delivered in the wrong shape. A board wants the answer first; a team wants a reason to care; a customer wants to be the hero. **This skill diagnoses the situation, picks the framework that fits, and drafts the message in it** â€

Pre-loaded Svelte 5 / SvelteKit best practices for the developer-svelte agent. Covers state management strategies, performance optimization, accessibility, SEO, TypeScript usage, testing (vitest + playwright), and error handling. Load alongside the other svelte-* skills before implementing anything non-trivial. Trigger phrases include "svelte best practices", "svelte performance", "svelte accessibility", "svelte typescript", "svelte testing", "sveltekit seo", "sveltekit error handling".

This skill should be used when the user says "check svelte env vars", "check environment variables", "validate env vars", "check env var patterns", "audit environment variables", "audit env vars", "check SvelteKit env", "svelte env check", or any phrase asking to audit or validate SvelteKit environment variable usage patterns.

**Emma Coats, former Pixar storyboard artist (rule #4 of her "22 Rules of Storytelling").** Every Pixar film hangs on the same skeleton — a stable world, a change that upends it, escalating consequences, and a new normal. It's the most natural shape for any story of *transformation*.

This skill should be used when the user reports an error, bug, or unexpected behavior and wants it diagnosed and fixed. Trigger on phrases like "check this error", "check this bug", "here's an error", "here's a bug", "I have an error", "I have a bug", "found a bug", "got an error", "debug this", "this is broken", "fix this error", "verify and fix", or any message that includes a stack trace or error output. Runs a structured workflow: gather context, investigate configured log/code sources, report root cause with ranked solutions, then apply a test-driven fix.