Skill Claude CodeCodex
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…
Skill Claude CodeCodex
This skill should be used when the user wants quality assurance on the product itself — "QA the product", "QA the checkout flow", "run a QA pass", "build comprehensive e2e tests", "write regression tests", "test the running app", "what-if testing", or any request to empirically test the product and author end-to-end…
Skill Claude CodeCodex
This skill should be used when the user asks to "cut a release", "release the guild", "ship it", "create a release", "tag a version", "publish a release", "guild release", or wants to finalize completed requirements into a versioned release. Renames CHANGELOG Unreleased to a version, archives completed REQs, and…
Skill Claude CodeCodex
Pre-loaded advanced Svelte 5 / SvelteKit techniques for the developer-svelte agent. Covers attachments ({@attach}), actions (use:), transitions and animations, the motion module, custom elements, packaging libraries, server hooks, remote functions, service workers, shallow routing, and view transitions. Load when the…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
Pre-loaded SvelteKit knowledge for the developer-svelte agent. Covers project structure, file-based routing (+page, +layout, +server, +error), load functions (universal vs server), form actions, page options (prerender / ssr / csr), building for production, and deployment via adapters (auto, node, static, vercel…
Skill Claude CodeCodex
Pre-loaded Svelte 5 core knowledge for the developer-svelte agent. Covers the component model, runes ($state, $derived, $effect, $props, $bindable), basic markup, control flow, snippets, bindings, scoped styles, lifecycle, and context. Load this skill before writing or editing any .svelte, .svelte.ts, or .svelte.js…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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…
Plugin Claude Code
PhD-level multi-perspective research inspired by Stanford's STORM. The 'storm research' skill orchestrates five expert persona agents (practitioner, skeptic, economist, historian, academic), maps their contradictions, synthesizes a cited briefing, and red-teams the result. Say 'storm research ' to start.
Agent
The peer-reviewed-evidence lens for STORM research. Use when you need what the actual studies and data show — including conflicting findings, effect sizes, and the quality of the evidence base. Spawned in parallel by the storm-research and multi-perspective-scan skills, one of five expert personas. Writes its analysis…
Agent
STORM Phase 2 analyst. Reads multiple perspective analyses (or any set of sources/viewpoints) and maps where they disagree, where they agree, and what none of them addressed. Surfaces the contradictions where real understanding lives. Spawned by the storm-research and contradiction-map skills. Writes…
Agent
The incentives-and-money lens for STORM research. Use when you need to follow the money: who profits, who pays, what incentives are misaligned, what the market structure rewards. Spawned in parallel by the storm-research and multi-perspective-scan skills, one of five expert personas. Writes its analysis to the run…
Agent
The long-memory, pattern-and-precedent lens for STORM research. Use when you need historical parallels, prior cycles, and "we have seen this before" context that the present-focused perspectives miss. Spawned in parallel by the storm-research and multi-perspective-scan skills, one of five expert personas. Writes its…
Agent
STORM Phase 4 auditor. Performs a rigorous, adversarial self-review of a research briefing and its supporting perspectives — fact-checking and hallucination audit, bias detection, completeness check, fairness of contradiction handling, and actionability. Closes STORM's known no-self-critique weakness. Spawned by the…
Agent
The hands-on operator's lens for STORM research. Use when you need the view of someone who works with a topic every day — what actually works in practice vs. theory, the failure modes nobody documents, the tacit knowledge. Spawned in parallel by the storm-research and multi-perspective-scan skills, one of five expert…
Agent
The adversarial critic's lens for STORM research. Use when you need someone highly critical of the mainstream view to surface flaws, overclaims, hidden problems, and failure cases. Spawned in parallel by the storm-research and multi-perspective-scan skills, one of five expert personas. Writes its analysis to the run…
Agent
STORM Phase 3 analyst. Reads the multi-perspective analyses and the contradiction map, then produces a single coherent, cited research briefing that no individual perspective could write: synthesized narrative, explicit handling of contradictions, reliability ranking, open questions, and concrete recommendations.…
Skill Claude CodeCodex
Use this skill when the user wants to find where sources, viewpoints, or perspectives disagree — phrases like "contradiction map", "where do these disagree", "map the conflicts", "find the disagreements", "where do the experts clash", "compare these viewpoints", "what do they agree on", or "find the gaps nobody…
Skill Claude CodeCodex
Use this skill when the user wants a fast multi-angle read of a topic without the full STORM pipeline — phrases like "multi-perspective scan", "give me 5 perspectives on ", "analyze from multiple angles", "what would different experts say about ", "perspective scan", "5 expert views", "steelman the different takes on…
Skill Claude CodeCodex
Use this skill when the user wants to rigorously audit a piece of research, a briefing, a report, or an argument before relying on it — phrases like "peer review this", "self-critique this", "audit my research", "red team this report", "fact-check this", "find the weak claims", "is this trustworthy", "grade this…
Skill Claude CodeCodex
Use this skill when the user wants deep, PhD-level, multi-perspective research on a topic and says things like "storm research ", "run STORM on ", "deep research ", "research from every angle", "multi-perspective deep dive", "give me a PhD-level briefing on ", "research properly", "I need to really understand ", or…
Plugin Claude Code
A requirements to implementation workflow for software development projects with a breakdown of implementation into phases.
Skill Claude CodeCodex
Reference guide for classifying development tasks into the 8-phase clean architecture structure (Foundational → Models → Services → Data → Rules → State Management → UI → Tests). Use when you need to determine which architectural phase a task belongs to.