Claude Skills by HirogaKatageri

This skill should be used when the user asks for "guild status", "board status", "what's the status", "show the board", "what's on the board", "project status", "show guild", "guild board", "what's happening", "brief me", "guild brief", "where are we", "what changed", "what moved since last time", "what should I work on next", or any read-only request for the state of the guild. Narrates a real briefing — direction, what is in flight, the open bugs, which tickets failed and why, the unresolve...

This skill should be used when the user says "check in", "clock in", "standup", "guild check in", "let's get to work", "start working", "continue working", "daily standup", "guild standup", "I'm here", "reporting in", or any phrase indicating they want to begin or resume a guild work session. Acts as the guild orchestrator: opens with the guild brief, runs each requirement's execution graph batch by batch, and puts the two gates in front of the guild master. A read-only status question ("guil...

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.

Use this skill when the user wants to review code changes, verify implementation quality, or check readiness before a PR or deployment. Trigger on phrases like "review my changes", "run comprehensive review", "check all my code", "am I ready for PR", "before I create a PR", "before I merge", "code audit", "quality check", "verify my implementation", "is my feature complete", "run all reviewers", "check if my implementation is complete", "deep code review", "deep review", or any multi-dimensio...

This skill should be used when the user asks to "create a workflow", "generate a workflow", "add a GitHub Actions workflow", "create a CI/CD pipeline", "write a script workflow", "automate a task", "set up automation", or wants to build any kind of automated workflow (GitHub Actions, Python scripts, Node.js scripts, shell scripts, Makefiles, etc.). Interactively gathers goals and configuration, suggests file names, job names, and step names, then generates a complete ready-to-use workflow file.

This skill should be used when the user asks for "the dashboard", "guild dashboard", "open the dashboard", "show me the dashboard", "build the dashboard", "visualize the board", "the roadmap", "show the roadmap", "a visual view of the guild", "the coverage view", "the activity feed", or wants to see the guild's state as a page rather than as text. Queries the warehouse and writes the self-contained .guild/dashboard.html, then opens it — and can optionally publish it as a shareable Artifact link.

This skill should be used when the user says "discuss", "let's discuss", "discuss [topic]", "talk about", "let's talk about", "summarize the context", "what are we working on", "break down the topics", "what subjects do we have", "let's review the context", "recap the conversation", or any phrase asking to analyze and discuss the current context or a specific subject within it.

Deprecated alias — the v4 name for what is now guild:brief. It claims NO natural-language trigger phrases; "guild status", "board status", "what's happening", "project status" and every other status phrasing belong to guild:brief and must route there. Invoke this only when the user explicitly types the old slash command /guild:guild-status.

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. Runs a live 3-way interview between the product-owner, the architect, and the user, places the requirement in the guild's direction (or deliberately leaves it unaffiliated), then writes the requirement, the implementation plan, the developer/test-planner/re...

Pre-loaded QA artifact reference for the qa-strategist and qa-tester agents. Says which QA output is a DATABASE ROW (defects in the `bug` table, quality areas in the `coverage` table) and which stays prose under `.guild/qa/` (charter, missions, session logs, regression manifest) — with the exact SQL and file format for each. Load this skill before writing any QA artifact or filing any bug. Trigger phrases include "qa artifacts", "qa charter", "qa mission", "file a bug", "bug row", "coverage a...

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 st...

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 regression coverage. Seeds the guild's independent QA discipline: a qa-strategist maps the risk surface onto the board as coverage rows, then qa-testers run the app and author Pla...

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, snapshots the completed requirements out of the board into a dated release directory, and creates an annotated git tag. Does not push.

This skill should be used when the user asks to "work a shift", "run unattended", "keep working while I'm away", "guild shift", "take the night shift", "work the board while I'm out", "run autonomously", "keep going without me", "work overnight", "run until you need me", or any request for the guild to keep working with nobody watching. Runs the unattended loop: claim bounties, run segments, commit per completed task, retry once, record every failure — and STOP at the next gate, because a gat...

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 task involves animation, dom integration, library packaging, advanced data flow, or pwa features. Trigger phrases include "svelte transition", "svelte animation", "svelte attachm...

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".

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, cloudflare, netlify). Load this skill before working on any SvelteKit route, server module, or build configuration. Trigger phrases include "sveltekit routing", "+page", "+server", "...

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 file. Trigger phrases include "svelte core", "svelte runes", "svelte 5 component", "svelte state", "svelte derived", "svelte effect", "svelte props", "svelte bind".

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.

This skill should be used when the user asks to "validate the guild", "check the guild", "does this match expectations", "run the expectations", "validate the board", "check the invariants", "verify the board", "did that actually land", "check the board against expectations", or wants to know whether what a skill just did matches what was required. Runs the SQL assertions in docs/expectations.md against the live board — the global invariants by default, a named process's postconditions on req...

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, r...

The guild's warehouse — how to read and write guild data with SQL. Load this before touching anything in the guild database: tasks, requirements, plans, goals, projects, bugs, review findings, work logs, coverage, the execution graph, gates, ticket capabilities, or the event feed. Also load it for the LIBRARY — documentation, decisions and ADRs, how a page relates to the work it describes, what superseded what, and which pages went stale. Also for the board, the brief, bounties, "what's next"...

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 covered". Works on an existing STORM workspace (.storm/{slug}/), on a set of files/documents, or on viewpoints pasted into the conversation. Spawns the contradiction-mapper agent. This...

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 <topic>", "analyze <topic> from multiple angles", "what would different experts say about <topic>", "perspective scan", "5 expert views", "steelman the different takes on <topic>", or "what are the different viewpoints on <topic>". Fans out the five STORM persona agents (practitioner, skeptic, economist, historian, academic) ...

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 research", "what's wrong with this analysis", or "review my briefing for bias". Spawns the peer-reviewer agent to run a fact-check & hallucination audit, bias detection, completeness ...

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 synth...

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.

This skill should be used when the user asks to "create a conventional commit", "generate conventional commits", "generate commit", "commit with conventional format", "group my changes for commits", "make a conventional commit message", or mentions "semantic commits", "commitizen", "commit conventions". Analyzes staged and unstaged changes, groups related modifications, and generates properly formatted conventional commit messages with interactive commit grouping options.

Analyze a master plan file and split it into 8 phase-specific implementation plans organized by feature tracks. Automatically identifies tracks, classifies tasks by phase, scores complexity, and generates detailed phase plan files following clean architecture principles.

Use this skill to structure a message as ABT — And, But, Therefore: setup, tension, resolution in three beats. Best for elevator pitches, one-liners, hooks, openers, and landing a point in under 30 seconds. Triggers on "abt", "and but therefore", "elevator pitch", "one-liner", "give me a hook", "make this punchy", "tighten this to one sentence", or "how do I open this". Turns raw material into a single tight arc: agreement → problem → solution.

Use this skill to structure a message with Simon Sinek's Golden Circle — Why → How → What. Best for rallying a team, framing a brand or mission, launching a company or product with meaning, or any "why we exist" moment. Triggers on "golden circle", "start with why", "help me articulate our why", "make our mission compelling", "frame our vision", "rally the team around <X>", or "why should anyone care about <X>". Turns raw material into a Why-first narrative that earns belief before it names f...

Use this skill to structure a message with the Pixar story spine — "Once upon a time... Every day... Until finally." Best for transformation and journey narratives: before/after, old world → new world, the arc of a change, product origin stories, case studies. Triggers on "pixar pitch", "story spine", "tell this as a journey", "before and after story", "narrate the transformation", "make this change story compelling", or "once upon a time". Turns raw material into a narrative arc with a statu...

Use this skill to structure a message with Barbara Minto's Pyramid Principle — answer first, then grouped evidence. Best for boards, executives, investors, and decision memos where the reader wants the bottom line now. Triggers on "pyramid principle", "minto", "bottom line up front", "BLUF", "structure this exec summary / board deck / decision memo", "make this investor update tighter", "lead with the answer", or "get to the point for leadership". Turns sprawling material into a governing tho...

Use this skill to structure a message with Donald Miller's StoryBrand (SB7) framework — make the customer the hero and position yourself as the guide. Best for marketing, sales, landing pages, value propositions, cold outreach, and product messaging. Triggers on "storybrand", "sb7", "make the customer the hero", "write a landing page / value prop / sales page", "clarify our marketing message", "why should a customer buy this", or "our messaging is confusing". Turns raw material into a hero's-...

Use this skill when the user has something to communicate — an idea, a pitch, a product, a strategy, an update, a decision, a launch, an ask — and wants it to actually land. Triggers on things like "help me tell the story of <X>", "how should I pitch <X>", "make this message land", "I need to present <X> to <audience>", "reframe this so it's compelling", "turn this into a story", "help me write my <keynote / investor update / launch post / all-hands / cold email>", "which storytelling framewo...

Use this skill to structure a message as What / So What / Now What — state the fact, explain the impact, recommend the action. Best for post-mortems, retros, incident reviews, status updates, debriefs, and any "here's what happened and what we should do" moment. Triggers on "what so what now what", "structure this post-mortem / retro / incident review / status update", "help me debrief <X>", "what's the takeaway and action", or "run this post-mortem cleanly". Turns raw observations into a cri...