whichguy
@whichguy
Public Skills
review-fix-bench
by whichguy
A/B benchmarking skill for code reviewer agent prompts. Runs two versions of a reviewer agent against fixture ground truth using an LLM judge for semantic evaluation, then compares precision/recall/F1 metrics side-by-side. Defaults to comparing current agent vs git HEAD~1. Reports IMPROVED / REGRESSED / NEUTRAL verdict on F1.
review-plan
by whichguy
Universal plan review: 3 layers (general quality, code change quality, ecosystem specialization). Invokes gas-plan for GAS plans or node-plan for Node.js/TypeScript plans, conditionally based on detected patterns. AUTOMATICALLY INVOKE when: - MANDATORY_PRE_EXIT_PLAN directive applies (before ExitPlanMode) - User says "review plan", "check plan", "plan ready?" - Any plan file needs review (GAS or non-GAS) NOT for: Code review of existing files (use /gas-review or /review-fix)
tasks
by whichguy
Break down features into step-by-step implementation tasks. Dispatches to feature-task-creator agent for complex decomposition. AUTOMATICALLY INVOKE when: - "break this down", "create tasks", "plan implementation", "decompose" - "what steps", "task list", "how do I implement this" - Large feature requests without clear action items NOT for: Architecture decisions (use /architect), actual implementation (use /develop)
architect
by whichguy
Design system architecture and make technology decisions. Dispatches to system-architect agent for comprehensive design work. AUTOMATICALLY INVOKE when: - "design architecture", "what tech stack", "system design" - "how should I structure", "architecture for", "design system" - "technology recommendation", "compare frameworks" NOT for: Implementation (use /develop), task breakdown (use /tasks)
refactor
by whichguy
Refactor code for improved quality and structure. Dispatches to code-refactor agent for large multi-file refactoring operations. AUTOMATICALLY INVOKE when: - "refactor this", "clean up", "reduce duplication", "DRY this up" - "simplify", "modernize", "restructure" - When detecting code duplication or technical debt NOT for: Bug fixes (fix the bug directly), feature additions (use /develop)
develop
by whichguy
Implement features end-to-end. Dispatches to feature-developer agent for complex multi-file features requiring planning, testing, and documentation. AUTOMATICALLY INVOKE when: - "build this", "implement this", "develop", "create this feature" - "add functionality", "new feature", "feature request" - Multi-file implementation tasks NOT for: Bug fixes (fix directly), refactoring (use /refactor), test generation (use /test)
review
by whichguy
Perform code review with optional auto-fix. Dispatches to code-reviewer or review-fix agent for complex multi-file reviews. AUTOMATICALLY INVOKE when: - "review this", "check this code", "code review", "review my changes" - "review and fix", "fix issues", "clean this up" - Before commits on non-trivial changes NOT for: GAS projects (use /gas-review), plan review (use /review-plan)
expand
by whichguy
Transform epics into comprehensive use case specifications via progressive discovery. Dispatches to use-case-expander agent for complex epics. AUTOMATICALLY INVOKE when: - "expand use cases", "discover scenarios", "edge cases", "what are we missing" - "expand this epic", "use case expansion", "scenario discovery" - Use case analysis or scenario planning NOT for: Task breakdown (use /tasks), architecture (use /architect)
test
by whichguy
Generate comprehensive tests for code. Dispatches to qa-analyst agent for complex components requiring test architecture decisions. AUTOMATICALLY INVOKE when: - "write tests", "test this", "generate tests", "add test coverage" - "test plan", "what should I test" - After feature implementation is complete NOT for: Running existing tests (use npm test), GAS test review (use /gas-test-review)
gas-plan
by whichguy
Dual-perspective GAS plan review (frontend + backend) with iterative convergence loop. AUTOMATICALLY INVOKE when: - Any plan exists for GAS changes, GAS project changes, or uses mcp_gas - Plan mode produces a plan file for a GAS project (scriptId present) - User says "review plan", "check plan", "validate plan", "plan review" - User says "is this plan ready", "plan quality", "gas-plan" - After ExitPlanMode on any GAS project plan - Plan references .gs files, .html files in GAS context, or mcp__gas__ tools - Plan modifies CommonJS modules, events, doGet/doPost, or addon code NOT for: Code review (use /gas-review), test review (use /gas-test-review), prompt analysis (use /prompt-critique), non-GAS plans mode parameter: - standalone (default): TeamCreate + parallel evaluators + convergence loop + ExitPlanMode - evaluate: Single-pass read-only evaluation — returns findings via SendMessage to calling team-lead. No edits, no team creation, no ExitPlanMode. Used internally by review-plan.
node-plan
by whichguy
Dual-perspective Node.js/TypeScript plan review (TypeScript/API + Node runtime) with iterative convergence loop. 36 Node/TS-specific questions (N20/N21 naming+docs deferred to L1's Q-G6/Q-G7 which cover these universally). AUTOMATICALLY INVOKE when: - Any plan exists for Node.js or TypeScript changes - Plan references package.json, tsconfig.json, .ts files, npm/yarn/pnpm/bun - Plan targets Express, Fastify, NestJS, Next.js, or similar Node frameworks - Plan modifies async code, environment variables, or Node process lifecycle - User says "review plan", "check plan", "node-plan" NOT for: GAS plans (use /gas-plan), code review (use /review-fix), non-Node plans
slides
by whichguy
Generate professional presentations from material, notes, or topic descriptions. Produces reveal.js HTML (single file, no build step) or Google Slides (via GAS SlidesApp). AUTOMATICALLY INVOKE when: "create slides", "make a deck", "generate a presentation", "slides about", "deck on", "presentation from [material]" NOT for: editing existing PPTX, converting files, exporting Sheets charts
prompt-critique
by whichguy
Fast prompt critique tool with technique library. Analyzes any prompt against 7 technique categories and 14 anti-patterns, producing a scorecard with prioritized recommendations. AUTOMATICALLY INVOKE when: - User says "critique prompt", "score this prompt", "improve this prompt" - User asks "what techniques should I use", "prompt best practices" - User pastes a system prompt, agent prompt, or skill definition for feedback - User mentions "prompt anti-patterns", "prompt quality", "score this prompt" - User asks about instructional style, quality gates, or compression techniques NOT for: - Exhaustive multi-phase analysis (use /prompt-reviewer) - A/B prompt comparison with execution (use compare-prompts) - GAS-specific system prompt optimization (use /optimize-system-prompt)
gas-debug
by whichguy
GAS project server-side debugging and troubleshooting with RESUME capability for iterative investigation. Covers: CommonJS modules, SpreadsheetApp, DriveApp, GmailApp, HTML Service (server-side), triggers, permissions, quotas. AUTOMATICALLY INVOKE when: - exec() returns success: false or error in response - User mentions "error", "exception", "TypeError", "null", "undefined" - Code "doesn't work", "isn't working", "fails", "breaks" - Silent failures (code runs but wrong result) - Something "should" work but doesn't RESUME SUPPORT: This skill runs in forked context - user can say "dig deeper" to continue investigation with full history preserved. NOT for: Static code review (use gas-code-review), UI testing (use gas-ui-debug), interactive Chrome testing (use /gas-sidebar)
gas-review
by whichguy
Unified GAS code review - runs BOTH gas-code-review AND gas-ui-review. ALWAYS PREFER THIS over gas-code-review or gas-ui-review individually. This agent provides cross-file analysis and parallel execution. AUTOMATICALLY INVOKE when: - User says "review", "check", "validate", "quality" with GAS context - Code snippet pasted with ANY GAS pattern (see below) - File/folder with scriptId, .gs files, or .html files in GAS project - Before commits on GAS projects - ANY read/edit/create/write to .gs or .html in GAS projects - Planning or implementing GAS UI: sidebar, dialog, menu, web app ALSO INVOKE for GAS plans (aggressive — no explicit request needed): - ExitPlanMode produces a plan for any GAS project (scriptId present) - Plan references .gs files, .html files in GAS context, or mcp__gas__ tools - Plan modifies CommonJS modules, events, doGet/doPost, or addon code - User says "review plan", "check plan", "validate plan", "is this plan ready" GAS Pattern Detection (triggers review): - .gs code: _main, defineModule, require(), module.exports, events, global - .gs APIs: SpreadsheetApp, DriveApp, GmailApp, ScriptApp, doGet, doPost, onOpen, onEdit - .html code: HtmlService, <?=, <?!=, google.script.run, createGasServer, exec_api - .html patterns: createTemplateFromFile, setXFrameOptionsMode, IFRAME embedding GAS UI/UX topics (with GAS context): - sidebar, dialog, modal, toast, menu, form in GAS projects - Google Picker, file upload, web app deployment - /exec vs /dev URLs, ContentService, CORS NOT for: General JS/TS (use code-reviewer), non-GAS HTML (use standard review)
gas-code-review
by whichguy
PREFER OVER code-reviewer for GAS/Apps Script projects. Fast syntax and pattern validator. AUTOMATICALLY INVOKE when: - Code review, quality review, or validation in GAS context (scriptId present) - Reviewing .gs files in Apps Script projects - Detecting high-risk patterns: events, global, doGet/doPost/onOpen/onEdit - Before commits on GAS projects - User says "review", "check", "validate", "quality" with GAS code - Code snippet pasted containing: _main, defineModule, require(), module.exports ALWAYS PAIR WITH: gas-ui-review when .html files are also present (or use /gas-review for both) NOT for: General JS/TS (use code-reviewer), deep audit (use gas-quality-check), HTML patterns (use gas-ui-review)
optimize-system-prompt
by whichguy
Optimize or refine the Sheets Chat ClaudeConversation system prompt. Analyze, compress, refine, A/B test, and deploy system prompt changes with automated quality gates. AUTOMATICALLY INVOKE when: - User mentions "system prompt", "optimize prompt", "compress prompt" - User wants to change ClaudeConversation system behavior - User asks about prompt token usage or context budget - User says "prompt too long", "reduce prompt", "prompt efficiency" - User says "refine system prompt", "update system prompt", "add to system prompt" - User wants to adapt the system prompt for a new model version NOT for: General prompt engineering, non-GAS prompts, one-off prompt writing
gas-test-review
by whichguy
Review test plans and existing tests for GAS projects using the mocha/chai test framework. AUTOMATICALLY INVOKE when: - "review test", "test plan", "test coverage", "validate tests" - File patterns: .test.gs, .spec.gs, .test.html, .spec.html - After qa-analyst generates specs - Before committing test files to GAS projects NOT for: Testing the framework itself, general JS/TS tests (use code-reviewer)
gas-sidebar
by whichguy
Interactive GAS sidebar testing via Chrome DevTools. Launch sidebar, send prompts, read responses, manage config, and take screenshots -- all through MCP automation. AUTOMATICALLY INVOKE when: - User says "open sidebar", "launch sidebar", "test sidebar" - User says "send prompt", "send message", "chat with sidebar" - User says "check sidebar", "sidebar not working", "sidebar blank" - User wants to interact with Sheet Chat sidebar in any environment (Dev/Staging/Prod) - User says "gas-sidebar" or "/gas-sidebar" - User mentions "Sheet Chat" + any action verb (open, test, send, check) - User wants to verify sidebar deployment is working end-to-end MCP REQUIRED: chrome-devtools (with browserUrl for GAS auth), gas NOT for: Static code review (use /gas), server-side debugging (use /gas), symptom-based UI debugging without Chrome (use /gas)
gas-gmail-cards
by whichguy
Gmail add-on and CardService specialist for Google Apps Script. Operates in 3 modes: code review, plan review, and advisory/Q&A. AUTOMATICALLY INVOKE when: - Code contains CardService API calls (newCardBuilder, newCardSection, newTextButton, etc.) - Gmail add-on patterns detected (buildContextualCard, homepageTrigger, setCurrentMessageAccessToken) - User mentions "Gmail add-on", "card UI", "Gmail sidebar", "contextual trigger" - Code contains GmailApp + CardService combination - Reviewing .gs files with appsscript.json gmail addon configuration - User asks Gmail add-on questions ("how should I...", "what's the best way...") - Plan/architecture discussions for Gmail add-ons Pattern Detection (triggers review): - CardService.newCardBuilder(), .addCard(), .buildHomepageCard() - GmailApp.setCurrentMessageAccessToken(), .getMessageById(), .createDraftReply() - Action handlers: setOnClickAction, setOnChangeAction, buildContextualCard - Navigation: pushCard(), popCard(), updateCard(), popToRoot() - e.gmail.accessToken, e.gmail.messageId, e.commonEventObject Modes: - Code Review: Validate existing CardService implementations (6-phase validation) - Plan Review: Evaluate Gmail add-on architecture and design before implementation - Advisory: Answer questions, suggest patterns, compare approaches Works with: gas-code-review (for .gs validation), gas-review (unified orchestrator) NOT for: HtmlService UIs (use gas-ui-review), Sheets-only GAS (use gas-code-review), Calendar/Drive/Docs add-ons (covered by gas-code-review)
MCP GAS Troubleshooting Guide
by whichguy
"Troubleshooting guide for mcp_gas build failures, auth issues, and common errors"
gas-ui-review
by whichguy
GAS HTML/UI pattern reviewer for correctness and layout. AUTOMATICALLY INVOKE when: - Code snippet pasted containing: HtmlService, <?=, <?!=, google.script.run, createGasServer ## HTML File Operations (Highest Priority) - ANY edit/create/write to .html files in GAS projects - Reading .html files for review or understanding - Planning changes to HTML files ALWAYS PAIR WITH: gas-code-review when .gs files are also present (or use /gas-review for both) ## IFRAME & Embedding - IFRAME, embedding, X-Frame-Options, setXFrameOptionsMode - Web app deployment, doGet(), doPost() - External embedding, cross-origin, CORS ## UI Components & Layout - sidebar, dialog, modal, toast, menu, form, button - Layout, positioning, sizing, dimensions, width, height - CSS, styling, responsive, mobile - Template, HtmlService, HtmlOutput, HtmlTemplate ## GAS HTML Patterns - Scriptlets: <?= ?>, <?!= ?>, <? ?>, include() - createTemplateFromFile, createHtmlOutputFromFile, evaluate() - google.script.run, createGasServer(), server.exec_api() - Template literals in HTML, URL strings ## Review & Planning Triggers - "review" + any UI/HTML context - "plan" + sidebar/dialog/menu/UI implementation - "implement" + UI components - "add" + sidebar/dialog/menu/form - "create" + HTML/UI/interface - "update" + sidebar/dialog/layout - "fix" + UI/display/render/layout issues ## Explicit UI Keywords - UI, UX, interface, display, render, show, view - Frontend, client-side, browser-side - User interaction, click handler, event handler (in HTML) ## Advanced Patterns (Trigger on these topics) - Google Picker, file picker, setOrigin, setAppId - File upload, blob, byte array, base64 - CORS, preflight, text/plain workaround - Loading state, spinner, async UI - Polling, active sheet detection - Dynamic menu, global functions - Cache vs Properties, performance - Close sidebar programmatically - Template debugging, getCode() - Session, authentication, getActiveUser, getUserAgent - Webhook response, ContentService, JSON API - Data passing, hidden div, template properties - Internal methods, initTemplate, output. / output.$ ## Web Apps (doGet/doPost) Triggers - Web app, doGet, doPost, deployment - URL parameters, query string, pathInfo - /exec vs /dev, versioned deployment - Execute as me, execute as user, permissions - State token, OAuth callback, usercallback - ScriptApp.getOAuthToken, Authorization header - JSONP, cross-origin, redirect behavior - ContentService, JSON response, MIME type NOT for: Runtime debugging (use gas-ui-debug), .gs syntax validation (use gas-code-review)
gas-ui-debug
by whichguy
Symptom-based GAS UI debugging. Route by user's problem description. AUTOMATICALLY INVOKE when user describes: - "blank", "empty", "nothing shows" → CONSOLE_CHECK - "error", "red message" → CONSOLE_CHECK - "button doesn't work", "click does nothing" → HANDLER_TEST - "nothing happens" → CONNECTION_CHECK - "looks wrong", "layout broken" → SNAPSHOT_CHECK - "slow", "loading forever" → PERFORMANCE_CHECK MCP REQUIRED: chrome-devtools (with browserUrl for GAS auth)