Research

Use when executing approved proposals. Researchers can execute ANY approved proposal (not just their own) to perform actions like memory cleanup, marking proposals ready for ticket/skill creation.

Work on the LaTeX thesis or LaTeXML HTML output. Use for build/lint/serve commands, LaTeX style rules, HTML pipeline notes, or assets conventions.

Claude Codeフックの詳細仕様、設計原則、設定方法。フック、hook、PreToolUse、Stop時に使用。

Turns ambiguity into an Uncertainty Register, prioritizes items, and produces observation tasks/experiments with evidence and decision rules. Use when the user mentions uncertainty/unknowns/assumptions/validation/investigation/hypotheses/risks or cannot decide (不確実性, 曖昧, 未知, 前提, 仮説, 検証, 調査, 優先順位, 観測, 意思決定).

Master philosophy of language - meaning, reference, truth, speech acts. Use for: semantics, pragmatics, meaning theory, reference. Triggers: 'meaning', 'reference', 'Frege', 'sense', 'Kripke', 'speech act', 'semantics', 'pragmatics', 'truth conditions', 'propositions', 'names', 'descriptions', 'rigid designator', 'natural kind', 'context', 'indexical'.

Writing assistant trained in Ken Klippenstein's investigative journalism style - anti-establishment, transparent, evidence-based, no MSM brain

Improves the RAG (Retrieval-Augmented Generation) chatbot for the Physical AI & Humanoid Robotics textbook with strict grounding, citation requirements, and performance optimization.

Run EPUBCheck and Ace accessibility validation. Use before final EPUB packaging or distribution to ensure publication readiness.

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

Documentation for the htmx JavaScript library (attributes, events, headers, API, extensions, examples, migration guides, server examples). Use when you need accurate htmx syntax/behavior or to locate the right reference page for an htmx question.

Use this skill to perform comprehensive editorial reviews of tacosdedatos content. Provides developmental editing (structure, flow, argument strength, pacing) and voice authenticity editing (ensuring content sounds like tacosdedatos, not generic AI). Use when reviewing drafts, giving feedback on submissions, or evaluating content before publication. Distinct from the writer skill (creates content) and copy-editor agent (grammar/mechanics polish).

Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed responses. Covers VertexAiRagRetrieval tool, corpus setup, and citation formatting.

Build and deploy self-hosted Text-to-Speech API using MeloTTS from Hugging Face and create a LiveKit plugin for voice agents. Use this skill when building TTS systems, LiveKit voice agents, or self-hosted speech synthesis solutions.

Set up GPU sandboxes for interpretability research. Use when writing setup.py scripts with Sandbox, SandboxConfig, ModelConfig, or create_notebook_session. Provides the exact API for Modal GPU environments - MUST read before writing any sandbox setup code.

Structured reasoning for complex problems using Sequential Thinking MCP. Break down problems into stages, track thought progression, identify connections, and generate insights. Use for architectural decisions, complex debugging, research planning, or any problem requiring deep analysis.

This skill should be used when users request research on technical topics, technology trends, industry developments, or any subject requiring web search, source analysis, and structured documentation. It provides a systematic workflow for gathering information from multiple web sources, synthesizing findings into a comprehensive summary, and saving results to a local file.

Prepare detailed, professional prompts for Google Imagen 3/4 image generation. Supports character, environment, and object prompts using natural language with technical photography specifications. Extensible support for multiple art styles via reference files.

Automatically troubleshoot unexpected results OR command/script errors without user request. Triggers when: (1) unexpected behavior - command succeeded but expected effect didn't happen, missing expected errors, wrong output, silent failures; (2) explicit failures - stderr, exceptions, non-zero exit, SDK/API errors. Applies systematic diagnosis using error templates, hypothesis testing, and web research for any Stack Overflow-worthy issue.

Generate and edit images using the Gemini API (Nano Banana). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Analyze completed growth experiment results, validate hypotheses, generate insights, and suggest follow-up experiments. Use when experiments are completed, when the user asks about results or learnings, or when discussing what to do next based on experiment outcomes.