Deploy a monorepo to Railway with multiple services using Dockerfiles, config-as-code, and the Railway CLI/GraphQL API. Use when deploying apps to Railway, setting up Railway projects, or fixing Railway build failures.

Use when writing or reviewing Bash scripts and shell snippets, especially for shebang selection, quoting, parameter expansion ("${VAR}" style), test expressions (`[ ]` vs `[[ ]]`), ShellCheck-guided fixes, and portability decisions across POSIX sh, Bash, and zsh compatibility targets.

Use this skill when building applications with Gemini models, Gemini API, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript, com.google.genai:google-genai for Java, google.golang.org/genai for Go), model selection, and API capabilities.

Dose-response / concentration-response curve fitting — IC50, EC50, Hill slope, Emax/Emin efficacy, and relative potency from paired concentration vs response data (enzyme/cell assays, drug screening, agonist/antagonist pharmacology). Fits the 4-parameter logistic (Hill sigmoidal) model. Use when you have concentrations + responses and need a potency value, to compare two compounds' potency, or to judge curve quality. NOT for image-derived dose-response (use tooluniverse-image-analysis) and NOT for survival/regression (use tooluniverse-statistical-modeling).

Guided journey from a large aged codebase everyone fears to touch to one that is safe to change, legible, bounded, and resilient - paid down in place without a rewrite. Orchestrates eight skills phase by phase - working-with-legacy-code, refactoring-patterns, clean-code, software-design-philosophy, clean-architecture, pragmatic-programmer, release-it, domain-driven-design - asking the user questions at every decision point and recording results in the project docs/ folder (TESTING.md, TECH-DEBT.md, REMOVE-TECHNICAL-DEBT-PLAN.md) so the journey resumes across sessions. Use when the user wants to tame a legacy codebase, pay down technical debt safely, avoid a big-bang rewrite, or says 'we are afraid to touch this code'. For a fresh vibe-coded prototype, improve-code-quality; for greenfield structure, design-code-architecture; for a product-and-UX pass, improve-app; to optimize a working codebase for speed, architecture-optimization. For one framework in isolation, invoke that skill directly.

Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite TARGET".

Search, download, and read academic papers through the paper-search MCP tools (mcp__paper-search__*), covering arXiv, PubMed, bioRxiv, Semantic Scholar, Crossref, OpenAlex and 15+ other sources. Use when the user asks to find papers, search research literature, download a paper PDF, or extract text from a paper.

Create a git branch following Sentry naming conventions. Use when asked to "create a branch", "new branch", "start a branch", "make a branch", "switch to a new branch", or when starting new work on the default branch.

Search 10 academic paper databases via REST APIs for research papers, preprints, and scholarly articles. Covers PubMed, PMC (full text), bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall. Use when searching for papers, citations, DOI/PMID lookups, abstracts, full text, open access, preprints, citation graphs, author search, or any scholarly literature query. Triggers on mentions of any supported database or requests like "find papers on X" or "look up this DOI".

PDF 读/写/转/OCR 一体化。触发场景：总结 PDF、读文本或表格、填 AcroForm 表单、渲染页面为图、合并/拆分/水印/旋转/加密、创建新 PDF（发票/报告）、PDF ↔ docx/md/txt 互转。典型说法：“总结这份 PDF”、“填一下这个 PDF 表单”、“把几个 PDF 合一起”、“PDF 加水印”、“PDF 转 Word”、“扫描件 OCR”、“看看 PDF 第 3 页长什么样”。用户提到 .pdf 文件、要产出 PDF、或要对 PDF 做任何改动都加载本技能。

Word 文档（.docx）读/写/转/评审一体化。触发场景：总结 docx、读段落/大纲/表格/图片/评论/修订、替换正文、插入图片、改页面设置、重建目录、加评论或回复、加修订（insert/delete/replace）、接受/驳回修订、docx ↔ pdf/html/md/txt 互转。典型说法："帮我总结这份 Word"、"第二段改成 XXX"、"把全部'A 公司'换成'B 公司'"、"加一条修订批注"、"接受所有修订"、"docx 转 pdf"、"从这些要点生成销售报告"。用户提到 .docx / .doc 文件或以 Word 文档为产出目标都加载本技能。

Guides Claude in reviewing and writing robust error-handling code. Covers distinguishing recoverable from unrecoverable errors, implementing retry-with-backoff patterns, structured error logging with correlation IDs, and crafting helpful user-facing error messages. Use when the user asks about error handling, exception management, try-catch patterns, error logging, retry logic, or debugging runtime failures in any codebase.

NOTE: molecule and target inputs and your NGC_API_KEY are transmitted to external NVIDIA-hosted API endpoints on every call. Use local NIM containers for confidential or proprietary data. Run a complete computational drug discovery pipeline using NVIDIA BioNeMo NIMs: generate drug-like molecules with GenMol, dock them to a protein target with DiffDock, then predict binding affinity with Boltz2. Use this skill whenever the user wants to generate and screen small molecule drug candidates, perform hit discovery, optimize leads against a protein target, or do virtual screening combining molecule generation, docking, and affinity prediction. Triggers on: drug discovery pipeline, hit discovery, lead optimization, virtual screening, molecule generation, molecular docking, binding affinity, GenMol, DiffDock, Boltz2, SMILES, SAFE notation, NIM microservice. This is a multi-step pipeline composing three BioNeMo NIMs.

Use this when the user wants to bulk-edit a Spotify playlist — add tracks, remove tracks, dedupe, verify contents — and they have open.spotify.com open in a logged-in tab. Covers search-and-add, remove-by-uid, list-contents, duplicate-removal, and the rate-limit + human-pacing patterns that Spotify enforces. Read this BEFORE attempting any direct GraphQL calls or scripting against the playlist — the rediscovery cost without this skill is significant (we know).

Senior + arquitecto + CTO del módulo sales_agent post redesign 2026-04. Carga §3 protected surfaces, anti-patterns, decisiones cross-fase, checklist pre-commit. NO carga code vivo (paths/LOC/tests cambian). Use cuando user pida cambio/feature/bug en sales_agent: voz de marca, scheduler/payment tools, observabilidad, callback handler, prompt cache, channel registry, semantic router, closer studio, follow_up engine, eval loop, costo agentes. Triggers: 'modifica sales_agent', 'bug en sales_agent', 'agregar tool al agente', 'agente no cierra', 'suena robótico', 'voz de marca', 'agregar canal sales', 'modificar prompt del specialist', 'closer studio', 'follow-up no dispara', 'el agente repite preguntas', 'PII en trazas', 'costo Kimi', 'DeepSeek alias', 'tier pricing 200k', 'eval goldens'.

Implements FastAPI endpoints, creates SQLAlchemy 2.0 async models, generates idempotent Alembic migrations, structures bounded contexts following DDD (domain→infrastructure→application→api), and produces typed Pydantic v2 DTOs. Runs inside Docker (visionarias_brain_dev). Use when: 'create an endpoint', 'modify the backend', 'create a new entity', 'update a service', 'database logic', 'fix a backend bug', 'add a migration', 'create a repository', 'agrega un campo', 'nueva ruta API', 'corrige el servicio', or any Python/FastAPI/SQLAlchemy/Alembic task.

Implements FastAPI endpoints, creates SQLAlchemy 2.0 async models, generates idempotent Alembic migrations, structures bounded contexts following DDD (domain→infrastructure→application→api), and produces typed Pydantic v2 DTOs. Runs inside Docker (visionarias_brain_dev). Use when: 'create an endpoint', 'modify the backend', 'create a new entity', 'update a service', 'database logic', 'fix a backend bug', 'add a migration', 'create a repository', 'agrega un campo', 'nueva ruta API', 'corrige el servicio', or any Python/FastAPI/SQLAlchemy/Alembic task.

Senior + arquitecto + CTO del módulo sales_agent post redesign 2026-04. Carga §3 protected surfaces, anti-patterns, decisiones cross-fase, checklist pre-commit. NO carga code vivo (paths/LOC/tests cambian). Use cuando user pida cambio/feature/bug en sales_agent: voz de marca, scheduler/payment tools, observabilidad, callback handler, prompt cache, channel registry, semantic router, closer studio, follow_up engine, eval loop, costo agentes. Triggers: 'modifica sales_agent', 'bug en sales_agent', 'agregar tool al agente', 'agente no cierra', 'suena robótico', 'voz de marca', 'agregar canal sales', 'modificar prompt del specialist', 'closer studio', 'follow-up no dispara', 'el agente repite preguntas', 'PII en trazas', 'costo Kimi', 'DeepSeek alias', 'tier pricing 200k', 'eval goldens'.

Use when building data-heavy screens, analytics dashboards, metric visualizations, or inline charts for Copilot. Creates bar/line charts, renders data tables, aggregates KPI metrics, builds filterable dashboard layouts, and generates HTML previews for concept validation. Triggers: 'dashboard', 'métricas', 'gráfico', 'chart', 'visualización', 'analytics', 'KPI', 'reporte', 'muestra los datos', 'cómo van los números'.

One-time, guided setup of a standalone LLM-maintained wiki — a Karpathy "LLM Wiki" style knowledge base for a problem domain and your general architecture best practices. Scaffolds an external wiki vault (its own git repo) with /ingest, /query, /lint commands and a conventions doc. Use when a developer wants to start, create, bootstrap, or initialize a wiki / second-brain / knowledge base to understand a problem space before building. The front of the Human Loop's Understanding phase.