tomevault-io/skills-registry - Page 91

requirement-clarification

Guidelines for asking clarifying questions when requirements are ambiguous. Use when scope is unclear, multiple approaches exist, or critical details are missing. Use when this capability is needed.

architecture-guidelines

System architecture: modules, project structure, ADRs, and testing. Use when designing or reviewing systems. Use when this capability is needed.

git-workflow

Standard git workflow for everyday development — branching, committing, rebasing, pull requests, reviewing, merging, and changelog generation. Use when asked to perform git operations, prepare a PR, resolve merge conflicts, or generate release notes. Use when…

nvim-e2e-workflow

Investigate and fix Lua plugin issues using Neovim headless mode. Use this skill when working on GitHub issues for this codediff/vscode-diff.nvim plugin - it provides E2E testing capabilities to reproduce issues, implement fixes, and validate changes. Use…

pi-heartbeat

Configure periodic health checks via HEARTBEAT.md and the /heartbeat command. Use when this capability is needed.

vue

Esposter Vue 3 SFC conventions — macro ordering, template patterns, watch aliases, props naming, refs/computed, and conditional logic. Apply when writing .vue files. Use when this capability is needed.

beautiful-hackathon-slides

Create distinctive, production-grade hackathon demo decks with bold design choices that stand out from typical technical presentations. Use when building pitch decks for hackathons, demo days, or competition submissions that need to combine technical depth…

next-best-practices

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling Use when this capability is needed.

crowdstrike-fusion-workflow-builder

> Use when this capability is needed.

wallet-monitor

Monitor ETH wallets for on-chain activity, detect whale trades, and track transaction history on Ethereum Mainnet and Base Use when this capability is needed.

n8n-architect

Use when the user explicitly wants to create, edit, validate, sync, or troubleshoot n8n workflows, asks about n8n nodes or automation, or wants to use n8n-as-code in the current context root.

understanding-feature-requests

This skill should be used when clarifying feature requests, gathering requirements, or checking for contradictions in proposed changes Use when this capability is needed.

verify-code

Run Phase 4 verification with Cursor and Gemini code review. Use when this capability is needed.

oscal-parser

Parse OSCAL (Open Security Controls Assessment Language) documents in JSON, YAML, or XML formats and extract structured compliance data. Use this skill when working with security control catalogs, system security plans, component definitions, or other OSCAL…

scikit-learn

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML…

release

Run the local Agent Safehouse release flow: inspect commits since the last published release, propose the next SemVer version and changelog, present a dry-run for confirmation, then update changelog, publish the GitHub release, and publish the stable Homebrew…

especialista-em-machine-learning

Especialista em Machine Learning. Use para escolher algoritmos, treinar/avaliar modelos, tuning de hiperparâmetros, evitar overfitting e métricas adequadas. Palavras-chave: machine learning, modelo, treino, hiperparâmetros, métricas, scikit-learn. Use when…

especialista-em-marketing-digital

Especialista em Marketing Digital. Use para canais online: SEO/SEM, mídia paga, conteúdo, redes sociais, analytics e automação de marketing. Palavras-chave: marketing digital, SEO, ads, mídia paga, analytics, conversão, tráfego. Use when this capability is…

especialista-em-orquestracao-de-agentes-claude

Especialista em Orquestração de Agentes e Subagentes de IA do Claude e Claude Code. Use para coordenar subagents, workflows, delegação, paralelização e padrões multi-agente no Claude Code/Agent SDK. Palavras-chave: Claude, subagent, orquestração, workflow,…

cheatsheet-generator

> Use when this capability is needed.

flutter-pre-caching

Pre-caches assets, fonts, images, and startup data in Flutter and Flutter Web. Use when preloading Google Fonts, asset/network images, Lottie/Rive animations, local JSON/config files, warming up initial API data, or optimizing Flutter Web startup. Use when…

langchain-chat-models

使用 LangChain 中的聊天模型集成指南，包括 OpenAI、Anthropic、Google、Azure 和 Bedrock Use when this capability is needed.

Source text: Chinese

langchain-embeddings

使用 LangChain 中的嵌入模型集成指南，包括 OpenAI、Azure 和本地嵌入 Use when this capability is needed.

Source text: Chinese

langchain-multimodal

Work with multimodal inputs/outputs in LangChain - includes images, audio, video, content blocks, and vision capabilities Use when this capability is needed.

Source text: Chinese

langchain-structured-output

使用 Zod 模式、类型安全响应和自动验证从 LangChain 代理和模型获取结构化的验证输出 Use when this capability is needed.

Source text: Chinese

langchain-text-splitters

使用 LangChain 中的文本分割器集成指南，包括递归、字符和语义分割器 Use when this capability is needed.

Source text: Chinese

langchain-tool-calling

聊天模型如何调用工具 - 包括 bindTools、工具选择策略、并行工具调用和工具消息处理 Use when this capability is needed.

Source text: Chinese

langchain-tools

在 LangChain 中定义和使用工具 - 包括工具装饰器、自定义工具、内置工具和工具模式 Use when this capability is needed.

Source text: Chinese

langchain-vector-stores

LangChain 向量存储集成使用指南，包括 Chroma、Pinecone、FAISS 和内存向量存储 Use when this capability is needed.

Source text: Chinese

simulator-automation

>- Use when this capability is needed.

agent-docs-writing

Use when reading, creating, or updating agent documentation, module docs, roadmaps, or AGENTS.md. Understands the full .augment/, agents/, and copilot-instructions structure.

code-review

Use when the user says \"review this\", \"check my code\", or wants feedback on changes. Reviews for correctness, quality, security, and coding standards.

condense-memory

Use when shrinking always-loaded memory files (AGENTS.md, CLAUDE.md, .cursorrules) via telegraph grammar — refuses sensitive paths, round-trips via .original.md backup.

copilot-agents-optimization

Use when optimizing AGENTS.md or copilot-instructions.md — deduplicates against .augment/ content, enforces line budgets, and focuses each file on its audience.

copilot-config

Tune the GitHub Copilot AI — `copilot-instructions.md`, PR-review patterns, suggestion behavior, output verbosity. NOT for dev-environment setup (use `devcontainer`). Use when this capability is needed.

docker

Use when working with Docker — Dockerfile edits, docker-compose services, containers, or the dual-container (fast + Xdebug) setup — even when the user just says 'my container won't start'.

git-workflow

Use when working with Git — branch naming, commit messages, PR creation, rebasing, or the code review process — even when the user says 'push this' or 'merge the branch' without naming Git.

project-analysis-node-express

Use for deep Node.js / Express project analysis: boot flow, middleware order, async behavior, data layer, auth/security, and Node-specific runtime failure patterns. Use when this capability is needed.

react-shadcn-ui

Use when building React UI on shadcn/ui primitives + Tailwind — the apply/review/polish skill dispatched by `directives/ui/*` for the `react-shadcn` stack.

receiving-code-review

Use when processing code review feedback (bot or human) before changing anything — triages, verifies, and pushes back with technical reasoning — even when the user just says 'fix the comments'.