AI & ML

tomevault-io Bundle

Project-specific development instructions. Use whenver instructions are mentioned. Auto-Load when working on tasks like coding, testing, git operations, or exploring the codebase. Read the matching file from references/. Use when this capability is needed.

tomevault-io Bundle

Writes, reviews, and improves SwiftData code using modern APIs and best practices. Use when reading, writing, or reviewing projects that use SwiftData. Use when this capability is needed.

tomevault-io Bundle

ASDF Runtime Version Updater

tomevault-io Bundle

Use when brainstorming ideas, stuck on a problem, exploring alternatives, or needing creative input - provides structured creativity methods (SCAMPER, Six Hats, Mind Map), Multi-Agent parallel thinking, and concept collision for unexpected sparks. Don't use for mechanical execution tasks

tomevault-io Bundle

用于制药和临床研究环境中生成专业临床决策支持（CDS）文档，包括患者队列分析（基于生物标志物分层并结合结局分析）以及治疗推荐报告（基于循证指南并包含决策算法）。支持 GRADE 证据分级、统计分析（如风险比、 生存曲线、瀑布图）、生物标志物整合以及监管合规要求。输出为可发表级别的 LaTeX/PDF 格式，针对药物开发、临床研究和证据综合进行了优化。 Use when this capability is needed.

tomevault-io Bundle

Scaffold, review, or refactor FastAPI services using uv, a src/ layout, versioned routers, and optional singleton clients; use for new services or architecture cleanups. Use when this capability is needed.

tomevault-io Bundle

This skill implements the **Recursive Language Model (RLM)** approach from MIT CSAIL (arXiv:2512.24601) for handling contexts that exceed effective processing capacity. Instead of feeding long prompts directly into the neural network, RLM treats them as external environment data to be examined programmatically. Use when this capability is needed.

tomevault-io Bundle

Reconcile Agent Skills Across Tools

tomevault-io Bundle

Configure LM Studio as embedding provider for GrepAI. Use this skill for local embeddings with a GUI interface. Use when this capability is needed.

tomevault-io Bundle

Integrate You.com MCP Server with crewAI

tomevault-io Bundle

Use when you want to rebuild or refresh the semantic search index for the codebase

tomevault-io Bundle

Modern Python toolchain substrate. uv for installs and venvs, ruff for lint and format, ty for typecheck, pytest for tests, hypothesis for property-based tests, src/ layout, pyproject.toml as single source of truth, pre-commit hooks. Plus LLM-stack patterns when the codebase calls anthropic, openai, tiktoken, or similar SDKs (prompt caching, retries, streaming, token counting). Use when the user says /python-setup, "set up Python project", "modern Python toolchain", "switch from poetry to uv", "ruff config", "ty migration from mypy", "configure pytest", or starts a new Python codebase. Covers Python 3.11+ idioms. Use when this capability is needed.

tomevault-io Bundle

Automated code quality scanning using SonarQube REST API and SonarScanner CLI. Detects code smells, bugs, and vulnerabilities across 30+ languages with configurable quality gates. Use when this capability is needed.

tomevault-io Bundle

Featurizes molecules for machine learning with molfeat (100+ featurizers) — ECFP and MACCS fingerprints, physicochemical descriptors, and pretrained model embeddings (ChemBERTa), converting SMILES into feature vectors. Use when turning molecules into ML-ready features for QSAR or molecular modeling, or comparing fingerprint and descriptor representations. Part of the AlterLab Academic Skills suite. Use when this capability is needed.

tomevault-io Bundle

Microsoft Foundry Skill

tomevault-io Bundle

Robotics Software Design Principles

tomevault-io Bundle

Train LangChain/LangGraph agents using Microsoft Agent-Lightning APO (Automatic Prompt Optimization). Use when user mentions APO training, prompt optimization, agent-lightning, training multi-agent systems, training single agents, or optimizing agent prompts. Use when this capability is needed.

tomevault-io Bundle

Swift Concurrency

tomevault-io Bundle

Implements systematic error handling in Flutter with Riverpod. Trigger this skill whenever the user asks about "handle error", "what if the API fails", "show error state", "error message", "retry on failure", "AsyncValue error", "API hatası", "hata göster", or when writing any provider that performs async work. Covers the domain error model with Freezed sealed classes, Dio exception mapping, AsyncValue UI patterns, retry logic, and when to use SnackBar vs inline error vs full-screen error state. Prevents silent error swallowing and technical error messages leaking to users. Use when this capability is needed.

tomevault-io Bundle

Generate an architecture summary from the knowledge graph and inject it into CLAUDE.md, AGENTS.md, or .github/copilot-instructions.md so every agent session starts with codebase context Use when this capability is needed.

tomevault-io Bundle

Apply CIS benchmarks and secure Linux servers. Configure SSH, manage users, implement firewall rules, and enable security features. Use when hardening Linux systems for production or meeting security compliance requirements. Use when this capability is needed.

tomevault-io Bundle

Detect anomalies in time series data using Prophet Framework (Meta), which frames the seasonality, trend holiday effect and other needed regressors into its model, to identify unusual surges or slumps in trends. This is a general methodology analyst can use for understanding what changes of their tracking metrics are manifesting anomalies pattern. Use when this capability is needed.

tomevault-io Bundle

Resume or hand off repositories that already use a local code relay workflow centered on AGENTS.md and orchestrator documents such as BOOT.md, PROGRAM.md, CHECKPOINT.md, HANDOFF.md, and LEADERBOARD.md. Use when Codex should recover context from repository documents, summarize the trusted best state, or prepare a clean session transition without depending on chat history or repository-local scripts. Use when this capability is needed.

tomevault-io Bundle

Build BSL semantic models with dimensions, measures, joins, and YAML config. Use for creating/modifying data models. Use when this capability is needed.

tomevault-io Bundle

Search past AI agent sessions, stored knowledge, and indexed content. Use for finding previous work, recalling conventions, storing learnings, and indexing documentation. Use when this capability is needed.

mturac Bundle

Audit system prompts, agent prompts, router prompts, tool/function-call prompts, and coding-agent instructions as executable contracts. Use before writing or seeding prompts; blocks vague "fix this / write code" tasks missing ownership and verification. Works with Hermes, Claude Code, Codex, OpenCode, OpenClaw.

tomevault-io Bundle

Comprehensive codebase assessment for agent and production readiness. Scans 8 pillars (48 criteria), verifies commands work, checks GitHub settings. Reports everything, fixes agent readiness only. Triggers on /flow-next:prime. Use when this capability is needed.

tomevault-io Bundle

Chrome DevTools Debug Companion

tomevault-io Bundle

Use this workflow to review broad or risky diffs through focused, read-only

tomevault-io Bundle

Release Homebrew (agent-workspace-launcher)

tomevault-io Bundle

Master 26 documented prompt engineering principles for crafting effective LLM prompts with 400%+ quality improvement. Includes templates, anti-patterns, and quality checklists for technical, learning, creative, and research tasks. Use when writing prompts for LLMs, improving AI response quality, training on prompting, designing agent instructions, or when user mentions 'prompt engineering', 'better prompts', 'LLM quality', 'prompt templates', 'AI prompts', 'prompt principles', or 'prompt optimization'. Use when this capability is needed.

tomevault-io Bundle

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines. Use when this capability is needed.

tomevault-io Bundle

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Codex, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques. Use when this capability is needed.

tomevault-io Bundle

Cursor Model Selection

tomevault-io Bundle

Comprehensive code review agent that performs systematic, multi-dimensional analysis of code quality. Conducts security, performance, maintainability, testing, and architecture reviews with detailed checklists and actionable recommendations. Use when reviewing PRs, auditing codebases, establishing review standards, or performing technical debt assessment. Use when this capability is needed.

tomevault-io Bundle

Guidance for selecting models when performing code review with subtasks. Load this skill to enable intelligent model selection for review analysis — choosing faster models for simple tasks and deeper reasoning models for complex analysis. Use when this capability is needed.