AI & ML

tomevault-io Bundle

Capture Tasks from Meeting Notes

tomevault-io Bundle

Enforces ThemeData discipline in Flutter widgets. Triggers automatically whenever the model is about to write a Color, TextStyle, or Decoration in a widget. Hardcoded colors (Colors.blue, 0xFFFFFFFF, Color(0xFFXXXXXX) inline) are forbidden in widget code. All colors must come from Theme.of(context).colorScheme.* or a custom ColorScheme extension. All text styles must come from Theme.of(context).textTheme.* with optional copyWith. The theme itself is defined ONCE in a central theme file, supports both light and dark modes, and uses Material 3 ColorScheme.fromSeed for color generation unless a brand requires exact hex values. Use when this capability is needed.

tomevault-io Bundle

Implement and review core changes in Axone's Go-based Prolog VM and interpreter with strict determinism for blockchain embedding. Use when editing predicate semantics, VM execution state, parser or lexer behavior, stream or filesystem I/O (open/*, read_write, set_stream_position), or interpreter wiring in engine/*.go, interpreter.go, and cmd/1pl/*, while preserving ISO compliance where feasible and maintaining explicit project deviations where required by blockchain constraints. Use when this capability is needed.

tomevault-io Bundle

USB and CAN connectivity for Zephyr RTOS. Covers USB device stack configuration (CDC ACM, HID, MSC), CAN controller integration, and professional USB-to-CAN adapter patterns including buffering and protocol packetization. Trigger when adding USB interfaces, implementing CAN bus communication, or building hardware diagnostic tools. Use when this capability is needed.

tomevault-io Bundle

This skill should be used when the user asks about "long-running agents", "antibrittle patterns", "agent reliability", "agents that run for hours", "run boxes", "context boundaries", or needs architecture guidance for AI agents that work autonomously for extended periods. Use when this capability is needed.

tomevault-io Bundle

This skill is for writing integrations to the Ruby SDK. Claude acts as the engineer implementing LLM provider or agentic framework integrations. Use when adding support for OpenAI-like providers, Anthropic-like providers, or agent frameworks. Covers TDD workflow, comprehensive testing (streaming/non-streaming/tokens/multimodal), defensive coding, MCP validation, and StandardRB compliance. Use when this capability is needed.

tomevault-io Bundle

Claude Agent SDK - Structured Outputs & Error Prevention Guide

tomevault-io Bundle

Guides the agent through creating and maintaining Capacitor plugins from scratch. Covers scaffolding a new plugin project, designing the TypeScript API, implementing native iOS (Swift) and Android (Java/Kotlin) bridges, implementing the web layer, defining TypeScript type definitions, plugin configuration values, plugin hooks, development workflow with local testing, documentation generation, and publishing to npm. Do not use for installing existing plugins into an app, upgrading existing plugins to newer Capacitor versions, adding SPM support to plugins, or non-Capacitor plugin frameworks. Use when this capability is needed.

tomevault-io Bundle

Search and retrieve context from past development sessions using Chronicle data. Works with MCP (fast, structured) or CLI commands (portable). Use when user asks about previous work, wants to recall past decisions, needs to understand codebase history, or wants to avoid repeating past approaches. Use when this capability is needed.

tomevault-io Bundle

Minimal TTS smoke test for Model Studio Qwen TTS. Use when this capability is needed.

tomevault-io Bundle

This skill enforces a "Notebook First" retrieval policy. Instead of loading entire markdown files or running web searches for architecture decisions, debugging patterns, or security knowledge, the agent queries purpose-built NotebookLM notebooks via the `nlm` CLI. This keeps the agent context window lean and retrieval fast. Use when this capability is needed.

tomevault-io Bundle

When to Use

tomevault-io Bundle

Multi-AI Review

tomevault-io Bundle

Track real-time API cost accrual during LLM execution. Activate on 'cost tracking', 'token usage', 'API costs', 'budget monitoring', 'usage metrics'. NOT for cost estimation, pricing tiers, Use when this capability is needed.

tomevault-io Bundle

Create optimized llm-context rules for specific tasks by analyzing codebase content and generating minimal file selection patterns Use when this capability is needed.

tomevault-io Bundle

Model Versioning Tracker

tomevault-io Bundle

为 imodelzoo 中指定模型生成 `tests/models_tests` 风格的 pytest 测例，包括模型配置 JSON、pytest 入口、marker 注册、`imodelExampleConfig.yaml` 聚合配置。适用于新增模型测例、补齐 get_model/quant/compile/demo/perf/eval/compare 流程。 Use when this capability is needed.

tomevault-io Bundle

Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and guides. Use for system documentation, architecture guides, or technical deep-dives.

tomevault-io Bundle

Add evaluation results to Hugging Face model repositories using the .eval_results/ format. Uses HF CLI for PR management and manual YAML creation. Use when this capability is needed.

tomevault-io Bundle

Codebase Map — AI Agent Knowledge Pack

tomevault-io Bundle

Run comprehensive pre-press preflight checks on Adobe Illustrator documents using illustrator-mcp tools. Detects print-critical issues (RGB in CMYK, broken links, low-res images, white overprint, text not outlined), text consistency problems (dummy text, notation variations), and PDF/X compliance. Use when user asks to check a document before printing, submission, or handoff — or mentions "preflight", "pre-press check", "print check", "submission check". Use when this capability is needed.

tomevault-io Bundle

Machine Learning

tomevault-io Bundle

Test with <angle brackets> Use when this capability is needed.

tomevault-io Bundle

Local Microsoft Agent Framework documentation reference. Use when asked about Microsoft Agent Framework, building AI agents in .NET or Python, MCP servers/clients, durable agents, agent tools, Teams/WebChat adapters, or agent-to-agent communication. Use when this capability is needed.

tomevault-io Bundle

Complete reference for the WoW Lua 5.1 runtime environment, restrictions, secure execution, taint system, addon security model, timers, hooks, frame scripting, logging, and restricted actions. Covers hooksecurefunc, C_Timer, securecallfunction, issecurevariable, taint propagation, combat lockdown, protected frames, InCombatLockdown, C_RestrictedActions, C_Log, and the FrameScript sandbox. Use when working with Lua restrictions, secure code, taint, timers, hooks, addon security, debugging, or the WoW Lua sandbox. Use when this capability is needed.

tomevault-io Bundle

MCP Server Recommendations

tomevault-io Bundle

Design the foundational data layer for a multi-tenant AI agent system -- domain connectors, versioned business rules, and tenant-scoped memory. Use when starting a new AI agent project or adding a new domain to an existing one. Use when this capability is needed.

tomevault-io Bundle

Conceptual data modeling workflow for domain entities, relationships, and lifecycle boundaries. Use when teams must align on domain meaning before logical/physical schema decisions; do not use for index-only or migration-only tasks. Use when this capability is needed.

tomevault-io Bundle

Django application development workflow for production-grade app changes. Use when Django-specific code (models, views, serializers/forms, routing, settings, middleware, auth flows) must be implemented or revised with framework runtime behavior in scope; do not use for repository-wide architecture governance or release management policy. Use when this capability is needed.

tomevault-io Bundle

Select and apply minimal hotfix commits across branches via cherry-pick with dependency risk control. Use when urgent fixes must be propagated without pulling unrelated changes; do not use for CI workflow design or application behavior implementation. Use when this capability is needed.

tomevault-io Bundle

ML experiment tracking workflow for reproducibility, metadata integrity, and run comparison traceability. Use when multiple ML runs must be compared or reproduced reliably; do not use for generic API-layer or infrastructure-only changes. Use when this capability is needed.

tomevault-io Bundle

ML feature engineering workflow for feature definition, lineage, and online-offline parity. Use when model performance depends on explicit feature design and parity controls; do not use for generic API-layer or infrastructure-only changes. Use when this capability is needed.

tomevault-io Bundle

Observability alerting workflow for signal quality, routing policy, and actionable thresholds. Use when alert rules need design or tuning to detect incidents with clear ownership and noise control; do not use for business-feature implementation logic. Use when this capability is needed.

tomevault-io Bundle

Security workflow for authorization boundaries, least-privilege policy, and enforcement design. Use when permission models, access decisions, or privileged action controls are required; do not use for authentication factor selection or non-security quality tuning. Use when this capability is needed.

tomevault-io Bundle

Property-based testing workflow for invariant validation over broad input spaces. Use when correctness depends on rules that must hold across many generated inputs; do not use for narrow deterministic examples only. Use when this capability is needed.

tomevault-io Bundle

Style, review, and refactoring standards for TypeScript codebases. Trigger when `.ts`, `.tsx`, `.d.ts`, or `tsconfig*.json` files are created, changed, or reviewed and TS-specific quality rules (type safety, narrowing, async/error handling, module boundaries) must be enforced. Do not use for JavaScript-only modules that are outside TypeScript type-check scope. In mixed JS/TS repositories, this skill owns `tsconfig`-scoped modules. For shared JS/TS configuration files (for example `package.json`, shared lint/test config), run together with `javascript-style-guide` when both JS and TS artifacts change in the same pull request. Use when this capability is needed.