AI & ML

tomevault-io Bundle

Add function-calling tools to Prompture agents. Covers ToolDefinition, ToolRegistry, tool_from_function, decorator patterns, serialization formats, and Conversation integration. Use when adding callable tools for LLM function calling. Use when this capability is needed.

tomevault-io Bundle

Analyze coding-agent session transcripts to discover patterns that could become AGENTS.md rules, skills, or prompt templates. Mines your usage history for automation opportunities across local coding-agent tools. Use when this capability is needed.

tomevault-io Bundle

Check Zed editor logs for banjo/agent errors. Use when user says "check zed logs", "zed errors", or "what's the zed error". Use when this capability is needed.

tomevault-io Bundle

Mission decomposition skill — breaks complex tasks into dependency-aware PHASE lines that the orchestrator executes directly, bypassing its internal LLM decomposer. Use when planning missions, creating mission files, or decomposing complex tasks. Use when this capability is needed.

tomevault-io Bundle

Analyze a systing trace database (.duckdb). Use when the user asks about a systing trace — flamegraphs, scheduling latency, CPU hotspots, network behavior, off-CPU time, TPU op/metric data, or any question about what's in a trace.duckdb file. Orchestrates the systing-analyze MCP tools (trace_info, query, flamegraph, sched_stats, cpu_stats, network_*). Use when this capability is needed.

tomevault-io Bundle

Zod schema validation patterns and type inference. Auto-loads when validating schemas, parsing data, validating forms, checking types at runtime, or using z.object/z.string/z.infer in TypeScript. Use when this capability is needed.

tomevault-io Bundle

Use sift-kg as an AI second brain — a persistent knowledge graph your agent operates from across sessions. Use proactively at session start to orient, when answering questions about the user's projects or domain, when generating ideas or suggestions, when user asks "what do I know about X", "how does X connect to Y", "find connections", "what should I work on", "give me ideas", or when you need to understand the structure of the user's knowledge. Not needed for one-off document analysis — sift's CLI commands work fine on their own for that. Use when this capability is needed.

tomevault-io Bundle

アクターモデルに基づいた均質なサブエージェントを定義します。新しいサブエージェントを定義する場合、エージェント/タスクの責務や境界を明確化したい場合、複数のエージェント間の協調動作を設計する場合、またはエージェント仕様を文書化する場合に使用してください。エージェント定義、責務設計、サブエージェント設計などのリクエストに応答します。 Use when this capability is needed.

tomevault-io Bundle

Control Obsidian from the terminal using the `obsidian` CLI. Use when the agent needs to open notes, search the vault inside Obsidian, append/prepend content to the active file, create notes from templates, manage properties, check backlinks/orphans, query Bases, or interact with the running Obsidian app. Requires Obsidian 1.12+ running. Use when this capability is needed.

tomevault-io Bundle

Use when working with the correct TCA shape as the generation target before code exists — file classification, Evaluation Model template, smart-method patterns (B.2, B.3), and Pydantic decorator stack discipline loaded into working context.

tomevault-io Bundle

Test, validate, and improve agent instructions (CLAUDE.md, system prompts) using sub-agents as experiment subjects. Measures instruction compliance, context decay, and constraint strength. Use for "test prompt", "validate instructions", "prompt effectiveness", "instruction decay", or when designing robust agent behaviors. Use when this capability is needed.

tomevault-io Bundle

Install an MCP server template from dotforge into a project or global Claude Code config with a single command. Use when this capability is needed.

tomevault-io Bundle

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture. Use when this capability is needed.

tomevault-io Bundle

Use this skill when certifying a GGUF model family for skippy stage-split serving, reviewing capability data, promoting family evidence into topology policy, or updating staged split certification docs.

tomevault-io Bundle

Drafts and reviews strong /goal objectives for Pi pi-goal and compatible goal-mode agents. Use when the user asks to write, improve, audit, or meta-prompt a long-running agent goal with clear success criteria, verification, constraints, iteration policy, and blocked stop conditions. Use when this capability is needed.

tomevault-io Bundle

Customize Model Deployment

tomevault-io Bundle

WHEN users express dissatisfaction with visual appearance or behavior; use Playwright MCP to capture screenshots and collaborate on UI fixes with a structured feedback loop. Use when this capability is needed.

tomevault-io Bundle

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 pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices. Use when this capability is needed.

tomevault-io Bundle

Set up MoonPay as an MCP server for Claude Desktop or Claude Code. Provides all MoonPay CLI tools via the Model Context Protocol. Use when this capability is needed.

tomevault-io Bundle

This skill should be used when working with Neatoo domain models, ValidateBase, EntityBase, ValidateListBase, EntityListBase, partial properties, property change tracking, validation rules, business rules, aggregate roots, entities, value objects, lazy loading, EntityLazyLoad, IEntityLazyLoadFactory, or any .NET DDD domain model framework work. Also triggers for IsValid, IsSelfValid, IsSavable, IsModified, IsNew, IsDeleted, RuleManager, AddActionAsync, AddValidationAsync, AddAction, AddValidation, IsBusy, WaitForTasks, IsLoaded, IsLoading, and base class behavior. This skill also provides guidance on where business logic belongs -- computed properties, conditional visibility, reactive behavior, and validation should live in the domain model (not the UI). Consult this skill when writing .razor files that bind to Neatoo entities to ensure logic stays in the domain layer. Neatoo is the domain model framework -- it does NOT include factory generation. For factory attributes ([Factory], [Create], [Fetch], [Remote]

tomevault-io Bundle

Add, update, or verify Nexus LLM provider model definitions. Use when adding newly released models, changing OpenAI/OpenRouter/Codex/GitHub Copilot/Anthropic/Google model metadata, updating provider defaults, or live-testing whether a model ID works through the reusable provider smoke test. Use when this capability is needed.

tomevault-io Bundle

Save and retrieve memories or embeddings via the repo helpers or API. Use when working with embedding config or memory storage. Use when this capability is needed.

tomevault-io Bundle

Run Monte Carlo uncertainty analysis on a hydraulic model by sampling parameters from statistical distributions and computing exceedance probabilities. Use this when the user wants uncertainty analysis, Monte Carlo simulation, or probabilistic results. Use when this capability is needed.

tomevault-io Bundle

Crater CLI 补全域：指导 AI Agent 帮用户生成、安装、更新或卸载 bash/zsh Tab 补全脚本，并排查 shell 补全不可用问题。用户提到 crater completion、crater comp、Tab 补全、bash、zsh、.bashrc、.zshrc、补全脚本、completion install/uninstall 时使用。 Use when this capability is needed.

tomevault-io Bundle

Sync your agent's work state to Claw's Pixel Town dashboard. Activate this skill to join the pixel office and report status. Throughout the conversation, update your state when your activity changes (idle, writing, researching, executing, syncing, error). Leave when the conversation ends. Use when this capability is needed.

tomevault-io Bundle

Convert academic PDF papers into polished, narrative-driven PowerPoint presentations using 13 specialized AI agents orchestrated by Claude Code. Based on Rhetorical Structure Theory (RST) discourse parsing with a multi-agent critique-revise-judge refinement loop. Every slide is visually rich -- text-only slides get programmatic diagrams and charts rendered via PptxGenJS (Node.js). No template PPTX required -- slides are built from scratch with selectable presentation themes and strict layout rules. Use when this capability is needed.

tomevault-io Bundle

bullshit — Cross-LLM Fact Checker

tomevault-io Bundle

Browser Automation with agent-browser

tomevault-io Bundle

Evaluate pending (unsubmitted) review comments on the current branch's PR and, after user confirmation, address each in a separate sub-agent and separate commit. Use when this capability is needed.

tomevault-io Bundle

Multi-agent orchestration tool for running conversations between AI agents (Claude, Gemini, Codex, Qwen, etc.). Use when tasks benefit from multiple perspectives, code review by different models, or collaborative problem-solving. Use when this capability is needed.

tomevault-io Bundle

Distill durable user or team rubric preferences from local agent execution histories, repository discussions, and existing agent/rubrics content. Use when asked to mine prior agent work, compare candidate preferences with current rubrics, and open a PR that adds or updates rubric YAML on the agent/rubrics branch. Use when this capability is needed.

tomevault-io Bundle

Scan a project with sentrux to get structural health grades (A-F) across 14 dimensions including coupling, cycles, cohesion, dead code, and test coverage. Use when the user wants to check code quality, architecture health, or before/after an agent session. Use when this capability is needed.

tomevault-io Bundle

Guide for adding and validating evaluation dataset configuration in slime. Use when user wants to configure eval datasets via --eval-config or --eval-prompt-data, add per-dataset overrides, or customize evaluation rollout behavior. Use when this capability is needed.

tomevault-io Bundle

Generate a comprehensive markdown summary of our conversation for seamless handoff to another AI agent Use when this capability is needed.

tomevault-io Bundle

Use this skill when the user asks about cmux, mentions cmux terminal, asks about cmux configuration, keyboard shortcuts, custom commands, notifications, browser automation, the cmux API, cmux split panes, cmux vertical tabs, cmux workspaces, or Claude Code agent teams in cmux. Also use when the user asks about a native macOS terminal for AI coding agents built on Ghostty, or references cmux.com documentation.

tomevault-io Bundle

Build production-ready Tavily integrations with best practices baked in. Reference documentation for developers using coding assistants (Claude Code, Cursor, etc.) to implement web search, content extraction, crawling, and research in agentic workflows, RAG systems, or autonomous agents. Use when this capability is needed.