AI & ML

tomevault-io Bundle

Vite

tomevault-io Bundle

Fast, consistent Markdown auto-formatter for typographic cleanup (smart quotes, ellipses), normalized formatting, and optional clean line wrapping for small, readable git diffs. Use when creating, editing, or normalizing Markdown (.md) files, cleaning up LLM-generated Markdown, or when the user mentions flowmark or formatting Markdown. Use when this capability is needed.

tomevault-io Bundle

Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers. Use when this capability is needed.

tomevault-io Bundle

Use when needing to query databases across environments (local, QA, UAT, prod) for investigation, debugging, or data verification. Triggers on "check the database", "query eventstore", "subscription lag", "look at UAT", "check QA database", "oban jobs", "read model state", or any database investigation request.

tomevault-io Bundle

Use when creating llmring.lock file for new project (REQUIRED for all applications), configuring model aliases with semantic task-based names, managing environment-specific profiles (dev/staging/prod), or setting up fallback models - lockfile creation is mandatory first step, bundled lockfile is only for llmring tools

tomevault-io Bundle

Write and run Playwright UI E2E tests for Kagenti - login, navigation, agent chat, across CI/Kind/HyperShift Use when this capability is needed.

tomevault-io Bundle

Rules and steps for creating a compute kernel in RL.cu project. Use when this capability is needed.

tomevault-io Bundle

Build, inspect, edit, and install Yanzi extensions. Use when an agent needs to create or modify `manifest.json`, author C# or PowerShell extensions, call Yanzi's local extension HTTP API, or troubleshoot extension loading and execution. Use when this capability is needed.

tomevault-io Bundle

ghostex-agent-orchestration

tomevault-io Bundle

Guides use of the debug_state tool and runtime introspection to diagnose agent issues between turns. Load this skill when something goes wrong during a session and you need to inspect agent state, token usage, event history, or tool availability. Use when this capability is needed.

tomevault-io Bundle

Use this skill for vague, high-rework planning work that needs iterative human decisions, such as product design, research planning, technical strategy, PRDs, workflow design, agent design, or skill design. Run concise P2A decision rounds, challenge assumptions early, record decisions in PLAN.md, DECISIONS.md, and OPEN_QUESTIONS.md, then produce FINAL_PLAN.md when converged. Do not use for simple factual Q&A, routine coding fixes, direct execution, translation, writing polish, or one-shot requests.

tomevault-io Bundle

Use this skill whenever the prompt contains any `github.com` URL, even if the user only pastes a link and gives no GitHub-specific keywords. Handles git and GitHub operations using the gh CLI. Triggers include any GitHub link to an issue, pull request, commit, compare page, Actions run, release, discussion, or repository. Covers creating and reviewing PRs, watching CI checks, interactive rebasing, branch cleanup, submodule management, and repository archaeology with git log/blame/bisect.

tomevault-io Bundle

IMPORTANT: How to Use This Skill

tomevault-io Bundle

Use when migrating a Microsoft 365 Agents SDK agent that uses ActivityHandler or TeamsActivityHandler to AgentApplication. This is ONLY for DotNet projects that uses `Microsoft.Agents.*` packages. Triggered by Agents SDK bots that subclass ActivityHandler or TeamsActivityHandler that need to be modernized to AgentApplication routing.

tomevault-io Bundle

Use when working on the Chat Customizations editor — the management UI for agents, skills, instructions, hooks, prompts, MCP servers, and plugins.

tomevault-io Bundle

Reconfigure pi-ds4/ds4 local DeepSeek V4 Flash by editing ~/.pi/ds4/settings.json. Use when the user asks how to configure, reconfigure, change settings, switch model quant/protocol/runtime, or debug pi-ds4 configuration. Use when this capability is needed.

tomevault-io Bundle

Use when working with local Muesli meetings, notes, dictations, or raw transcripts through the bundled `muesli-cli` CLI. Prefer this skill when a coding agent needs to inspect transcripts, summarize meetings with its own model, or write notes back into Muesli without requiring the user's API keys.

tomevault-io Bundle

Log session activity to the vault's AGENT_ACTIVITY.md ledger. Use at the end of every session to ensure cross-agent context and updates are tracked across all AI agents (Gemini, Pi, Claude, etc.). Use when this capability is needed.

tomevault-io Bundle

Use `nuwa-id` (from identity-kit) to run a DIDAuth flow on `id.nuwa.dev`. The agent generates a key locally, sends a deep link to the user, asks user to return DID text, verifies key binding, then sends authenticated HTTP requests. Use when this capability is needed.

tomevault-io Bundle

Draft a release announcement blog post for an obot release, modeled on the existing obot.ai blog voice. Use when the user asks to draft a release blog, write a launch post, or write a blog announcement for a vX.Y.0 release. Outputs a markdown file the user can paste into the CMS. Can also create the post as a Wordpress draft via the `obot-wordpress` MCP server when the user asks, but never publishes a live post without explicit confirmation. Use when this capability is needed.

tomevault-io Bundle

Fine-tune MiniCPM5-1B with LLaMA-Factory (YAML-driven SFT / DPO / WebUI). Use when the user wants to fine-tune via LLaMA-Factory, llamafactory-cli, mentions YAML configs, WebUI, or asks for the most-documented community framework. Use when this capability is needed.

tomevault-io Skill

Soul-Bound Keys and Soulchain for persistent agent identity, reputation, and messaging. The identity primitive for the agentic web. Use when this capability is needed.

tomevault-io Bundle

Go repository intelligence for Claude Code. Use whenever the user is reading, navigating, editing, reviewing, or refactoring a Go codebase. Replaces grep/rg/find for Go symbols with AST-accurate call graphs, blast radius analysis, impact analysis, and 57+ semantic queries via the local gograph MCP server. Mandatory for Go work whenever the gograph MCP server is connected. Use when this capability is needed.

tomevault-io Bundle

Find Contracts for a Hugging Face Model

tomevault-io Bundle

Review a PR against the Pascal architectural rules — package boundaries (core/viewer/editor/nodes), the registry-driven composition model (def.geometry / def.renderer / def.system), legacy-dispatch regressions, the slots + world-scale-UV convention for new nodes/geometry, hook hygiene (useEditor/useScene/useViewer), and selector performance. Use when the user asks to review a PR, audit a branch, or check that changes respect the codebase's architecture. Use when this capability is needed.

tomevault-io Bundle

Interruption pattern detection and retrieval from Amp thread history. Use for analyzing tool rejection patterns and improving agent behavior. Use when this capability is needed.

tomevault-io Bundle

Agreement protocol in multi-agent systems Use when this capability is needed.

tomevault-io Bundle

CUDA and GPU development with Flox. Use for NVIDIA CUDA setup, GPU computing, deep learning frameworks, cuDNN, and cross-platform GPU/CPU development. Use when this capability is needed.

tomevault-io Bundle

面向 Henji-AI 的模型与供应商适配工作流。用于“新增供应商”“给现有供应商新增模型”“模型和供应商都要新增”“校对参数顺序/隐藏参数/默认请求值”这类需求；先输出确认清单，用户确认后再实施。 Use when this capability is needed.

tomevault-io Bundle

用于新建 Agent、首次安装后的默认 Agent 启动、或会话重新创建后的首轮培训。 Use when this capability is needed.

tomevault-io Bundle

Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server. Use when this capability is needed.

tomevault-io Bundle

Connect to A2A protocol agents from Castella. Communicate with agents, display agent cards, send messages, handle responses, and stream results. Use when this capability is needed.

tomevault-io Bundle

Enable AI agents to introspect and control Castella UIs via MCP. Create MCP servers, expose UI resources, handle MCP tools, and use semantic IDs. Use when this capability is needed.

tomevault-io Bundle

Git worktree manager for AI agent workflows. Use this skill whenever the user wants to work on a branch in isolation, check out a PR, run parallel tasks, manage stacked PRs, sync branches, or dispatch a Claude Code agent to a task. Also trigger when the project uses willow — look for a ~/.willow directory, ww commands in shell history, or a willow.json config. Prefer ww commands over raw git checkout/branch/worktree. Use when this capability is needed.

tomevault-io Bundle

Audit and sync agent instruction files across all coding agent formats. FRE (first-run) checks scaffolding completeness; ongoing use keeps files in sync after edits. Use when this capability is needed.

tomevault-io Bundle

Use when updating an Inconvo agent semantic model or user-context from code context. Covers the full CLI mutation workflow — tables, columns, relations, conditions, policies, virtual tables, computed columns, and user-context — using `inconvo model` and `inconvo connection` commands.