olafgeibig
- 13 skills
- 0 followers
- 4 hours ago last updated
- ▌ Skill Builder 2 · olafgeibig bundleUse this skill when creating new Claude Code skills from scratch, editing existing skills to improve their descriptions or structure, or converting Claude Code sub-agents to skills. This includes designing skill workflows, writing SKILL.md files, organizing supporting files with intention-revealing names, and leveraging CLI tools and Node.js scripting.
- ▌ Vault Ops · olafgeibig bundleUse this skill when working with a markdown notes vault such as Obsidian. It defines a default workflow for selecting a vault, reading vault-local instructions, navigating notes, writing regular notes, and maintaining Maps of Content (MoCs). Triggers: vault, obsidian, notes vault, moc, map of content, markdown notes.
- ▌ Vault Wiki · olafgeibig bundleMulti-domain LLM Wiki in vault — build and maintain a federation of interlinked markdown wiki knowledge bases inside your Obsidian vault. Each domain wiki has its own schema, index, and log, linked across boundaries via path-based wikilinks. Use when user wants to use a wiki (create, ingest into, query, lint).
- ▌ Container Use · olafgeibig bundleUse this skill when working with Apple Containers (lightweight Linux VMs) as a native Docker replacement on macOS. This includes building container images, running containers, managing container lifecycle, configuring networking, handling volumes, mounting files with SSH forwarding, or performing multi-platform builds. Invoke for tasks involving the container CLI, Apple container tool, or Linux containers on Apple Silicon macOS 26+.
- ▌ Skill Builder · olafgeibig bundleUse this skill when creating new Claude Code skills from scratch, editing existing skills to improve their descriptions or structure, or converting Claude Code sub-agents to skills. This includes designing skill workflows, writing SKILL.md files, organizing supporting files with intention-revealing names, and leveraging CLI tools and Node.js scripting.
- ▌ Turbovault Use · olafgeibig bundleSafe and effective use of TurboVault MCP tools — vault selection, active vault management, read/write/edit_note patterns, SEARCH/REPLACE syntax, search tools, graph tools, batch operations, verification, and troubleshooting. Load this skill whenever a task uses mcp_turbovault_* tools.
- ▌ Plantuml Syntax · olafgeibig bundleAuthoritative reference for PlantUML diagram syntax. Provides UML and non-UML diagram types, syntax patterns, examples, and setup guidance for generating accurate PlantUML diagrams.
- ▌ Explore Codebase · olafgeibig bundleExplore and understand codebases. Use this when analyzing source code, manifests and other config for software engineering tools like kubernetes, helm, terraform. Usually the codebases are cloned git repositories in a directory `./repos/`
- ▌ Ob Headless Sync · olafgeibigObsidian Headless Sync — systemd timer monitoring, diagnostics, and recovery for the ob sync service on headless machines
- ▌ Skill Governance · olafgeibigUse this skill whenever creating, maintaining, or self-improving ANY skill, and especially before an agent patches a skill in an external_dirs repository. It defines the two skill ownership classes (own vs third-party), the decision matrix for routing generic / project-specific / agent-specific improvements, and the mandatory read-before-write and promotion-freeze rules. Triggers: skill governance, skill maintenance, self-improvement, improve a skill, patch a skill, update a skill, skill scope, skill ownership.
- ▌ Transcript Fixer · olafgeibig bundleUse this skill when fixing speech-to-text transcripts, meeting transcripts, interview notes, or ASR output with misheard names, product terms, acronyms, or domain vocabulary. Uses project-local config, glossary files, deterministic corrections, and native agent review. No internal AI API calls; optional scripts only apply configured replacements and extract glossary terms.
- ▌ Summarize Meeting · olafgeibigSummarize a meeting transcript into structured notes with date, participants, topic, key decisions, summary points, and action items. Use when processing meeting recordings, creating meeting notes, writing meeting minutes, or recapping discussions.
- ▌ Lightrag Deep Research · olafgeibigDeep research workflow over an internal LightRAG knowledge base (no web search). Use when you need an in-depth investigation with a structured plan, iterative sub-questions, evidence gathering via LightRAG queries (local/global/hybrid/mix/naive), synthesis, and KB-citations. Best for: architecture/security research, incident retrospectives, design decisions, policy interpretation, and any question that should be answered primarily from your organization’s knowledge base.