LucaNerlich
- 5 skills
- 0 followers
- 1 week ago last updated
- ▌ Ingest · lucanerlich bundleIngest fresh source documents into the AI Wiki knowledge base. Use whenever the user asks to ingest, process, import, or "catch up" new sources in raw/ — clippings or PDFs awaiting processing, or says "add this to the wiki". Reads each source in full, then creates/updates source, entity, concept, and topic pages, refreshes index.md / overview.md / log.md, and marks sources processed. Queries Index.base and Glossary.base through the Obsidian CLI to find existing pages and avoid duplicates instead of reading large files into context.
- ▌ Search · lucanerlich bundleSearch the AI Wiki knowledge base by keyword and return all relevant pages and sources, ranked, with wikilinks and one-line descriptions. Use whenever the user asks to find, look up, search for, or "what do we have on" a topic in the wiki, lists keywords to research, or asks a question the wiki likely answers. Queries Index.base and Glossary.base plus full-text search through the Obsidian CLI for context efficiency, reads only the top matches, and offers to synthesize the answer into an analysis page.
- ▌ Release Version · lucanerlichAutomate project releases — updates CHANGELOG.md, bumps the version in package.json, commits, tags, and pushes. Use this skill whenever the user says "release", "bump version", "cut a release", "new version", "update changelog and release", "ship it", "tag a release", "prep a release", or asks to bump a patch/minor version. Also trigger when the user asks to update the changelog and push a new version, or when they mention versioning workflow, release workflow, or semver bumping in the context of a Node/JS project with a package.json.
- ▌ Session Summary · lucanerlichSummarize the current coding session and write structured notes into Obsidian. Use when the user says "summarize session", "write session notes", "session debrief", "log what we did", "write a summary", or asks to document what happened in the session.
- ▌ Codebase Cleanup · lucanerlichDeep codebase cleanup and code quality improvement using 8 specialized subagents. Use this skill whenever the user wants to clean up their codebase, improve code quality, reduce complexity, remove dead code, fix types, untangle dependencies, or generally whip a project into shape. Triggers include phrases like "clean up my codebase", "improve code quality", "remove dead code", "fix my types", "untangle dependencies", "remove slop", "code hygiene", "tech debt", "refactor", or any request that involves systematically improving an existing codebase across multiple dimensions. Even if the user only mentions one aspect (e.g., "find unused code"), consider whether the full sweep would serve them better and offer it.