From llm-wiki
Batch research from research-tasks.json — fetch, ingest, wiki merge. Use when research_loop.enabled for automated passes (e.g. HN front page).
npx claudepluginhub skinnnyjay/wiki-llm --plugin llm-wikiThis skill uses the workspace's default tool permissions.
**Not** ad-hoc topic research — for a user **topic or question**, use **wiki-research** and **`/llm-wiki:research`**.
Creates new Angular apps using Angular CLI with flags for routing, SSR, SCSS, prefixes, and AI config. Follows best practices for modern TypeScript/Angular development. Use when starting Angular projects.
Generates Angular code and provides architectural guidance for projects, components, services, reactivity with signals, forms, dependency injection, routing, SSR, ARIA accessibility, animations, Tailwind styling, testing, and CLI tooling.
Executes ctx7 CLI to fetch up-to-date library documentation, manage AI coding skills (install/search/generate/remove/suggest), and configure Context7 MCP. Useful for current API refs, skill handling, or agent setup.
Not ad-hoc topic research — for a user topic or question, use wiki-research and /llm-wiki:research.
Requires research_loop.enabled: true in llm-wiki/config.json. If false, tell the user to enable it.
llm-wiki/research-tasks.json or research-tasks.yaml (or the path in research_loop.tasks_file; YAML needs pip install pyyaml).run: true (or user-specified id), respect max_items_per_run and delay_seconds_between_fetches.llm-wiki research-loop runs hackernews_top and fetch_urls tasks from the JSON/YAML file; then apply wiki-ingest / wiki-maintainer for anything written to raw/.llm-wiki ingest (e.g. hackernews, url) directly to write into raw/; then apply wiki-ingest / wiki-maintainer.references/hn-example.md for Hacker News API usage and ethics (rate limits, ToS).Do not scrape aggressively; prefer official APIs.
Optional: skills/references/context-persona.md for ingest/tool alignment; persona.name in config (default Gennie).
research_loop.enabled: true confirmed (or user told how to enable it).max_items_per_run respected; new files under raw/; wiki-ingest / wiki-maintainer applied for batch merge when requested.wiki/log.md updated for the loop run when non-trivial.llm-wiki integrations status and any llm-wiki line from Step 1 of this skill (from the vault root).