wiki-manager
Manage LLM-compiled wikis: initialize, ingest/import, compile/query, research/audit, collect…
Fast, read-only, index-first llm-wiki queries for OpenCode and compatible instruction-file harnesses.
$ npx -y skills add nvk/llm-wiki --skill wiki-query --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/wiki-queryContext preview
The summary Claude sees to decide when to auto-load this skill.
Fast, read-only, index-first llm-wiki queries for OpenCode and compatible instruction-file harnesses.
name: wiki-query description: > Fast, read-only, index-first llm-wiki queries for OpenCode and compatible instruction-file harnesses.
Use this protocol for fast, read-only questions and inventory lookups. It is the canonical query profile shared by Claude, Codex, Pi, local models, and the portable fallback.
lint, rebuild indexes, or append query logs.
or every sibling topic.
in sources and articles.
not answer the question.
1. If the request says `--local`, or the current project contains `.wiki/`, use `<cwd>/.wiki` and read `.wiki/_index.md` first. 2. Otherwise read `~/.config/llm-wiki/config.json`. Expand only a leading `~` in `hub_path`. If unavailable, try `resolved_path`, then `~/wiki`. 3. At a hub, read `<hub>/_index.md` and `<hub>/wikis.json`. Choose exactly one active topic from its title, aliases, summary, or an explicit `--wiki NAME`. Resolve registry paths relative to the hub; if stale, try `<hub>/topics/NAME`. 4. For a selected topic, read its `_index.md`, then only the relevant branch index: `wiki/_index.md`, `raw/_index.md`, `inventory/_index.md`, `datasets/_index.md`, or `output/_index.md`. 5. Follow index links to the minimum exact files needed. Follow article source links only when provenance or primary evidence matters. 6. Use one targeted search inside the selected wiki only if indexes do not identify the answer. Bound the pattern and result count.
If topic choice is genuinely ambiguous, list at most three index-derived candidates and ask one short question instead of scanning multiple topics.
insufficient.
about candidates, status, priority, or next actions.
LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.
Manage LLM-compiled wikis: initialize, ingest/import, compile/query, research/audit, collect…