wiki-manager
Manage LLM-compiled wikis: initialize, ingest/import, compile/query, research/audit, collect…
Manage LLM-compiled wikis in Codex: ingest/import, shape/promote Ideas, review portfolios, track inventory/datasets, archive, compile/query/lint/audit, research/plan, manage sessions, private adapters, personal specialists, and outputs. Activates when the user mentions wiki
$ npx -y skills add nvk/llm-wiki --skill wiki --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/wikiContext preview
The summary Claude sees to decide when to auto-load this skill.
Manage LLM-compiled wikis in Codex: ingest/import, shape/promote Ideas, review portfolios, track inventory/datasets, archive, compile/query/lint/audit, research/plan, manage sessions, private adapters, personal specialists, and outputs. Activates when the user mentions wiki
name: wiki description: > Manage LLM-compiled wikis in Codex: ingest/import, shape/promote Ideas, review portfolios, track inventory/datasets, archive, compile/query/lint/audit, research/plan, manage sessions, private adapters, personal specialists, and outputs. Activates when the user mentions wiki workflows, knowledge-base management, ingestion, collection ingestion, import wiki, collect, catalog, curate, find all, idea, turn idea into project, portfolio, business ideas, projects, inventory, source queue, candidate list, watch list, backlog, dataset, large data, data registry, dataset manifest, compilation, querying, linting, audit, research, librarian, scan quality, article quality, content review, output drift, provenance, archive wiki, archive topic, restore wiki, private adapter, adapter registry, skill-factory, checkpoints, personal specialist, specialist skill, specialist reviewer, expert lens, adapter route, adapter doctor, adapter run, read, review, or edit a hosted external resource such as a document, session capture, capture context, rehydrate, resume from session, implementation plan, or uses /wiki-style shorthand in a repo with .wiki/, ~/wiki/, or a configured hub path.
You manage an LLM-compiled knowledge base. Source documents are ingested into `raw/`, then incrementally compiled into a wiki of interconnected markdown articles. Codex is both the compiler and the query engine.
Codex plugins package skills, MCP servers, apps, and metadata. They do not register Claude-style custom `/wiki:*` commands. Treat any `/wiki`, `/wiki:*`, or command-flag examples in this skill and its references as shorthand for the same workflow expressed in natural language, or via explicit `@wiki` invocation.
**Resolution**: At the start of every operation, resolve **HUB** by reading `~/.config/llm-wiki/config.json` first. Prefer `hub_path`: expand the leading `~` only (not tildes in `com~apple~CloudDocs`) on the current machine. Treat `resolved_path` as a legacy cache only: use it when no `hub_path` exists, or as a fallback if the expanded `hub_path` is unavailable and `resolved_path` is initialized. Do not write machine-specific `resolved_path` values into shared configs. If no config file exists, try `~/wiki/_index.md` as a fallback. If `stat`/existence checks succeed but reading `wikis.json` or listing `topics/` fails with `Operation not permitted`, the hub path is correct and macOS is blocking this process; tell the user to grant Full Disk Access or iCloud Drive access to the exact app launching the agent and restart. Do not switch to `~/wiki` or `resolved_path` for that error. See [references/hub-resolution.md](references/hub-resolution.md) for the full protocol.
The config file looks like:
{
"hub_path": "~/Library/Mobile Documents/com~apple~CloudDocs/wiki"
}If no config exists and `~/wiki/` has `_index.md`, that works too. But config is checked first — in sandboxed environments `~/wiki/` may not be accessible. All references to `~/wiki/` below mean HUB.
**Topic sub-wikis are the default.** HUB is a hub — content lives in `HUB/topics/<name>/`. Each topic gets isolated indexes, sources, and articles. This keeps queries focused and prevents unrelated topics from polluting each other's search space.
For collection families that will grow across subjects, prefer kind-first topic slugs such as `memes-bitcoin`, `memes-ethereum`, `tools-bitcoin`, or `examples-seedqr`. Use subject-first slugs when the subject is the primary research area and the collection is only one artifact within that topic.
Resolution order:
1. `--local` flag → `.wiki/` in current project 2. `--wiki <name>` flag → named wiki from `HUB/wikis.json`; resolve registry paths as `<HUB>`, `~`, absolute, or relative to HUB, and fall back to `HUB/topics/<name>` if a registry path is stale 3. Current directory has `.wiki/` → use it 4. Otherwise → HUB (the hub)
When a command targets the hub and the hub has no content, suggest creating a topic sub-wiki instead.
See [references/wiki-structure.md](references/wiki-structure.md) for the complete directory layout and all file format conventions.
1. **Indexes are a derived cache.** The `.md` files and their YAML frontmatter are the source of truth. `_index.md` files are a cached view rebuilt on read when stale. Always read indexes first for navigation — but before trusting one, stale-check it (file count vs row count). See [references/indexing.md](references/indexing.md) for the Derived Index Protocol.
2. **Raw is immutable.** Normal workflows never modify ingested sources. Explicit retraction runs first via hidden-input `scripts/llm-wiki retract`; content, archives, and sessions cannot veto it.
3. **Articles are synthesized, not copied.** A wiki article draws from multiple sources, contextualizes, and connects to other concepts. Think textbook, not clipboard.
4. **Dual-linking for Obsidian + Codex.** Cross-references use both `[[wikilink]]` (for Obsidian graph view) and standard markdown `[text](path)` (for Codex navigation) on the same line: `[[slug|Name]] ([Name](../category/slug.md))`. Bidirectional when it makes sense.
5. **Frontmatter is structured data.** Every `.md` file has YAML frontmatter with title, summary, tags, dates. This makes the wiki searchable without full-text scans.
6. **Incremental over wholesale.** Compilation processes only new sources by default. Full recompilation is expensive and explicit (`--full`).
7. **Honest gaps.** When answering questions, if the wiki doesn't have the answer, say so. Never hallucinate. Suggest what to ingest to fill the gap.
8. **Multi-wiki awareness.** When querying, answer from the primary wiki first. Then peek at sibling wiki indexes (via `HUB/wikis.json`) for relevant overlap. Flag connections but never merge content across wikis.
9. **Chunk large writes.** Never create fi
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…
Fast, read-only, index-first llm-wiki queries for OpenCode and compatible instruction-file…