Skip to main content
skill CX Codex

wiki-retrieve — Claude Code skill for vault search

wiki-retrieve builds a local BM25 index from wiki/ notes and finds relevant passages. Use it when an agent needs matching pages to read before answering a question.

MIT 348 installs ★ 16,676 updated 2026-10-22

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add AgriciDaniel/claude-obsidian --skill wiki-retrieve -a claude-code
Open on GitHub

What wiki-retrieve does

wiki-retrieve splits pages into chunks, adds a short page-level context prefix, then indexes the resulting text with BM25. Search returns paths and snippets; the agent reads those pages and produces its own synthesis. Index data and derived files live in .vault-meta, while canonical notes remain unchanged.

Optional reranking uses a multilingual Nomic model through Ollama. If the model or service is unavailable, results fall back to their original BM25 order. Remote Ollama endpoints and the Anthropic API require explicit consent and the relevant flags before page text can leave the machine. Run the scripts with Python 3 and pass the target vault using --vault.

What it helps with

  • find relevant passages in wiki/ notes
  • build a local BM25 index for a vault
  • rerank search candidates with a Nomic model
  • inspect index statistics and BM25 results

Example prompts for the agent

  • Search wiki/ for notes about retrieval setup and return five passages without reranking.
  • Build the index for this vault, then explain the results for the query wiki.
  • Rerank the matches with nomic-embed-text if that model is already installed in Ollama.

How to install wiki-retrieve

1Skills CLI (Vercel)

npx skills add AgriciDaniel/claude-obsidian --skill wiki-retrieve -a claude-code

2Manually: put the files in place

~/.claude/skills/wiki-retrieve/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/wiki-retrieve/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about wiki-retrieve

How do I install wiki-retrieve in Claude Code?

Run npx skills add AgriciDaniel/claude-obsidian --skill wiki-retrieve -a claude-code. The skill file is available at ~/.claude/skills/wiki-retrieve/SKILL.md.

What does wiki-retrieve do?

It builds a local BM25 index from notes in wiki/ and returns matching passages with their page paths. The agent reads those pages and creates the answer separately.

Does search require an embedding model?

No. The base search uses BM25, and Ollama-based reranking is optional. If the selected model or service cannot be used, results retain their BM25 order.

Source text

SKILL.md · MIT
---
name: wiki-retrieve
description: "Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta, remote egress requires explicit consent, and unavailable reranking falls back deterministically."
---

# Retrieve relevant passages

This extension derives search data from `wiki/` into `.vault-meta/`. It never
changes canonical notes. Always pass the selected vault explicitly.

Resolve the installed product root from this skill's own location, not from the
vault or current working directory:

```bash
PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian
PREFIX="$PRODUCT_ROOT/scripts/contextual-prefix.py"
BM25="$PRODUCT_ROOT/scripts/bm25-index.py"
RETRIEVE="$PRODUCT_ROOT/scripts/retrieve.py"
RERANK="$PRODUCT_ROOT/scripts/rerank.py"
test -f "$PREFIX" && test -f "$BM25" && test -f "$RETRIEVE" && test -f "$RERANK"
```

## Pipeline

1. `contextual-prefix.py` splits pages on paragraph boundaries and stores the
   raw chunk plus a short page-level prefix.
2. `bm25-index.py` builds a local, standard-library BM25 index over the
   contextualized text.
3. `retrieve.py` selects BM25 candidates, optionally reranks them, rejects
   invalid records, deduplicates by page, and returns paths and snippets.
4. The caller reads the returned pages and performs synthesis; retrieval output
   is not itself evidence.

## Provision locally

Preview first, then build synthetic prefixes without network egress:

```bash
python3 "$PREFIX" --vault "$VAULT" --all --no-llm --peek
python3 "$PREFIX" --vault "$VAULT" --all --no-llm
python3 "$BM25" --vault "$VAULT" build
python3 "$RETRIEVE" --vault "$VAULT" "wiki" --top 1 --no-rerank --explain
```

Chunk and index files are disposable runtime state. Incremental prefixing skips
records whose chunk hashes, page hashes and provider/model profile still match.
Legacy records without that profile regenerate on an explicit build. A complete scan removes
surplus records for deleted pages, and the prefixer invalidates the BM25 index
before changing its chunk set so a mixed stale index is not served.
Prefix and BM25 build operations share the vault-wide mutation lock with every
other writer; a busy vault fails closed instead of publishing a partial index.

## Contextual-prefix privacy

Synthetic prefixes use only local frontmatter and page text. The explicit
Anthropic API profile can send page bodies off-machine and requires the user's
consent plus `--allow-egress` and a configured API key. There is no Claude CLI
generation tier or ambient subprocess fallback. Never infer consent from an
API key or installed binary. Preview the scope first and state which provider
will receive what data.

Remote Ollama endpoints also require explicit approval and
`--allow-remote-ollama`; the default reranker accepts localhost only.

Local model prefixes are a separate explicit option. Use an already installed
exact `name:tag`; no server is started and no model is installed or pulled:

```bash
python3 "$PREFIX" --vault "$VAULT" --all --local-ollama --ollama-model installed:tag --peek
python3 "$PREFIX" --vault "$VAULT" --all --local-ollama --ollama-model installed:tag
```

The prefix adapter verifies cloud-disabled server status and local model
identity before sending page text. Unsupported or unavailable preflight falls
back to synthetic prefixes for new or changed chunks only; prefixes from the
same endpoint and model stay in place, so a transient outage leaves an
unchanged vault's chunks and BM25 index untouched. This requirement can exclude
older Ollama servers.
Reranking and tiling use the same local-only proof before query, page, chunk,
or embedding cache work. `--allow-remote-ollama` approves the endpoint, not
cloud delegation by the server.
See [prefix providers](../../docs/prefix-providers.md) for the exact policy,
cloud model selection and verification limits. The reranker has its own model
and endpoint policy; selecting local prefixes does not enable reranking.

## Query

For a strictly read-only lookup, use the prebuilt BM25 index:

```bash
python3 "$RETRIEVE" --vault "$VAULT" "$QUERY" --top 5 --no-rerank --explain
```

For an explicitly requested rerank, omit `--no-rerank`. The default is Ollama's
multilingual `nomic-embed-text-v2-moe` model (approximately 958 MB); the product
never pulls it automatically. To use an already-installed, smaller,
English-oriented v1.5 model, pass `--model nomic-embed-text` explicitly.
Nomic models use `search_query:` for the query and `search_document:` for
candidate text. Nomic v2 has a 512-token input context and Ollama truncates
longer embedding inputs by default; BM25 still scores the complete chunk.
Embeddings are cached by exact model, verified digest, input scheme, and hash
of the exact prefixed input. A missing local Ollama service, malformed HTTP
reply, missing selected model, unusable vector, or any candidate embedding
failure falls back for the complete result set to the original BM25 order; it
never mixes cosine and BM25 score scales.

Query input is bounded at 8,000 normalized characters and result counts must be
between 1 and 1,000. Oversized queries and invalid limits fail with an
actionable usage error instead of looking like an empty successful search.
An untagged model request matches only the installed untagged name or its
`:latest` alias; select any other tag explicitly.

Use direct diagnostics when needed:

```bash
python3 "$BM25" --vault "$VAULT" stats
python3 "$BM25" --vault "$VAULT" query "$QUERY" --top 10
python3 "$RERANK" --vault "$VAULT" "$QUERY" --peek
python3 "$RERANK" --vault "$VAULT" "$QUERY" --model nomic-embed-text --peek
```

## Integrity rules

- Accept only relative chunk and page paths whose resolved targets remain under
  `$VAULT/.vault-meta/chunks/` and `$VAULT/wiki/` respectively.
- Reject hashless legacy chunk records and require chunk-body, page, and index
  hashes to match before a cached record can be built or served.
- Reject absolute paths, symlink escapes, missing pages, mismatched chunk IDs,
  changed page hashes, and stale index/chunk hash pairs.
- Rerank the full candidate set, then deduplicate by page, then apply `--top`.
- An empty index is an honest no-result state. A missing or corrupt index makes
  `retrieve.py` exit 10 with a stable rebuild command; callers fall back to the
  standard vault query/text-search path and do not fabricate matches.
- Do not cite benchmark percentages unless a reproducible vault-specific
  benchmark produced them.

Measure a prebuilt index against explicit labels with `bench --queries FILE
--vault VAULT`. See [offline retrieval evaluation](../../docs/retrieval-evaluation.md)
for recall, MRR, missing labels and negative cases. This is a read-only
measurement and never silently rebuilds an index or calls a model.

## Checkpoint

Observe cache readiness and privacy boundaries, think about whether lexical or
semantic ranking is needed, verify returned paths and source freshness, and
grow by measuring retrieval misses against a maintained local query set.

© AgriciDaniel · MIT · AgriciDaniel/claude-obsidian

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set15

The whole set →
wiki-query wiki-query is a Claude Code skill that answers questions from a chosen Obsidian vault without changing its files. It uses the vault as the evidence source. CX Codex +1 512installs wiki-lint wiki-lint runs a deterministic read-only check on an Obsidian vault: dead links, orphan pages, frontmatter gaps. It reports, it does not repair. CX Codex +1 508installs canvas Creates and edits Obsidian boards in JSON Canvas format: text cards, files, links, groups and edges. Useful when you want a visual map of a vault. CX Codex +1 500installs defuddle Plans Defuddle extraction and retains already available local source files. No network cleaning ships with it — just the plan and the capture. CX Codex +1 478installs wiki-fold wiki-fold is a Claude Code skill that builds a rollup from entries in an Obsidian wiki/log.md. It previews the draft first and leaves child pages untouched. CX Codex +1 445installs wiki-mode wiki-mode configures vault filing methodologies like PARA, LYT, or Zettelkasten and suggests destinations for new Obsidian notes without writing files. CX Codex +1 344installs wiki-cli wiki-cli is a Claude Code skill that checks whether the official Obsidian CLI can read a vault, then searches notes; if unavailable, it reads files directly. CX Codex +1 341installs think Applies a ten-stage OBSERVE–LISTEN–THINK–CONNECT–FEEL–ACCEPT–CREATE–GROW cycle to complex decisions, architecture reviews, and incident postmortems. Separates facts from assumptions and surfaces hidden risks. CX Codex +1 337installs

Project sponsors

Companies that keep this analytics open