Import a wiki knowledge graph into the current vault — either from a graph.json export file (stubs) or from an OKF (Open Knowledge Format) markdown bundle (full page bodies). Use this skill when the user says "import wiki", "import from export", "load graph.json", "import vault", "import OKF bundle"

Wiki Import — Reconstruct Pages from an Export You are importing a vault's knowledge into the current vault from one of two sources produced by wiki export : graph.json — the graph skeleton. Reconstructs page stubs (frontmatter, typed relationships, a Related link list — no body). Lossy. OKF bundle (a wiki export/okf/ directory) — the actual markdown files. Reconstructs full pages with their real bodies. Lossless. Use this for true vault to vault transfer. Either way, the import writes pages with correct frontmatter and wikilinks, then updates all vault metadata. Step 2, Step 3 (graph only), and Step 5 are shared; Step 4 forks by source type. Before You Start Writing profile: Before drafting or rewriting natural language Markdown, read and apply the Writing Profile Resolution section in llm wiki/SKILL.md . Framework schema, provenance, safety, and operation specific requirements take precedence. Preserve imported source prose; apply WRITING.md preferences only to newly generated metadata or stubs. 1. Resolve config — follow the Config Resolution Protocol in llm wiki/SKILL.md (inline @name override → walk up CWD for .env → global config → prompt setup). This gives OBSIDIAN VAULT PATH . 2. Read $OBSIDIAN VAULT PATH/AGENTS.md if it exists — apply any owner specific conventions. Step 1: Locate and Detect Source Type Find the import source: If the user provided a path argument, use it directly. Otherwise auto detect, in order: ./wiki export/okf/ (a directory) → ./wiki export/graph.json (a file). If neither exists, ask the user for the path. Detect the source type: The path is a file ending in .json → graph.json import (validate below, then Step 3 + Step 4 Graph). The path is a directory containing .md files with OKF frontmatter (a type: key), and/or a root index.md with okf version → OKF bundle import (skip Step 3; go to Step 4 OKF). Both okf version 0.1 and 0.2 bundles are accepted; Step 4 OKF reads either. Anything else → report what's wrong and stop. Validate a graph.json source: Must be valid JSON Must have top level keys: nodes (array), links (array), graph (object) Must have at least 1 node If validation fails, report what's wrong and stop. Validate an OKF bundle source: Must contain at least 1 non reserved .md file (i.e. not index.md / log.md ) with parseable YAML frontmatter containing a non empty type . A .md with no frontmatter or no type is skipped (with a count), not fatal — OKF consumers are permissive (OKF §11). Show a preview before importing: graph.json: OKF bundle: Step 2: Determine Conflict Resolution Mode Read the user's phrasing to determine mode. Default is merge . Mode Trigger phrases Behaviour merge (default, no special phrasing) Existing pages: update frontmatter tags/summary/relationships and add missing wikilinks; new pages: create stub. skip "skip existing", "don't overwrite", "only new pages" Leave existing pages completely untouched; only create pages that don't exist yet. overwrite "overwrite", "replace existing", "force import" Replace all matched pages with freshly reconstructed stubs regardless of existing content. Step 3: Build Internal Maps (graph.json only — skip for OKF bundles) Before writing anything, build two maps from the links array: Adjacency map — for each node id, collect all neighbour ids (edges in either direction): Typed edge map — for each node id, collect outgoing typed edges only ( typed: true ): Step 4 Graph: Reconstruct Pages from graph.json (graph.json source only) Record counts: created = 0 , skipped = 0 , merged = 0 . For each node in nodes : 1. Compute page path = $VAULT/<node.id .md 2. Ensure the parent directory exists (e.g. $VAULT/concepts/ ) 3. Check if the file already exists: merge mode (default) + exists → read existing file, apply merge logic (see below), increment merged merge mode (default) + doesn't exist → proceed to create stub, increment created skip mode + exists → increment skipped , continue to next node skip mode + doesn't exist → proceed to create stub, increment created overwrite mode + exists → proceed to write fresh stub (overwrite), increment merged overwrite mode + doesn't exist → proceed to create stub, increment created Page template (new or overwrite) If adjacency[node.id] is empty, omit the Related section entirely. Merge logic (merge mode, existing page) 1. Read the existing page's frontmatter. 2. Tags : union of existing tags and node.tags (deduplicated, keep existing order, append new ones). 3. Summary : if the existing page has no summary field and node.summary exists, add it. 4. Relationships : union of existing relationships: entries and typed edges[node.id] — skip entries where the same (target, type) pair already exists. 5. Updated : set updated to the current ISO timestamp. 6. Body : scan for a Related section. If it exists, append any missing wikilinks from adjacency[node.id] that aren't already linked anywhere in the body. If no Related section exists, append one with the missing links. 7. Leave the rest of the body untouched. Step 4 OKF: Reconstruct Pages from an OKF bundle (OKF source only) Record counts: created = 0 , skipped = 0 , merged = 0 , unparseable = 0 . Walk the bundle directory tree. For each .md file that is not a reserved file ( index.md , log.md ): 1. Parse the YAML frontmatter. If it has no frontmatter or no non empty type , increment unparseable and skip the file. 2. Compute the concept id = the file's path relative to the bundle root, with .md stripped (e.g. concepts/transformers.md → concepts/transformers ). The target page is $VAULT/<concept id .md . 3. Reverse map frontmatter (the inverse of the canonical mapping table in wiki export Step 3.5): title ← title . category ← the preserved category extension key if present; else lower case the directory prefix of the concept id ( concepts/… → concepts ); else derive from type ( Concept → concepts , Entity → entities , Skill → skills , Reference → references , Synthesis → synthesis , Project → projects , Journal → journal ). tags ← tags . summary ← description . updated ← the preserved updated extension key if present; else generated.at ; else a legacy v0.1 timestamp ; else now. created ← the preserved created extension key if present, else now. sources ← OKF sources , as a list of strings: for each entry that is a mapping, take its resource ; keep plain strings as is (that's how v0.1 bundles from older exports carried our native list). If the bundle has no sources , use ["imported from OKF bundle <bundle path "] . If a top level resource URL is present and not already in the list, add it. lifecycle ← the preserved lifecycle extension key if present; else from status : draft → draft , deprecated → archived , stable or absent → leave lifecycle unset. (OKF has no equivalent of reviewed / verified / disputed , so only our own exports restore them, through the preserved key.) Carry through any other preserved extension keys verbatim ( relationships , lifecycle changed , tier , base confidence , …), and the OKF only keys generated , verified , stale after , and usage window so a later export doesn't lose them. These make the round trip lossless. Treat a bare verified mapping as a one element list (OKF §5.2). Except what our own exporter derived. Drop generated when generated.by starts with obsidian wiki/ (it was computed from updated ), and drop verified entries whose by is human:vault owner (computed from the source vault's trust ledger, which doesn't travel). Keeping them would add keys the source page never had. Generated or verified blocks from any other producer are kept. 4. Reverse transform body links — markdown links that point at .md paths become wikilinks (this restores both real cross links and forward references the exporter preserved per wiki export Step 3.5): [text](../concepts/transformers.md) or [text](/concepts/transformers.md) → resolve the path (relative to this file's dir, or bundle root for / absolute) to a concept id → [[concepts/transformers]] , or [[concepts/transformers text]] when text differs from the target's title. The target's title comes from the bundle page when it exists; otherwise the exporter wrote the target's id as the link text, so treat text equal to the full id (or to its last path segment) as no alias. Treat the markdown target as a file path first : normalize the .md path relative to the current file, then strip the trailing .md from the resolved file path to recover the page id. Do not try to infer the id from directory traversal segments before resolving the full file path. This preserves round trips for folder note layouts like projects/social twitter.md plus projects/social twitter/... , where ../../social twitter.md must restore to projects/social twitter . This applies even when the target page is not in the bundle — a path form link to a not yet written page round trips back to a dangling [[wikilink]] (Obsidian supports these; OKF §11 forbids rejecting them). Do not leave it as a markdown link. When OBSIDIAN LINK FORMAT=markdown is set in config, keep markdown links (just rewrite the path to be vault relative); do not convert to wikilinks. Leave external http(s):// links and Citations sections untouched. 5. Write the page using the conflict mode from Step 2: merge + exists → reverse map frontmatter and merge it into the existing page (union tags ; fill summary / sources only if missing; union relationships ; refresh updated ). For the body, OKF carries a real body: replace the existing body with the bundle body only if the existing page is a stub (body is just a heading + Related ); otherwise keep the existing body and append any bundle Citations / new sections not already present. Increment merged . merge + doesn't exist → write the full page (frontmatter + full bundle body). Increment created . skip + exists → increment skipped , continue. skip + doesn't exist → write the full page. Increment created . overwrite + exists → write the full page, replacing the existing one. Increment merged (label as Replaced in the summary). overwrite + doesn't exist → write the full page. Increment created . 6. Ensure the parent directory ( $VAULT/concepts/ , etc.) exists before writing. Unlike the graph.json path, do not generate a Related stub section — the bundle body already contains the real cross links. Step 5: Update Vault Metadata .manifest.json Add a new entry keyed by the canonical path of the graph.json file: Set source type to "wiki export" for a graph.json import or "okf bundle" for an OKF bundle import. Key the entry by the absolute path of the source (the graph.json file or the bundle directory). Also increment: stats.total sources ingested by 1 stats.total pages by the count of pages actually created (not skipped/merged) If .manifest.json doesn't exist, create it with the standard structure: index.md , log.md , and hot.md One locked call. The index is reconciled from the pages now on disk, so every created or merged page lands under its category with the documented ( tag) spacing: Omit takeaways if the import does not shift the overall picture; the previous takeaways carry across. Never hand edit index.md , log.md , or hot.md — the command takes the lock that keeps a parallel writer from dropping your update. See .skills/llm wiki/references/MEMORY.md for the full procedure. Step 6: Print Summary Only

wiki-import