skillfed

wiki-ingest

wiki-ingest transforms a single source document into a set of durable wiki pages organized across entities, concepts, and synthesis sections. It reads existing space conventions and content to avoid duplication, flags contradictions rather than silently overwriting, and maintains full cross-linking and citation trails back to the original source.

wiki-ingest turns a raw source document into durable, cross-linked wiki pages with proper citations and conflict tracking.

AI-generated summary based on this skill's SKILL.md

9 1 MIT updated by getpaperclipai

Install

getpaperclipai/paperclip/wiki-ingest · repository language: TypeScript

CLI (skillfed)coming soon
git clone https://github.com/getpaperclipai/paperclip
cp -r paperclip/packages/plugins/plugin-llm-wiki/skills/wiki-ingest ~/.claude/skills/wiki-ingest

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I ingest a raw source document into wiki-ingest?

wiki-ingest reads a single source document and transforms it into a set of durable wiki pages organized across entities, concepts, and synthesis sections. The skill reads existing space conventions and content to avoid duplication, then creates cross-linked pages with full citation trails back to your original source material.

What happens when wiki-ingest finds contradictions?

wiki-ingest flags contradictions rather than silently overwriting existing wiki pages. When new source material conflicts with what's already in your wiki, the skill surfaces the conflict for review so you can decide how to resolve it, maintaining data integrity and transparency.

Can wiki-ingest convert raw files to wiki pages?

Yes. wiki-ingest converts unstructured source material into structured wiki entries with proper citations. It processes raw documents—including markdown and other formats—and organizes them into interlinked wiki pages while preserving references back to the source.

Does wiki-ingest create cross-links between wiki concepts?

wiki-ingest creates cross-linked wiki entities and concepts from your captured source document. The skill automatically builds connections between related pages and maintains a full linking structure, making your wiki knowledge base navigable and interconnected.

How does wiki-ingest handle existing wiki content?

wiki-ingest reads your existing space conventions and content before ingesting new material. It avoids duplication by checking what's already there, flags any contradictions it finds, and updates pages only when appropriate—keeping your wiki consistent and well-organized.

What logging and verification does wiki-ingest provide?

wiki-ingest processes operation issues that request wiki ingestion with proper logging and verification. The skill tracks ingestion operations, maintains audit trails, and ensures that all source material is properly verified before being added to your wiki system.

SKILL.md

rendered from the published skill — quoted content, verbatim

Wiki Ingest

Turn one source document into durable, interlinked wiki knowledge.

Inputs

  • An operation issue with operationType: "ingest" assigned to you.
  • A raw/ path mentioned in the issue body (always treat raw/ as immutable).
  • The operation issue's target wikiId, spaceSlug, and space root (otherwise stop and surface the missing config to the requester).

Workflow

  1. Read context first.
  2. Read the target space's AGENTS.md for page conventions (filenames, frontmatter, voice, citation style).
  3. Read the target space's wiki/index.md to see what already exists.
  4. Read the target space's last ~20 entries of wiki/log.md to avoid re-ingesting a source or re-resolving a contradiction someone else already filed.
  5. Read the source end to end with

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 1 file
packages/plugins/plugin-llm-wiki/skills/wiki-ingest/SKILL.md

Related skills

Tags

knowledge-base-import document-processing wiki-authoring source-citation cross-linking content-ingestion interlinked-pages contradiction-detection