wiki-ingest
Helps your agent add new information to the LLM Wiki. It organizes content so it's easy to find and use.
What it does
This tool organizes information from a raw document and turns it into interconnected knowledge within a wiki. It creates pages for sources, concepts, and summaries, ensuring everything is linked and properly cited.
When to use it
- ✓When you are assigned a task to add a new document to the wiki.
- ✓If you need to transform a text file into an organized wiki format.
- ✓When you want to ensure new information is correctly referenced and linked to existing knowledge.
Example of what to ask your AI
“Please ingest the document at 'raw/my_document.txt' into the wiki.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The tool reads the document, checks what already exists in the wiki to avoid duplication, and creates new pages for the content. It also adds links between pages and updates the main index.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add paperclipai/paperclip --skill wiki-ingestOr download just the file:
curl -L https://raw.githubusercontent.com/paperclipai/paperclip/master/packages/plugins/plugin-llm-wiki/skills/wiki-ingest/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
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 treatraw/as immutable). - The operation issue's target
wikiId,spaceSlug, and space root (otherwise stop and surface the missing config to the requester).
Workflow
- Read context first.
- Read the target space's
AGENTS.mdfor page conventions (filenames, frontmatter, voice, citation style). - Read the target space's
wiki/index.mdto see what already exists. - Read the target space's last ~20 entries of
wiki/log.mdto avoid re-ingesting a source or re-resolving a contradiction someone else already filed.
- Read the target space's
- Read the source end to end with
wiki_read_source, passing the operation issue'swikiIdandspaceSlug. Do not skim. Note the source's structure, claims, dates, and anything that contradicts existing pages. - Plan, then confirm — but only if the user is in the loop. If the operation came from a routine (no live user), proceed. If a user is asking interactively, summarise the 3–5 takeaways you intend to file and ask which to emphasise before writing.
- Write the source page at
wiki/sources/<slug>.md— ~300–800 words, frontmatter per the wiki schema, neutral voice, key claims with quoted excerpts where they carry weight. The source page is the canonical citation target for everything else this skill writes. - Update or create downstream pages in
entities/,concepts/, andsynthesis/. A typical ingest touches 5–15 pages; resist creating pages for ideas that only appear once. - Wire the cross-links. Every claim that comes from the source cites it as
(see [[wiki/sources/<slug>]]). Every entity / concept mentioned by name on more than one page links to its dedicated page. - Flag contradictions; do not silently overwrite. When new material disagrees with an existing page, append a
> ⚠ contradicted by [[wiki/sources/<slug>]] (YYYY-MM-DD)callout to the older page and note the conflict in the log. - Refresh
wiki/index.mdwith one-line summaries for any new pages. - Append a log entry in
wiki/log.md:## [YYYY-MM-DD] ingest | <source title> - source: raw/<filename> - new pages: [[...]], [[...]] - updated pages: [[...]], [[...]] - notes: <one-line synthesis or open question>
Voice
- Terse, factual, neutral. Reference material, not narrative.
- No "Today I learned" or "This is interesting because" framing.
- Quote the source verbatim when paraphrasing would lose precision.
Verification
Before closing the operation issue:
- Source page exists at
wiki/sources/<slug>.mdwith valid frontmatter and asources:field pointing to the raw path. - Every new or updated page links back to the source page or a downstream page that does.
-
wiki/index.mdlists every new page under the right category with a one-line summary. -
wiki/log.mdhas the ingest entry with the exact filename heading format (sogrep "^## \[" wiki/log.mdkeeps working). - Any contradiction between the new source and an older page is annotated, not silently overwritten.
- No file under
raw/was modified.
Tools
wiki_list_sources, wiki_read_source, wiki_search, wiki_read_page, wiki_write_page. Always include the operation issue's wikiId and spaceSlug.
FAQ
What happens if the new document contradicts something already in the wiki?
The tool doesn't delete old information. Instead, it adds a note to the old page indicating the contradiction and where to find the new information.
How does the tool know how to organize the pages?
It reads the formatting and style conventions of the wiki space, such as the 'AGENTS.md' file, to ensure new pages follow the established pattern.
What are 'entity pages' and 'concept pages'?
Entity pages refer to specific people, places, or organizations mentioned. Concept pages explain general ideas or themes covered in the document.
Details
Original description by the author
Use when an operation issue asks to ingest a captured `raw/` source into the LLM Wiki, or the user says "ingest <slug>". Create durable source, entity, concept, synthesis, index, and log pages; use paperclip-distill for Paperclip bundles.
repo: paperclipai/paperclip
Popularity
- GitHub stars
- 103k
- Ranking position
- #371
- License
- MIT
- Updated
- 10/16/2026
Comments
- …
More skills from this repository
delegate-work
Helps your agent delegate work to another agent. It's useful for breaking down complex tasks and tracking progress in an organized way.
paperclipai/paperclip
follow-up-results
Has your agent check results from previous work. It's useful for tracking task progress and adding human feedback.
paperclipai/paperclip
review-my-team
Helps your agent review the connected team. It's useful for getting a summary of the team, tasks, blockers, and pending approvals.
paperclipai/paperclip
paperclip-task-bridge
Has your agent create and manage tasks on another platform. It's useful for interacting with project management systems directly.
paperclipai/paperclip
Similar skills
architecture-decision-records
Has your agent record important project structure decisions. It helps to understand the reasoning behind choices and maintain a clear history of changes.
affaan-m/ECC
code-tour
Lets your agent create step-by-step code walkthroughs with exact file and line anchors. It's useful for project introductions, code explanations, or change reviews. Helps understand how a system works.
affaan-m/ECC
codebase-onboarding
Helps your agent analyze unfamiliar code and create an onboarding guide. It includes an architecture map, entry points, and conventions. Ideal for starting on a new project.
affaan-m/ECC