wiki-query
Wiki Query pulls answers from wiki pages and raw sources, citing each fact as it goes. When synthesis is needed, it offers to file a new page rather than answering silently. If the wiki can't answer, it says so plainly and suggests a concrete next step.
Wiki Query answers questions by searching wiki pages and raw sources, then citing each claim directly in the response.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-28
Wiki Query answers questions by searching wiki pages and raw sources, then citing each claim directly in the response. Wiki Query pulls answers from wiki pages and raw sources, citing each fact as it goes. When synthesis is needed, it offers to file a new page rather than answering silently. If the wiki can't answer, it says so plainly and suggests a concrete next step.
Use it when
- Wiki Query identifies knowledge gaps honestly and suggests concrete next steps rather than guessing.
- Yes.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
paperclipai/paperclip/wiki-query · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I answer questions from a wiki with citations?
Wiki Query answers wiki-based questions by pulling from wiki pages and raw sources, then citing each fact inline as it responds. Wiki Query structures answers with bullet points and linked references so readers can verify claims directly. When you ask Wiki Query a question, it searches relevant wiki pages, checks facts against raw sources for accuracy, and presents findings with proper attribution to each source.
What does Wiki Query do when the wiki can't answer?
Wiki Query identifies knowledge gaps honestly and suggests concrete next steps rather than guessing. When Wiki Query encounters a question the wiki doesn't cover, it tells you plainly that the answer isn't available, then offers to file a new synthesis page to document the gap. This approach keeps responses factual and helps grow the wiki over time.
Can Wiki Query search wiki pages and cite sources?
Yes. Wiki Query navigates wiki pages to locate relevant information, then cites each source inline as part of its answer. Wiki Query verifies claims against raw sources before responding, ensuring citations point to accurate material. This search-and-cite workflow lets you trust that every fact in a Wiki Query answer is traceable back to a documented source.
How does Wiki Query handle wiki query operations?
Wiki Query processes wiki query operations by first searching and navigating wiki pages to find relevant information. It then verifies wiki claims against raw sources before responding, structures answers with inline citations and bullet points, and identifies any knowledge gaps. If synthesis is needed, Wiki Query offers to file a durable page rather than leaving gaps unaddressed.
What is Wiki Query's approach to source verification?
Wiki Query verifies wiki claims against raw sources before responding to any question. This verification step ensures that every cited fact has been checked for accuracy at the source level. By combining wiki page navigation with raw source inspection, Wiki Query builds confidence that answers are both well-sourced and factually sound.
Does Wiki Query file new pages for knowledge gaps?
Wiki Query can file durable synthesis pages when gaps are identified during query operations. Rather than answering silently or leaving holes in coverage, Wiki Query offers to document gaps as new pages. This synthesis-filing capability helps keep the wiki comprehensive and ensures that unanswered questions become opportunities to expand the knowledge base.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Wiki Query
Answer a question from what the wiki actually contains, with citations.
Inputs
- An operation issue with
operationType: "query"and the question in the body. - The operation issue's target
wikiId,spaceSlug, and space root.
Workflow
- Open the target space's
wiki/index.mdfirst — it is the navigation aid. Identify candidate pages. - Read the candidate pages end to end with
wiki_read_page, always passing the operation issue'swikiIdandspaceSlug. Follow[[wiki-links]]to neighbouring pages when the question spans entities or concepts. - Inspect raw sources when a wiki page's claim feels thin. The wiki points to
raw/precisely so you can verify before answering. Usewiki_read_source. - Answer the question in the operation issue thread. Structure:
- Direct answer first, in 1–4 sentences.
- Then the supporting facts as bullet points, each with an inline citation: `(see
(truncated - see the full file via the links below)
File tree — 1 file
packages/plugins/plugin-llm-wiki/skills/wiki-query/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Answer wiki-based questions with proper citations and source verification”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Wiki Query answers questions grounded in your wiki's actual content, citing pages and raw sources as it goes. It reads your wiki's index and candidate pages, verifies claims against raw sources when needed, and structures answers with inline citations. When synthesis is required, it offers to file the work durably so knowledge compounds instead of disappearing into chat.
wiki-ingest automates the transformation of a single source document into a structured wiki by creating and linking source, entity, concept, and synthesis pages. It reads your space's conventions, flags contradictions with existing content, and maintains a log of all ingestions. The skill ensures every claim traces back to its origin and all cross-references stay current.
Wiki Lint scans a wiki space to surface seven classes of structural and content issues: contradictions between pages, stale claims, orphaned pages, concept gaps, broken wiki-links, weak provenance, and index drift. It returns a severity-grouped triage list with evidence and suggested fixes, but never modifies wiki content—leaving all decisions to the maintainer.
Wiki Lint performs read-only audits of wiki spaces, surfacing contradictions, orphaned pages, stale claims, concept gaps, broken links, and provenance issues. It returns a severity-grouped triage list with evidence and suggested fixes, leaving all decisions to the maintainer.
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.
Paperclip Distill transforms project, issue, comment, and document activity from Paperclip into structured wiki pages that tell the story of what happened, what was decided, and what matters next. It produces executive standups and project indexes designed for readers unfamiliar with the source material, emphasizing interpretation and context over raw issue lists or dated status dumps.
More skills LLM Wiki Maintainer (MIT) · index-refresh (MIT) · index-refresh (MIT)