Skills for Real Engineers. Straight from my .agents directory.
wiki-query
Agent skill frompaperclipai/paperclip
Use when an LLM Wiki operation issue asks a question. Answer from wiki pages and raw sources with citations, name gaps plainly, and offer to file durable synthesis when the answer should compound.
How to install wiki-query
npx skills add paperclipai/paperclip# or add only this skill to Claude Code: copy the folder
packages/plugins/plugin-llm-wiki/skills/wiki-query/
# into
~/.claude/skills/wiki-query/ (all projects)
.claude/skills/wiki-query/ (one project)
1# Wiki Query23Answer a question from what the wiki actually contains, with citations.45## Inputs67- An operation issue with `operationType: "query"` and the question in the body.8- The operation issue's target `wikiId`, `spaceSlug`, and space root.910## Workflow11121. **Open the target space's `wiki/index.md` first** — it is the navigation aid. Identify candidate pages.132. **Read the candidate pages** end to end with `wiki_read_page`, always passing the operation issue's `wikiId` and `spaceSlug`. Follow `[[wiki-links]]` to neighbouring pages when the question spans entities or concepts.143. **Inspect raw sources** when a wiki page's claim feels thin. The wiki points to `raw/` precisely so you can verify before answering. Use `wiki_read_source`.154. **Answer the question** in the operation issue thread. Structure:16 - Direct answer first, in 1–4 sentences.17 - Then the supporting facts as bullet points, each with an inline citation: `(see [[wiki/concepts/managed-resources]])` or `(see raw/<filename>)`.18 - If you needed to read a raw source the wiki did not summarise, name that as a gap.19…
Excerpt shown under the repository's MIT license.
More skills in paperclip
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
