technical/data/, linked from entity ## Implementation
"How is this deployed?"
technical/infrastructure/
"How does [entity A] relate to [entity B]?"
domain/relationships/ if standalone; entity ## Relationships tables
"What are the open questions about [topic]?"
## Open Questions sections, home.md conflict flags
Rules
Never read raw entries (docs/raw/entries/). The wiki is the knowledge base.
Don't guess. If the wiki doesn't cover it, say so and note it as a gap.
Do not modify any wiki files. Query is read-only.
1---2name: query3description: Command: `/wiki query <question>`4---5# Command: `/wiki query <question>`67Answer questions by navigating the wiki. All commands that navigate start at `home.md`.89## How to Answer10111. Read `home.md`. Scan for relevant articles. Use `also:` aliases and the `## Pending Articles` section to identify gaps.122. Check `_backlinks.json` — high backlink counts indicate central concepts.133. Read 3–8 relevant articles. Follow `[[wikilinks]]` 2–3 links deep. Cross namespace boundaries when the question requires both domain and technical context.144. Synthesize. Lead with the answer. Cite articles by name. Acknowledge ambiguities and open questions explicitly.1516## Query Patterns1718| Query | Where to look |19|-------|--------------|20| "What is [entity]?" | `domain/entities/`, linked `domain/concepts/` |21| "What rules govern [entity/command]?" | `domain/rules/`, entity `## Invariants`, command `## Validation Rules` |22| "Who can do [command]?" | `domain/commands/`, `domain/roles/` |23| "How does [flow] work?" | `domain/flows/`, participating entities |24| "Why was [decision] made?" | `decisions/domain/` or `decisions/technical/` |25| "What does [term] mean?" | `domain/concepts/` |26| "What is this project for?" | `project/overview.md` |27| "How is the system structured?" | `technical/architecture/` |28| "What does [service/module] do?" | `technical/modules/` |29| "What are the API contracts?" | `technical/apis/` |30| "How is [entity] persisted?" | `technical/data/`, linked from entity `## Implementation` |31| "How is this deployed?" | `technical/infrastructure/` |32| "How does [entity A] relate to [entity B]?" | `domain/relationships/` if standalone; entity `## Relationships` tables |33| "What are the open questions about [topic]?" | `## Open Questions` sections, `home.md` conflict flags |3435## Rules3637- Never read raw entries (`docs/raw/entries/`). The wiki is the knowledge base.38- Don't guess. If the wiki doesn't cover it, say so and note it as a gap.39- Do not modify any wiki files. Query is read-only.
Run npx skillmds@latest add thapaliyabikendra/query in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Command: `/wiki query <question>` It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
thapaliyabikendra (@thapaliyabikendra) published this skill. Their other Agent Skills are listed on their SkillMD profile.