一键导入
wiki-query
Answer a question from the wiki — locate pages via the index, synthesize a cited answer, and offer to file valuable answers back as new wiki pages
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Answer a question from the wiki — locate pages via the index, synthesize a cited answer, and offer to file valuable answers back as new wiki pages
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Update the ai-sdd framework binary + skills to the latest release — an apply-on-confirm wrapper that runs `ai-sdd update --check`, surfaces the current-to-latest version transition, and (only on explicit confirmation) runs `ai-sdd update` and lands a standalone reseed commit. Agent-agnostic (claude-code or codex). Use when a teammate wants to update / upgrade ai-sdd, sees the update-available notice, or invokes `/ai-sdd-update`.
Stand up (or refresh) an ai-sdd factory for a repository so any coding agent — claude-code, codex, … — can drive it. Discovers the repo's conventions, scaffolds the .ai-sdd/ home, authors worker skills + schemas, compiles the deterministic gates, and wires provider-neutral skill surfacing (AGENTS.md + per-agent symlinks). Use when onboarding a repo to ai-sdd or re-bootstrapping after the codebase/conventions drift.
Drive a software-factory run by dispatching a sub-agent per worker — the deterministic `ai-sdd` engine plans (next), a fresh sub-agent does each worker's work via its skill, the engine gates and advances (submit), and each completed slice is committed. Agent-agnostic (claude-code or codex). Use when asked to run, drive, continue, or advance a factory run / pipeline / orchestration, or when the user mentions `ai-sdd next` / `ai-sdd submit`.
Print the diagram-driven ai-sdd workflow cheatsheet — the canonical command sequence (bootstrap → plan → run, validate/next/submit/status) that travels with the binary. Use when a user forgets which command comes next, asks "how do I drive a run / what's the workflow", or needs the command reference without leaving the repo.
Turn a complete PROGRAM brief into a runnable master plan — a decision-closed program requirements doc and a master orchestration graph whose nodes are whole sub-features (kind:pipeline) sequenced by milestone validation gates with owners. The program tier above ai-sdd-plan. Requires a real program brief (refuses a one-liner) and human approval of the program requirements draft before emitting the graph. Use when planning a multi-feature, multi-person project in a bootstrapped repo (run ai-sdd-bootstrap first); each sub-feature is then planned with ai-sdd-plan. Re-run on an existing program to amend it in place (create-vs-amend is auto-detected from disk): append sub-features/milestones and rewire pending nodes; a started node (completed or in-flight) is immutable and corrected forward with a downstream `<node>-revert` node.
Turn a complete feature brief into a runnable plan for a bootstrapped repo — a decision-closed requirements doc and an orchestration graph (slices + depends_on) the engine executes. Requires a real brief (refuses a bare one-liner — asks for one) and human approval of the requirements draft before generating slices. The planning layer between an idea and ai-sdd-run. Use when starting a new feature in a repo that already has a .ai-sdd/ (run ai-sdd-bootstrap first). Re-run on an existing feature to amend it in place (create-vs-amend is auto-detected from disk): append slices and rewire pending ones; a started slice (completed or in-flight) is immutable and corrected forward with a downstream `<slice>-revert` slice.
| name | wiki-query |
| description | Answer a question from the wiki — locate pages via the index, synthesize a cited answer, and offer to file valuable answers back as new wiki pages |
| category | researching |
| model | claude-sonnet-4-6 |
| argument-hint | <question> |
| disable-model-invocation | false |
| user-invocable | true |
Answer a question using the wiki as the primary source of truth. If the wiki lacks coverage, say so and suggest /wiki-ingest for relevant raw sources. Never answer from general knowledge alone when a wiki page exists — cite it.
Question: $ARGUMENTS
wiki/index.md in full — it is the home Map of Content.index.md files (wiki/work/<family>/index.md) list only active items — read those first, then read the individual files needed.Read each relevant page completely before synthesizing. Do not summarize from the first paragraph — check for contradictions, confidence caveats, and supersession markers throughout the page.
If a page cites a sources: raw file, read the raw source only if the page's distillation is insufficient.
Answer the question in 2–5 paragraphs. For each claim, cite the wiki page: ([page title](relative/path/to/page.md)).
If you found contradictions between pages, surface them explicitly with a > **Contradiction:** callout and note which source is more recent.
If the wiki has no coverage at all: say so clearly and suggest:
This question isn't covered in the wiki yet.
To add coverage: /wiki-ingest raw/<relevant-source>
If the synthesized answer represents durable, timeless knowledge (a pattern, a design decision rationale, an entity summary) that doesn't currently exist as its own wiki page, offer:
Worth filing this answer as a new wiki page?
Target: wiki/knowledge/concepts/<concept-slug>.md
Never file stateful work artifacts here — requirements, decisions, tasks, bugs belong in wiki/work/ and are created by their own skills (/req-create, /decision-create, etc.).
If the user says yes:
wiki/knowledge/concepts/<concept-slug>.md with proper frontmatter (id, title, updated, tags, sources if derived from a raw source).derived_from::[[source-slug]] if the answer came from an ingested source.wiki/index.md.wiki/log.md: ## [YYYY-MM-DD] query | <question summary>\nFiled answer as wiki/knowledge/concepts/<slug>.md.wiki/knowledge/; never file under wiki/work/.wiki/work/ files — this skill is read-only for work artifacts.