vouch-ask
Answer a question from the vouch KB with citations, or say what's missing
npx skills add vouchdev/vouch --skill vouch-ask --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# /vouch-ask Answer "$ARGUMENTS" using only reviewed knowledge from the vouch KB. Every statement in the answer must carry a `[claim-id]` or `[source-id]` citation. Steps: 1. Call `kb_search` with `query: "$ARGUMENTS"`, then `kb_context` on the same query to assemble the working set. 2. If the results answer the question, write the answer citing every claim id you relied on. Use `kb_read_page` for typed record detail (contacts, project records, followups). 3. If the KB cannot support an answer, say so plainly and list the closest claims found. Do not fill gaps from your own knowledge — an uncited answer is worse than no answer. 4. Only when the user explicitly asks about in-flight knowledge, list `kb_list_pending` items — each labeled `UNREVIEWED` — after the cited answer, never mixed into it. Never call `kb_approve`. Never restate pending proposals as facts.
What does the vouch-ask skill do?
Answer a question from the vouch KB with citations, or say what's missing
How do I install it?
Run `npx skills add vouchdev/vouch --skill vouch-ask --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From vouchdev/vouch, a repository with 120 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.
