From produck
Loads full Produck feedback context (page HTML, annotations, session timeline) and drives a feedback-to-PRD-to-build loop for fixing bugs or building features users asked for.
How this skill is triggered — by the user, by Claude, or both
Slash command
/produck:produck-feedbackThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Purpose:** Turn real, in-context user feedback into shipped fixes. This skill drives the
Purpose: Turn real, in-context user feedback into shipped fixes. This skill drives the Produck MCP — it tells the agent how to find the right feedback, load the full context behind it, and convert that context into an aligned change instead of a guess.
Requires the Produck MCP server connected. If
search_feedback/get_feedbackare not available, seereferences/connect-mcp.mdto connect it and mint a token first.
Produck captures feedback in the user's own session, so a ticket is far richer than a text complaint. Each ticket can carry:
The job of this skill is to pull that context and use all of it, not just the title.
The server is named produck (tools may appear prefixed, e.g. mcp__produck__search_feedback).
search_feedback — find relevant ticketsReturns lightweight summaries; use it to locate tickets, then load full context with get_feedback.
| Input | Type | Notes |
|---|---|---|
domain | string, optional | Filter to one website domain. |
limit | int 1–50, optional | Defaults to 20. |
cursor | string, optional | Pagination cursor from a previous call. |
Returns { items, nextCursor, count } — each item a summary (id, domain, page URL, created-at,
annotation count, source). Page with cursor until nextCursor is null when you need the full set.
get_feedback — load one ticket in full| Input | Type | Notes |
|---|---|---|
feedbackId | string, required | The ticket id (from a search_feedback item, a URL, or the user). |
Returns the full ticket: written/spoken feedback, reconstructed HTML, annotations, session activity,
and the design doc when present. Always get_feedback before building — never act on a summary alone.
search_feedback → find the relevant ticket(s) (filter by domain, page as needed)
get_feedback → load ONE ticket's full context
user-alignment → turn the ticket into an agent-executable PRD (do not skip)
build → implement the fix / high-fidelity mockup
verify → check the change against the ticket's annotations + design doc
user-alignment skill first to produce an aligned PRD — interpreted intent, scope,
non-goals, acceptance criteria — then build from that. The two skills are designed to compose.To connect the MCP, choose the install path for your agent and mint a token — see
references/connect-mcp.md.
npx claudepluginhub tryproduck/produck-skills --plugin produckAggregates user feedback from Dovetail, Productboard, Notion, Linear, and GitHub, clusters into themes, surfaces top unaddressed signal, and maps to roadmap. Produces FEEDBACK.md for downstream PM skills.
Sets up post-launch feedback channels and processing workflows for PRD v0.9 Go-to-Market. Produces CFD- entries for capturing user input, sentiment tracking, and escalation rules.
Guides collecting and prioritizing user feedback via 1-on-1s, surveys, NPS, in-app widgets, feature boards; implements simple feedback DB tables and contextual triggers.