design-chain
Run one design round through the design chain: vision, owners, brief with verbatim anchors, three directions, craft manifest,…
Split the approved PRD into one issue spec per manifest entry
> /plugin marketplace add assafkip/kipi-systemHow it fires
How this command gets triggered: by you, by Claude, or both.
/prd-splitContext preview
What this command does when you run it.
Split the approved PRD into one issue spec per manifest entry
description: Split the approved PRD into one issue spec per manifest entry allowed-tools: Bash
Materialize the PRD's `## Issues` fenced JSON manifest into issue specs under `issues_dir`. The split script enforces:
(An empty `required_checks` silently bypasses the runner's verification gate — the split refuses to create such specs.)
byte-identical.
Two-step flow — dry-run first so the author can see planned writes before any file lands on disk:
1. Dry-run:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/prd_split.py" --dry-runRead the `would_create` paths back to the author. Confirm before committing. If they do not confirm, stop. Do NOT run step 2 without explicit agreement.
2. Commit:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/prd_split.py"On collision, the script names the divergent files. Do not delete or overwrite them. Ask the author to rename either the manifest entry or the existing file.
After a successful split, tell the author to archive or clear the PRD before starting an issue (`prd_runner.py archive` or `prd_runner.py clear`). The concurrency guard blocks loading an issue while a PRD context is active.
Give your AI the right knowledge, at the moment it needs it. Kipi turns the scattered knowledge around your work into context that follows you across AI sessions: decisions, conversations, projects, people, commitments, lessons, documents, history.
Run one design round through the design chain: vision, owners, brief with verbatim anchors, three directions, craft manifest,…
Create the queued Linear projects and issues that shell scripts captured offline.
Scaffold a new RCA document from the canonical template, ready to fill.
Synthesize the previous assistant response to audio; autoplays locally with controls.
Run the full voice review on one draft by hand (bands, shapes, echo, gate roster, channel rules).