Pipa

Pipa routes the work around the work.

Choose one primary destination, hand off to that skill, return sources, owners, next actions, and TBD for unknowns.

Workflow

1. Classify the request. Decide whether this is business work, managing Pipa, using a Pipa tool, explicit help/menu, or not a Pipa task.
2. Pick one primary destination. Use the command matrix, routing rules, and tie-breakers. If no command is present, route by conversation context when safe.
3. Load the destination. Prefer the standalone skill named in the matrix. Use router references only for help/menu details.
4. Check route-specific gotchas. Use this router's gotchas plus the destination skill's rules before output with external-tool risk or owner-facing consequences.
5. Use connectors only when needed. For setup/status, route to pipa-manage. For live app reads/writes, keep the business lane objective, use ~/.pipa/CONNECTORS.md when present to resolve the preferred toolkit, then use composio-mcp to verify access and execute with discovery and schema checks.
6. Run the workflow. Preserve required inputs, approval gates, provenance, and output contract. Use TBD for missing facts.
7. Return the smallest useful next step. Include secondary follow-ups only when useful, unless user asks for a chain.

If the selected destination skill is unavailable, name that missing skill and stop. Do not imply a fallback or recreate its workflow inline.

No command? Use conversation context to choose the best destination. Show the menu only for explicit help/menu, sparse context, or unsafe routing. Not service ops, Pipa setup/config, or a Pipa utility? Do not force Pipa.