SuperAPI AI Directory

rowboat

Agents & models

View repository

Updated 10-29 05:36

About this skill

Rowboat

Instructions

  1. Confirm the target. This skill is for the rowboatlabs/rowboat app, not an arbitrary knowledge graph. Pin repository facts to the commit in references/source.json; this does not establish current runtime behavior.
  2. Classify the work surface: app install/config; source synchronization; graph build/curation; or a bug in a UI/core module. Inspect the relevant pinned files and current checkout before giving commands.
  3. Use the app's actual model. Rowboat ingests work context (including connected email/meetings and assistant conversations) into a Markdown, backlinked knowledge base. The graph builder tracks source-file state and processes one source file per agent batch to reduce cross-file entity contamination; it is not evidence of an independent graph database.
  4. Diagnose before changing state. For stale/missing notes, check source sync completion, changed-file detection, graph state, and the note destination before proposing rebuild or re-import. Preserve source files and state unless the user approves a destructive reset.
  5. Check source-grounded implementation details. Follow references/upstream.md for exact pinned setup/configuration, graph lifecycle, operational checks, and limitations. Treat commands there as documentation, not permission to execute.
  6. Gate effects separately. Ask for approval before downloading/installing the app or dependencies, changing configuration or login state, connecting accounts, importing/private-email or meeting data, accessing cloud resources, writing to a database, starting a public service, or paid uploads. Read-only local inspection needs no such effect approval.
  7. Verify claims honestly. The offline preflight helper can compare listed public-file hashes only. Report runtime_verified: false as no runtime proof; never claim installation, account connection, synchronization, or graph correctness from source hashes alone.
  8. Link references/source.json, references/upstream.md, and evals/evals.json when deeper provenance or edge cases matter. Authored eval scenarios are not executed test evidence.

Examples

  • "In rowboat, new meeting notes aren't appearing in the knowledge graph. Trace the sync/build path without changing my files." → Inspect state and sync/build boundaries read-only; do not re-import automatically.
  • "Set up Rowboat and connect my Gmail." → Explain the pinned setup path, then gate download/install and account authorization/import separately.
  • "Design a Neo4j ontology for a research archive." → Route to ontology/database design, not this application skill.

Best practices

  • Keep app workspace identity and owner identity explicit; do not infer the user's identity from email headers.
  • Preserve source provenance and distinguish a Markdown note graph from catalog metadata, vector search, or relational storage.
  • Use the current checkout's package scripts and configuration as truth when they differ from this pinned snapshot.
  • For troubleshooting, state the last verified layer and the next read-only check before proposing a write.

References