google-cloud-storage-okf
Experimental, generic, and powerful skill for token-efficient search, semantic navigation, and progressive disclosure of unstructured or semi-structured objects (PDFs, logs, JSON/CSV dumps, media, large documents) in Google Cloud Storage (GCS) using the Open Knowledge Format (OKF). Beyond basic retrieval, agents can creatively apply this skill to a broad spectrum of search and reasoning tasks, including: (1) high-precision search and point-queries within large objects without loading full content into context; (2) multi-hop cross-document search and synthesis across multiple cloud objects; (3) searching and temporal reasoning across chronologically partitioned log streams, audit trails, and incident timelines; and (4) creating reusable Table of Contents metadata for downstream agents. Use proactively whenever searching, querying, or interacting with gs:// URIs where full-object downloads would waste tokens, degrade context quality, or exceed window limits.
- Version
- v2
- License
- Apache-2.0
Pinned to revision ab0883d81107, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/google-cloud-storage-okf/SKILL.md
- skills/google-cloud-storage-okf/scripts/__init__.py
- skills/google-cloud-storage-okf/scripts/core.py
- skills/google-cloud-storage-okf/scripts/mcp_server.py
Every link opens the file at its source, pinned to the revision this page describes.