/drive-usage
Brain Drive filing discipline: where artifacts go + how to name them. Triggers: Drive/Brain Drive upload, folders, prompts/results, audits, plans, transcripts, dashboards, docs.local artifacts. NOT for Gemini Drive/web research; >100KB use archive.
$ golems-cli skills install drive-usageUpdated 2 weeks ago
Etan's pain: agents (except researchers) don't use Drive right and leave artifacts scattered in
docs.local/. This skill makes filing automatic. Rule of thumb: if an artifact should outlive this session, it goes to Brain Drive in the RIGHT folder —docs.local/is a cache, not a home.
This is the routing/where-does-this-go layer. Related: /google-drive-archive = the heavy (>100KB/media) archival workflow; /braindrive = query Drive via Gemini; /gemini-research = web research with Drive sources. This skill decides which folder + what name, then hands off to those for the actual move when heavy.
Brain Drive folder model (real — root 1XJOCNtK-gYE_UVVfBGZjW3RLZIQ4NcGJ)
| Folder | id | What goes here |
|---|---|---|
01_STANDARDS | 1IM9Q1EjQ5JRos804Ix6ZCr_Mq9VnEhMv | Canonical specs, conventions, locked schemas, standards docs (durable reference). |
02_GROUNDING | 1jYJPjJ0Hhu2eZjFdBeLxI3Oipaq7ab6z | Grounding corpora / reference data agents ground answers on. |
03_RESEARCH | 1nSQkJaIaD6lzcxVZ15-AvB7hl8Ip2W_r | Research prompts + results. In-flight → 03_RESEARCH/Active/<topic>/ (id 1zqKMg4zd58W24bTVZGe1EnTueB7OIgS7). |
04_INGEST | 1pgV_aX4N1rtUMBaxFY1DQalEdl-EBVas | Raw inbound to be processed/digested (not yet curated). |
06_ARCHIVE | 1ld8fKs9-4URpp-R1D7J_41RBuxHVZjBK | Forever storage of finished heavy artifacts (transcripts, audio/video, big audits/plans). Target of /google-drive-archive. |
Folder semantics (what each numbered folder means) are confirmed with brainlayer-LEAD (s:57, owns Drive/backup). Legacy non-numbered folders (
Research×2 duplicates,Sessions,Collabs,_inbox-*,BrainBar Design Audit) are pre-taxonomy scatter — do not add to them; file into the numbered model. (Consolidation of the legacy dupes is an s:57 cleanup task.)
Decision tree (where does THIS artifact go?)
- A research prompt or its results? →
03_RESEARCH/Active/<topic>/(e.g.skills-eval-phoenix/). Drive-ground prompts by uploading the real artifacts beside them. - A finished heavy artifact (>100KB / media / raw transcript / big audit)? → invoke
/google-drive-archive→ lands in06_ARCHIVE/<area>/<topic>/<date>/, leaves a_DRIVE-LEDGER.mdpointer indocs.local/. - A canonical standard / spec / locked schema? →
01_STANDARDS/. - Grounding corpus / reference data? →
02_GROUNDING/. - Raw, not-yet-digested inbound? →
04_INGEST/. - Lightweight, session-scoped scratch? → fine to leave in
docs.local/— but if anyone else (or future-you) needs it, FILE it per 1–5.
Naming convention
YYYY-MM-DD-<topic>[-<surface/agent>].<ext> — date-prefixed, kebab-case, topic-first. Folders: <topic>-<domain>/ (e.g. weave-eval-phoenix/). Keep the local mirror name identical to the Drive name so the ledger maps 1:1.
Full SKILL.md source — includes LLM directives, anti-patterns, and technical instructions stripped from the Overview tab.
Etan's pain: agents (except researchers) don't use Drive right and leave artifacts scattered in
docs.local/. This skill makes filing automatic. Rule of thumb: if an artifact should outlive this session, it goes to Brain Drive in the RIGHT folder —docs.local/is a cache, not a home.
This is the routing/where-does-this-go layer. Related: /google-drive-archive = the heavy (>100KB/media) archival workflow; /braindrive = query Drive via Gemini; /gemini-research = web research with Drive sources. This skill decides which folder + what name, then hands off to those for the actual move when heavy.
Brain Drive folder model (real — root 1XJOCNtK-gYE_UVVfBGZjW3RLZIQ4NcGJ)
| Folder | id | What goes here |
|---|---|---|
01_STANDARDS | 1IM9Q1EjQ5JRos804Ix6ZCr_Mq9VnEhMv | Canonical specs, conventions, locked schemas, standards docs (durable reference). |
02_GROUNDING | 1jYJPjJ0Hhu2eZjFdBeLxI3Oipaq7ab6z | Grounding corpora / reference data agents ground answers on. |
03_RESEARCH | 1nSQkJaIaD6lzcxVZ15-AvB7hl8Ip2W_r | Research prompts + results. In-flight → 03_RESEARCH/Active/<topic>/ (id 1zqKMg4zd58W24bTVZGe1EnTueB7OIgS7). |
04_INGEST | 1pgV_aX4N1rtUMBaxFY1DQalEdl-EBVas | Raw inbound to be processed/digested (not yet curated). |
06_ARCHIVE | 1ld8fKs9-4URpp-R1D7J_41RBuxHVZjBK | Forever storage of finished heavy artifacts (transcripts, audio/video, big audits/plans). Target of /google-drive-archive. |
Folder semantics (what each numbered folder means) are confirmed with brainlayer-LEAD (s:57, owns Drive/backup). Legacy non-numbered folders (
Research×2 duplicates,Sessions,Collabs,_inbox-*,BrainBar Design Audit) are pre-taxonomy scatter — do not add to them; file into the numbered model. (Consolidation of the legacy dupes is an s:57 cleanup task.)
Decision tree (where does THIS artifact go?)
- A research prompt or its results? →
03_RESEARCH/Active/<topic>/(e.g.skills-eval-phoenix/). Drive-ground prompts by uploading the real artifacts beside them. - A finished heavy artifact (>100KB / media / raw transcript / big audit)? → invoke
/google-drive-archive→ lands in06_ARCHIVE/<area>/<topic>/<date>/, leaves a_DRIVE-LEDGER.mdpointer indocs.local/. - A canonical standard / spec / locked schema? →
01_STANDARDS/. - Grounding corpus / reference data? →
02_GROUNDING/. - Raw, not-yet-digested inbound? →
04_INGEST/. - Lightweight, session-scoped scratch? → fine to leave in
docs.local/— but if anyone else (or future-you) needs it, FILE it per 1–5.
Naming convention
YYYY-MM-DD-<topic>[-<surface/agent>].<ext> — date-prefixed, kebab-case, topic-first. Folders: <topic>-<domain>/ (e.g. weave-eval-phoenix/). Keep the local mirror name identical to the Drive name so the ledger maps 1:1.
The discipline (the one rule)
Before you finish a task that produced a durable artifact: did you FILE it in the right Brain Drive folder, or leave it scattered in docs.local/? If durable and still only local → file it now (this skill or /google-drive-archive) and drop a one-line _DRIVE-LEDGER.md pointer. "It's in docs.local" is not "it's saved."
Quick reference (MCP)
- Upload:
mcp__google-drive__uploadFile(localPath, parentFolderId=<from table>). - New topic folder:
mcp__google-drive__createFolder(name, parent=<numbered folder id>). - Find:
mcp__google-drive__search(query, rawQuery=true)with'<id>' in parents. - Heavy/forever: hand off to
/google-drive-archive.
After creating/editing this skill it must be REGISTERED (golem-install / symlink into
~/.claude/skills) before any agent can invoke it — committed ≠ installed.
Changelog entries are derived from eval runs and skill version updates. Full cascading changelog (Phase 4D) coming soon.
- +Initial release to Golems skill library