Ai memory setup
Skill fabioc-aloha/Alex_Skill_Mall/plugins/supervisor-fleet/ai-memory-setup
Detect, create, and manage the AI-Memory fleet communication channel. Fires on bootstrap, session start (announcements), and feedback writes.From its SKILL.md
npx -y skills add fabioc-aloha/Alex_Skill_Mall --skill ai-memory-setupAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
7.3 KB, ~1.7k tokens by cl100k_base, as published. Nobody here has run it
AI-Memory Setup
AI-Memory is the shared folder on the user's cloud drive where ACT heirs exchange feedback, announcements, and registry data. This skill covers detection, creation, path resolution, and ongoing read/write operations.
Supported Cloud Providers
| Provider | Folder patterns detected | Notes |
|---|---|---|
| OneDrive | OneDrive, OneDrive - * (personal, family, business) | Most common; multiple accounts create multiple folders |
| iCloud | iCloudDrive, iCloud Drive, iCloud~com~apple~CloudDocs | macOS and Windows variants |
| Dropbox | Dropbox, Dropbox (Personal), Dropbox (Business) | Personal and business variants |
| Google Drive | Google Drive, My Drive | Drive for Desktop sync folder |
| Box | Box, Box Sync | Enterprise cloud storage |
| MEGA | MEGA, MEGAsync | Encrypted cloud storage |
| pCloud | pCloud, pCloud Drive | European cloud storage |
| Nextcloud | Nextcloud | Self-hosted cloud |
Discovery scans the user's HOME directory for any folder matching these patterns. Unknown cloud drives are ignored (the user can still point to them manually via ai_memory_root).
Path Resolution Algorithm
Resolve the AI-Memory root in this order:
- Config override: read
.github/config/cognitive-config.json. Ifai_memory_rootis set, use<HOME>/<ai_memory_root>/AI-Memory. - Auto-discovery: scan
<HOME>for folders matching known cloud provider patterns. Skip any folder listed inai_memory_exclude. Among matches, prefer drives that already contain anAI-Memory/subfolder. - Local fallback:
~/AI-Memory(no cloud sync, still functional) - Exclusion list:
ai_memory_excludein cognitive-config.json lists folder names to skip (e.g.,["OneDrive - Microsoft"]to avoid the work account).
The resolution order matches _registry.cjs (the muscle used by bootstrap-heir.cjs and upgrade-self.cjs). LLM heirs and scripts must agree on the same path.
Folder Structure
<cloud-drive>/AI-Memory/
README.md # Channel overview
feedback/
README.md
alex-act/ # Heir feedback inbox
README.md
announcements/
alex-act/ # Fleet-wide announcements
README.md
heirs/
registry.json # Fleet registry (auto-maintained)
knowledge/ # Shared knowledge base
insights/ # Analytical insights
Operations
Detect (session start)
On every session start, resolve the AI-Memory root. If found:
- Check
announcements/alex-act/for unread files - Report any new announcements to the user (one line each)
- Do NOT read or report feedback (that's the Supervisor's job)
If not found: note it silently. Do not prompt the user unless they explicitly ask about fleet communication.
Create (first time setup)
When AI-Memory is needed but doesn't exist (bootstrap, first feedback write):
-
Discover which cloud drives exist:
node .github/scripts/_registry.cjs --discoverOutput lists all detected cloud drives with provider name and whether AI-Memory exists.
-
If multiple drives found, ask the user which one to use. If only one, use it. If none, offer
~/AI-Memoryas local fallback. -
Create the folder structure:
node .github/scripts/_registry.cjs --init "<drive-name>"Or during bootstrap, use the
--ai-memoryflag:node bootstrap-heir.cjs --target . --heir-id my-project --ai-memory "Dropbox" --apply -
The choice is automatically persisted in
.github/config/cognitive-config.json:{ "ai_memory_root": "Dropbox", "ai_memory_exclude": ["OneDrive - Microsoft"] } -
Verify:
node .github/scripts/_registry.cjs --resolve .should return the AI-Memory path.
Write Feedback
When the heir observes friction worth surfacing:
- Resolve AI-Memory root
- Write one markdown file per item to
feedback/alex-act/ - Filename format:
YYYY-MM-DD-<short-slug>.md - Strip project specifics per
cross-project-isolation.instructions.md - Required frontmatter: Date, Category (bug/friction/feature-request/success), Severity (critical/high/medium/low), Heir (redacted), Edition version
Read Announcements
On session start (triggered by greeting-checkin.instructions.md):
- Resolve AI-Memory root
- List files in
announcements/alex-act/(skip README.md) - For each unread file, report the title and date
- Do NOT delete announcement files (they persist for all heirs)
Multi-Cloud-Drive Disambiguation
Users may have multiple OneDrive accounts (personal + work). The ai_memory_exclude field prevents heirs from writing to the wrong drive.
| Scenario | Resolution |
|---|---|
| One OneDrive | Auto-detected, no config needed |
| Two OneDrives, AI-Memory in one | ai_memory_root pins the correct one |
| Two OneDrives, AI-Memory in both | ai_memory_exclude blocks the wrong one |
| No OneDrive, has iCloud | iCloud candidate resolves |
| No cloud drive at all | ~/AI-Memory local fallback |
Configuration Reference
cognitive-config.json fields (heir-owned, never overwritten on upgrade):
| Field | Type | Default | Purpose |
|---|---|---|---|
ai_memory_root | string | (auto-detect) | Cloud drive folder name to use |
ai_memory_exclude | string[] | [] | Folder names to skip during detection |
Anti-Patterns
| Anti-pattern | Correction |
|---|---|
| Hardcoding an absolute path | Use the resolution algorithm; paths differ per user and OS |
Creating AI-Memory in OneDrive - Microsoft (work account) | Personal cloud drive only; work drives may have retention policies |
| Writing feedback without stripping project context | Always apply cross-project-isolation before writing |
| Reading feedback as a heir | Feedback is for the Supervisor; heirs read announcements only |
| Creating AI-Memory on every session | Create once on bootstrap; subsequent sessions just resolve |
Muscle Reference
The _registry.cjs script (shipped with Edition) provides both a programmatic API and a CLI:
Programmatic API
| Function | Purpose |
|---|---|
resolveAiMemoryRoot(heirRoot?) | Returns the AI-Memory path or null; honors cognitive-config.json |
discoverCloudDrives(heirRoot?) | Scans HOME for cloud drive folders; returns [{ name, path, provider, hasAiMemory }] |
initAiMemory(driveName) | Creates full folder structure + READMEs |
upsertHeir(marker, repoPath) | Updates heirs/registry.json |
CLI
node .github/scripts/_registry.cjs --discover # List cloud drives
node .github/scripts/_registry.cjs --init "<name>" # Create AI-Memory in named drive
node .github/scripts/_registry.cjs --resolve [dir] # Resolve AI-Memory root
Bootstrap Flag
node .github/scripts/bootstrap-heir.cjs --ai-memory "<drive-name>" ...
Overrides auto-selection during bootstrap. Persists to cognitive-config.json.