agentsclimarketplace

Ai memory setup

Skill fabioc-aloha/Alex_Skill_Mall/plugins/supervisor-fleet/ai-memory-setup

284 curated plugins for AI assistants across 16 categories: security, Azure, documentation, code quality, cloud infrastructure, and more. Works with GitHub Copilot. Drop into .github/skills/local/ and go.

Install
npx -y skills add fabioc-aloha/Alex_Skill_Mall --skill ai-memory-setup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 3 stars3 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.

What its author says it does

Copied from the file, not written here

Detect, create, and manage the AI-Memory fleet communication channel. Fires on bootstrap, session start (announcements), and feedback writes.

SKILL.md

7.3 KB, 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

ProviderFolder patterns detectedNotes
OneDriveOneDrive, OneDrive - * (personal, family, business)Most common; multiple accounts create multiple folders
iCloudiCloudDrive, iCloud Drive, iCloud~com~apple~CloudDocsmacOS and Windows variants
DropboxDropbox, Dropbox (Personal), Dropbox (Business)Personal and business variants
Google DriveGoogle Drive, My DriveDrive for Desktop sync folder
BoxBox, Box SyncEnterprise cloud storage
MEGAMEGA, MEGAsyncEncrypted cloud storage
pCloudpCloud, pCloud DriveEuropean cloud storage
NextcloudNextcloudSelf-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:

  1. Config override: read .github/config/cognitive-config.json. If ai_memory_root is set, use <HOME>/<ai_memory_root>/AI-Memory.
  2. Auto-discovery: scan <HOME> for folders matching known cloud provider patterns. Skip any folder listed in ai_memory_exclude. Among matches, prefer drives that already contain an AI-Memory/ subfolder.
  3. Local fallback: ~/AI-Memory (no cloud sync, still functional)
  4. Exclusion list: ai_memory_exclude in 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:

  1. Check announcements/alex-act/ for unread files
  2. Report any new announcements to the user (one line each)
  3. 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):

  1. Discover which cloud drives exist:

    node .github/scripts/_registry.cjs --discover
    

    Output lists all detected cloud drives with provider name and whether AI-Memory exists.

  2. If multiple drives found, ask the user which one to use. If only one, use it. If none, offer ~/AI-Memory as local fallback.

  3. Create the folder structure:

    node .github/scripts/_registry.cjs --init "<drive-name>"
    

    Or during bootstrap, use the --ai-memory flag:

    node bootstrap-heir.cjs --target . --heir-id my-project --ai-memory "Dropbox" --apply
    
  4. The choice is automatically persisted in .github/config/cognitive-config.json:

    {
      "ai_memory_root": "Dropbox",
      "ai_memory_exclude": ["OneDrive - Microsoft"]
    }
    
  5. Verify: node .github/scripts/_registry.cjs --resolve . should return the AI-Memory path.

Write Feedback

When the heir observes friction worth surfacing:

  1. Resolve AI-Memory root
  2. Write one markdown file per item to feedback/alex-act/
  3. Filename format: YYYY-MM-DD-<short-slug>.md
  4. Strip project specifics per cross-project-isolation.instructions.md
  5. 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):

  1. Resolve AI-Memory root
  2. List files in announcements/alex-act/ (skip README.md)
  3. For each unread file, report the title and date
  4. 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.

ScenarioResolution
One OneDriveAuto-detected, no config needed
Two OneDrives, AI-Memory in oneai_memory_root pins the correct one
Two OneDrives, AI-Memory in bothai_memory_exclude blocks the wrong one
No OneDrive, has iCloudiCloud candidate resolves
No cloud drive at all~/AI-Memory local fallback

Configuration Reference

cognitive-config.json fields (heir-owned, never overwritten on upgrade):

FieldTypeDefaultPurpose
ai_memory_rootstring(auto-detect)Cloud drive folder name to use
ai_memory_excludestring[][]Folder names to skip during detection

Anti-Patterns

Anti-patternCorrection
Hardcoding an absolute pathUse 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 contextAlways apply cross-project-isolation before writing
Reading feedback as a heirFeedback is for the Supervisor; heirs read announcements only
Creating AI-Memory on every sessionCreate 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

FunctionPurpose
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.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.