Skill

init

Configures learning-loop plugin for first-time setup or upgrade: vault path, persona voice, CLAUDE.md integration, binaries, cache health. Idempotent re-run skips completed steps.

Node

Javascript

developer-tools

automation

npx claudepluginhub robinslange/learning-loop --plugin learning-loop

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Seven-phase detect-confirm-apply flow. One question at a time. Safe to re-run: detects existing state and skips completed steps.

Supporting Assets

phases/01-detect.mdphases/02-vault.mdphases/03-binary.mdphases/04-federation.mdphases/05-claudemd.mdphases/06-cache-health.mdphases/07-librarian.md

SKILL.md

Similar Skills

cache-components

139.4k

Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.

cache-components

pdf

131.6k

Processes PDFs: extracts text/tables/images, merges/splits/rotates pages, adds watermarks, creates/fills forms, encrypts/decrypts, OCRs scans. Activates on PDF mentions or output requests.

11 files

document-skills

Stats

Stars5

Forks0

Last CommitMay 3, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Init: Learning Loop Setup

Seven-phase detect-confirm-apply flow. One question at a time. Safe to re-run: detects existing state and skips completed steps.

All operations use Node.js APIs (fs, path, child_process). No bash find, no shell globbing for detection.

Paths

PLUGIN, PLUGIN_DATA, and VAULT are injected by the session-start hook (see "Learning Loop Paths" in your context). Use those resolved values for ALL path references in the phase files. If not present, resolve them by running:

node PLUGIN/scripts/resolve-paths.mjs

Process

Read each phase file in order and execute its instructions. After Phase 1's dashboard, only enter the phases the dashboard reports as needing work.

Read PLUGIN/skills/init/phases/01-detect.md -- detect state, present dashboard. If everything is configured, stop here.
Read PLUGIN/skills/init/phases/02-vault.md -- vault path, folders, system files.
Read PLUGIN/skills/init/phases/03-binary.md -- binary, vendor deps, orphan cleanup, index, shims, plugin deps.
Read PLUGIN/skills/init/phases/04-federation.md -- single yes/no, hands off to /learning-loop:federation for the full flow.
Read PLUGIN/skills/init/phases/05-claudemd.md -- CLAUDE.md integration.
Read PLUGIN/skills/init/phases/06-cache-health.md -- optional cache-health statusline.
Read PLUGIN/skills/init/phases/07-librarian.md -- optional librarian background agent.

After all phases complete, present the summary below.

Summary

Learning loop configured.

  Vault:        [path] ([N] notes)
  Folders:      [N]/7 present
  Binary:       ll-search vX.Y
  Search:       [N] notes indexed
  Federation:   [configured | deferred to /learning-loop:federation | not requested]
  CLAUDE.md:    [status]
  Cache health: [installed | skipped: oh-my-claude not found]
  Librarian:    [enabled | skipped: ollama/hardware not available]
  Shims:        ll-watch + ll-search installed in ~/.local/bin

Start the watcher with: ll-watch
Run /learning-loop:help to see available commands.

Rules

One question at a time. Wait for the answer before moving on.
Validate paths before writing config.
Never overwrite existing vault files without asking.
Never restructure an existing vault.
Preserve existing config.json fields when updating: read, merge, write.
All detection via Node.js APIs. No find, no shell globbing.
If any step fails, explain what went wrong and how to fix it.
Works for: fresh install, existing vault + new plugin, or upgrade.