From learning-loop
Retrieves and organizes existing knowledge on a topic from vault notes, episodic memory, literature, and past conversations. Categorizes by depth, links connections, suggests next actions like discovery. Use /refresh 'topic'.
npx claudepluginhub robinslange/learning-loop --plugin learning-loopThis skill uses the workspace's default tool permissions.
Quick retrieval of everything the vault holds on a topic. No web research, no enrichment: just surfaces what's already captured. The inward-facing counterpart to `/discovery`.
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.
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.
Share bugs, ideas, or general feedback.
Quick retrieval of everything the vault holds on a topic. No web research, no enrichment: just surfaces what's already captured. The inward-facing counterpart to /discovery.
/refresh "topic": what do I know about this?/refresh: no argument; ask what the user wants to recall/discovery: orient on existing knowledge firstIf a topic was provided, use it. If not, ask.
Spawn a single discovery-vault-scout subagent (subagent_type: learning-loop:discovery-vault-scout) with this prompt:
Search for everything we have on: <topic>
topic: <topic>
vault_path: {{VAULT}}/
The scout handles vault content search (Grep + Glob + vault-search.mjs), episodic memory, and discrimination of confusable pairs. Wait for it to return results.
Read the top note matches from the scout's results (up to 10 notes). For each:
Organize by knowledge depth, not by folder:
## What you know about: [topic]
### Strong knowledge (permanent / well-sourced)
- [[note-name]]: one-line summary
- [[note-name]]: one-line summary
### Working knowledge (fleeting / partially developed)
- [[note-name]]: one-line summary
### Raw captures (inbox / unprocessed)
- [[note-name]]: one-line summary
### Literature
- [[source-note]]: what it covers
### Past conversations
- [context]: key insight from episodic memory
### Connections
- These notes link to each other: [[a]] ↔ [[b]] ↔ [[c]]
- Related project: [[project-name]]
Omit empty sections silently. If nothing is found, say so plainly: "Nothing in the vault on this topic."
Based on what was found:
| Finding | Suggestion |
|---|---|
| Nothing found | "Run /discovery to start exploring" |
| Only raw inbox notes | "Run /inbox to triage, or /deepen on the strongest one" |
| Good coverage, some gaps | "Run /discovery to fill gaps, or /deepen on a specific note" |
| Strong coverage | "You know this well. Anything specific you want to revisit?" |
If the vault scout's discrimination report found confusable pairs in this topic:
PLUGIN/agents/_skills/discrimination.md3-permanent/ or 2-literature/ → Mode A (titles only, "what's the difference?")0-inbox/ or 1-fleeting/ → Mode B (full notes, "is this distinction clear?")If no confusable pairs were found, skip this section silently.
| Agent | Purpose | When |
|---|---|---|
discovery-vault-scout | Vault content/filename search, episodic memory, project index | Step 2: always launched for the search phase |
/refresh produces no new notes. It just shows what's there.