From learning-loop
Batch triages 0-inbox/ notes by classifying intention status, clustering topics, auto-promoting mature ones, surfacing top-5 limbo for decisions, and sweeping 1-fleeting/ to archive with approvals.
npx claudepluginhub robinslange/learning-loop --plugin learning-loopThis skill uses the workspace's default tool permissions.
Launches the `inbox-organiser` agent to process all notes in `0-inbox/`. The agent clusters by topic, assesses maturity via the promote-gate skill, detects counter-arguments, and executes promotions autonomously. Merges and deletes require approval.
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.
Launches the inbox-organiser agent to process all notes in 0-inbox/. The agent clusters by topic, assesses maturity via the promote-gate skill, detects counter-arguments, and executes promotions autonomously. Merges and deletes require approval.
/reflect sessions that deposited notesThis skill emits provenance events for pipeline observability. Run each Bash command silently.
At session start:
node "${CLAUDE_PLUGIN_ROOT}/scripts/provenance-emit.js" '{"agent":"inbox","skill":"inbox","action":"session-start"}'
At session end:
node "${CLAUDE_PLUGIN_ROOT}/scripts/provenance-emit.js" '{"agent":"inbox","skill":"inbox","action":"session-end","promoted":N,"deleted":N,"merged":N,"limbo":N}'
Per-note tracking is handled automatically by the PostToolUse hook.
Launch the inbox-organiser agent with:
{{VAULT}}/all (or topic:<name> if the user specified a topic filter)The agent definition is at PLUGIN/agents/inbox-organiser.md.
Use subagent_type: "learning-loop:inbox-organiser" with the full prompt from the agent definition, or launch as a general-purpose agent that reads the agent file.
Before the agent returns, check the librarian queue for pending observations targeting inbox notes.
Read PLUGIN_DATA/librarian/queue.jsonl (where PLUGIN_DATA = CLAUDE_PLUGIN_DATA env or ~/.claude/plugins/data/learning-loop). Parse each line as JSON. Filter to items where status === 'pending', target starts with 0-inbox/, and task is one of: voice_flag, tag_suggestion, duplicate_flag.
If matches exist, include them as advisory context when presenting the agent's results, grouped by task type:
Librarian observations:
Voice flags:
"gmail multi daemon pull deduplication": Names a topic, not an insight. Consider retitling.
Tag suggestions:
"ginkgo biloba acute pk profile" → pharmacology, neuroscience
Duplicate flags:
"foo-claim.md" ↔ 3-permanent/foo-claim-original.md (similarity 0.93)
...
These are informational: the user decides whether to act on them during triage. Apply or dismiss them in /health --librarian.
When the agent returns, it will list any actions needing approval (merges, deletes). Present these to the user and wait for confirmation. Execute approved actions.
The agent returns a structured summary. Present it to the user.
inbox-organiser agent and its _skills/._archive/1-fleeting/.