Menu
Capture an external source as a literature note. Usage: /learning-loop:literature <URL> or /learning-loop:literature "paper title". Fetches content, extracts core ideas in vault voice, writes to 2-literature/ with vault links.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Deep research with the local librarian doing the token-heavy middle. Scope on Claude, Search+Fetch+Extract on the local Ollama model, adversarial Verify + Synthesize back on Claude. Usage: /learning-loop:research "<question>". Falls back to Claude-native WebSearch when the librarian is unavailable or sub-tier.
End-of-session consolidation. Usage: /learning-loop:reflect (no args). Reviews conversation, extracts learnings, routes to auto-memory or vault, cross-links projects, promotes inbox notes. Run after substantial work sessions.
measure whether a /dream pass helps, hurts, or ties against no consolidation. usage: /learning-loop:dream-eval --mode={single|control|repeated} [--passes=N] [--mine]. single scores pre/post on the live corpus; control forks two clones and dreams one; repeated dreams a clone N times and plots the drift + content-survival curve.
Consolidate auto-memory between sessions. Usage: /learning-loop:dream (no args). Four-phase cycle: Orient, Gather Signal, Consolidate, Prune Index. Seven operators: MERGE, RESOLVE, ABSTRACT, COMPRESS, PRUNE, LINK, DATE NORMALIZE. Rebuilds MEMORY.md.
Cross-store correction for a retracted or updated belief. Usage: /learning-loop:rewrite "old pattern" "new pattern" [reason]. Searches vault, auto-memory, and episodic history; presents an impact map for triage; executes user-approved changes; records a supersession so future episodic searches get annotated.
Diagnose your learning-loop installation. Runs health checks, presents issues, offers per-fix remediation, re-runs each check after the fix to confirm. Safe to run anytime; only makes changes you approve. Pass --redact to scan plugin data files for leaked credentials instead.
| name | literature |
| description | Capture an external source as a literature note. Usage: /learning-loop:literature <URL> or /learning-loop:literature "paper title". Fetches content, extracts core ideas in vault voice, writes to 2-literature/ with vault links. |
Launches the literature-capturer agent to capture an external source as a literature note. The agent fetches the source, extracts core ideas in persona voice, finds vault connections and counterpoints, verifies claims, and writes to 2-literature/.
/literature <URL>: fetch and capture a web source/literature <paper title or citation>: search for and capture an academic source/literature: no argument; asks the user what to capture/deepen flags uncaptured sources worth preservingNo argument (/literature):
Use AskUserQuestion:
What source would you like to capture?
- A URL: I'll fetch and extract core ideas
- A paper title or citation: I'll search for it first
Argument provided: Proceed immediately.
Launch the literature-capturer agent with:
{{VAULT}}/The agent definition is at ${CLAUDE_PLUGIN_ROOT}/agents/literature-capturer.md (resolve to a literal path before dispatch — see agents-shared/vault-io.md → Placeholders).
The agent may identify existing vault notes that reference the source without wiki-links. Present these to the user and execute approved edits.
The literature-capturer is a subagent. The literature note it wrote to 2-literature/ bypassed PostToolUse, so backlinks and edge inference didn't run. Replay on the returned path:
printf '%s\n' "$LITERATURE_NOTE_PATH" \
| node "${CLAUDE_PLUGIN_ROOT}/scripts/sweep-hook-replay.mjs" --stdin
Where $LITERATURE_NOTE_PATH is constructed from the agent's response (e.g. {{VAULT}}/2-literature/<filename>, where <filename> is the kebab-case filename literature-capturer returned). The backlink edits from Step 2 happen via main-thread Edit and trigger PostToolUse normally: no replay needed for those. See skills-shared/hook-replay.md for the full pattern.
The agent returns a structured report with the captured note, connections, counterpoints, and related sources. Present it to the user.
literature-capturer agent and its agents-shared/.2-literature/ without asking.