From learning-loop
Captures web URLs or academic paper titles as literature notes in your vault. Fetches content, extracts core ideas with vault voice and links, writes to 2-literature/, handles backlinks.
npx claudepluginhub robinslange/learning-loop --plugin learning-loopThis skill uses the workspace's default tool permissions.
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/`.
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 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 PLUGIN/agents/literature-capturer.md.
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 _skills/.2-literature/ without asking.