From Scholar
Guides usage of scholar plugin surfaces for literature review sessions — UI views, CLI subcommands, and slash commands.
How this skill is triggered — by the user, by Claude, or both
Slash command
/scholar:workflowThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Scholar exposes three concentric surface layers — all backed by the same `scholar.*` MCP tools.
Scholar exposes three concentric surface layers — all backed by the same scholar.* MCP tools.
| Task | UI view | CLI / slash |
|---|---|---|
| Browse papers | scholar.dashboard → CorpusDashboard | scholar list |
| Read paper | scholar.paper.show → PaperDetail | — (open via UI) |
| Synthesis digest | scholar.digest.show → DigestPanel | scholar digest / /scholar:digest |
| Reading prompts | scholar.prompts.show → ReadingPromptsPane | — (open via UI) |
| Reading progress | scholar.progress.show → ReaderProgress | — (open via UI) |
| Ingest | — | scholar ingest / /scholar:ingest |
| Status | — | scholar status / /scholar:status |
scholar.*. The vendored pdf MCP child surfaces as scholar.pdf.* proxies — never invoke raw pdf.* from a host.window.cowork.askClaude is a function. In hosts without it, a static "Claude fallback unavailable in this host." note appears in its place and the toggle is hidden.--claude (CLI) and "Use Claude instead" (UI) are explicit per-request opt-ins — never the default path.ctx.db at entry (§7.6); a corpus.activate mid-session swaps the active corpus for the next call, not the current one.docs/superpowers/specs/2026-05-22-scholar-plugin-design.md (§9 view contracts, §11 askClaude sentinel, §13 annotation reconciler)bin/scholar.nu (transport + exported subcommands)skills/{ingest,digest,status}/SKILL.md (the /scholar:* slash surfaces)npx claudepluginhub zaynram/cowork-marketplace --plugin scholarSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.