/kb-literature-review
Run the project-scoped literature workflow from Sources/Papers into Knowledge, Writing, and Maps/literature.canvas.
> /plugin marketplace add Galaxy-Dawn/claude-scholar > /plugin install claude-scholar@claude-scholar
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/kb-literature-review
Context preview
What this command does when you run it.
Run the project-scoped literature workflow from Sources/Papers into Knowledge, Writing, and Maps/literature.canvas.
Command definition
kb-literature-review.mdname: kb-literature-review description: Run the project-scoped literature workflow from Sources/Papers into Knowledge, Writing, and Maps/literature.canvas. tags: [Research, Obsidian, KB, Literature]
/kb-literature-review
Use `obsidian-literature-workflow`.
Conditional outputs:
- `Knowledge/Literature Overview.md` only when paper notes contain enough Evidence Records for synthesis
- `Knowledge/Method Taxonomy.md` when useful and evidence-backed
- `Knowledge/Research Gaps.md` when useful and evidence-backed
- `Knowledge/Claim Map.md` or a warning when evidence is weak
- `Writing/related-work-draft.md` only when promoted claims pass the evidence gate
- `Maps/literature.canvas`
Keep source notes in `Sources/Papers/`. Do not turn source notes into synthesis notes.
Evidence gate:
- refuse polished `Knowledge` or `Writing` synthesis when paper notes lack Evidence Records,
- keep abstract-only or webpage-placeholder items in coverage / `To-Read`,
- generate a warning or `Knowledge/Claim Map.md` instead of a mature related-work draft when evidence is weak,
- preserve claim strength on literature canvas edges.
Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.
Repo: Galaxy-Dawn/claude-scholar
Other commands on claude-scholar.
- /analyze-results
Optional experiment line slug for report naming
Open command - /build-fix
Incrementally fix Python type and lint errors:
Open command - /checkpoint
Create or verify a checkpoint in your workflow.
Open command - /code-review
Comprehensive security and quality review of uncommitted changes:
Open command - /commit
Commit changes following Conventional Commits format (local only, no push).
Open command - /create_project
δ½Ώη¨ζ¬ε°ζ¨‘ζΏ ~/Code/template θι GitHubοΌθ¦η template_repoοΌ
Open command