write-literature-reviewlisted

# Write Literature Review ## Overview Use this skill when the user wants a serious literature review rather than a quick paper list. The workflow is intentionally iterative: search broadly, expand by citations, screen with judgment, repeat until saturation, then read deeply and synthesize. Keep a separate execution log throughout the whole workflow at `logs/workflow_log.md`. Update it step by step as work happens. The log should record what you did, what inputs you used, what outputs you produced, what you learned, and what decision or next action followed. ## Workflow Use `references/workflow.md` as the authoritative workflow. At a high level, the agent should: 1. Clarify scope, confirm the citation format, and record the setup in `plan/review_plan.md`. 2. Draft up to 10 search keywords and save them in `search/seed_keywords.json`. 3. Build a seed set with `scripts/lit_review_pipeline.py search`. 4. Screen by title and abstract, then iteratively expand and rescreen until saturation. 5. Rank the final filtered set and inspect up to 30 full texts. 6. Build the knowledge graph artifacts. 7. Write `review/literature_review.md`, render the final deliverables, and finalize `logs/workflow_log.md`. When there is any ambiguity about step order, stopping conditions, screening rules, or expected intermediate files, defer to `references/workflow.md`. ## Workspace Layout Keep only three presentation files at the workspace root: - `literature_review.pdf` - `references.md` - `kn