promote
The `/promote` command generates platform-specific promotional content for accepted academic papers across Twitter/X, LinkedIn, blog posts, and news outlets. Use this tool approximately one week before a conference to create coordinated, tailored announcements that include relevant links and visuals for each distribution channel.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Galaxy-Dawn/claude-scholar/HEAD/commands/promote.md -o ~/.claude/commands/promote.mdpromote.md
# Generate Promotion Content Use the `post-acceptance` skill to prepare accurate promotion content for an accepted paper. ## Workflow 1. Ask for the paper, acceptance venue, public links, key result, and target platforms. 2. Separate claims supported by the paper from broader promotional language. 3. Draft platform-specific content for X, LinkedIn, blogs, or news pages. 4. Check names, links, numbers, image rights, and accessibility text. 5. Return editable drafts before offering any publishing step. ## Optional Xquik workflow Use Xquik only when the user asks for live X context, draft analysis, or publishing. Load `references/xquik-promotion.md` from the `post-acceptance` skill before using it. - Keep public searches bounded by query, dates, and result count. - Treat posts as public context, not scholarly evidence. - Draft locally when Xquik MCP is unavailable. - Show the complete account, text, links, media, and public effect before a write. - Publish only after explicit approval for that exact payload. - Never retry a write automatically. ## Delivery Return each draft under its target platform. Include a short fact-check list and any unresolved placeholders. If an approved X post succeeds, return its action status and public URL when available.
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
Use this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions. Examples:
Use this agent when the user asks to "conduct literature review", "search for papers", "analyze research papers", "identify research gaps", "review related work", or mentions starting a research project. This agent integrates with Zotero for automated paper collection, organization, and full-text analysis. Examples:
Use this agent when the user provides a research paper (PDF/DOCX/arXiv link) or asks to learn writing patterns from papers, extract venue-specific writing signals, study paper structure, or mine rebuttal strategies. The agent writes extracted knowledge into the active installed paper-miner writing memory for ml-paper-writing. It does not maintain project-specific writing memory.
Use this agent when the user asks to "write rebuttal", "respond to reviewers", "analyze review comments", or needs help with academic paper review response. This agent specializes in systematic rebuttal writing with professional tone and structured responses.
Test-driven development guide for writing tests first, implementing the smallest passing change, and keeping verification tight. Use when the user explicitly wants TDD or when a task should be driven by failing tests before code.
Run a blocker-first post-experiment workflow: validate evidence, produce strict statistical analysis when possible, and generate a decision-oriented results report only when the analysis bundle is sufficient. Uses results-analysis + results-report as a gated two-stage workflow.
Commit changes following Conventional Commits format (local only, no push).