chanw-research
- 139 skills
- 0 followers
- 47 repo stars
- last month last updated
- ▌ Paper Reviewer · chanw-research bundleUse when acting as a journal or grant reviewer and writing formal reviewer-side evaluations focused on methodology, statistics, reporting standards, reproducibility, and constructive feedback.
- ▌ Paper Workflow · chanw-researchUse when deciding which paper-related skill to use or how to sequence manuscript work from project setup through submission and rebuttal.
- ▌ Scientific Writing · chanw-research bundleUse when writing or revising scientific manuscripts, abstracts, figures, or references for journal submission and you need full-paragraph prose, scientific structure, citation-style guidance, or reporting-guideline support.
- ▌ Rebuttal Response · chanw-researchUse when responding to journal or conference reviewer comments and you need a structured author response, aligned manuscript edits, and clear decisions about when to clarify, add evidence, concede, or respectfully disagree.
- ▌ Citation Verifier · chanw-research bundleUse when checking manuscript citations, bibliography hygiene, DOI or PMID completeness, placeholder references, or BibTeX consistency before submission or revision.
- ▌ Manuscript Optimizer · chanw-researchUse when reviewing or revising an academic manuscript whose central claim, evidence chain, figures, terminology, and prose may have drifted out of sync before submission or resubmission.
- ▌
- ▌
- ▌ Reference Audit Guide · chanw-research bundleUse when the user asks for citation-verification principles, reference-audit best practices, or guidance on preventing fake or inaccurate citations in academic writing.
- ▌
- ▌
- ▌ Ask · chanw-researchAsk the wiki a question, retrieve and synthesize relevant pages, optionally crystallize the answer back into the wiki
- ▌
- ▌ Init · chanw-research bundleBootstrap ΩmegaWiki from user sources plus optional discovery, then ingest the final paper set in parallel
- ▌ Check · chanw-researchScan the full wiki to detect health issues and produce a tiered fix-recommendation report (covers all 9 entity types + graph consistency)
- ▌ Reset · chanw-researchReset wiki state to a clean scaffold by scope (wiki / raw / log / checkpoints / all). Useful during development or carefree restarts after a botched setup.
- ▌ Setup · chanw-researchInteractive API key configuration guide — checks current .env state and walks you through Semantic Scholar, DeepXiv, and Review LLM setup
- ▌
- ▌ Ingest · chanw-research bundleIngest a paper into the wiki — creates pages (papers + concepts + people + claims) and builds all cross-references and graph edges. Trigger whenever the user says "ingest", "add this paper", drops a `.pdf` / `.tex` / arXiv URL, or asks to fold a paper into the knowledge base.
- ▌ Refine · chanw-researchGeneral-purpose multi-round iterative improvement — repeatedly calls /review on any research artifact, parses feedback, applies fixes, updates wiki, until the target score is reached
- ▌ Review · chanw-researchGeneral-purpose cross-model review — Review LLM independently reviews any research artifact, outputs structured scores, wiki entity mapping, and improvement suggestions
- ▌ Survey · chanw-researchGenerate a Related Work section for a paper from wiki knowledge — thematic grouping → narrative structure → LaTeX output, following citation-verification and academic-writing
- ▌ Exp Run · chanw-researchFull experiment execution pipeline — prepare code → deploy → monitor → collect results, supporting three run modes
- ▌ Novelty · chanw-researchMulti-source novelty verification — WebSearch + Semantic Scholar + wiki + Review LLM cross-verify — outputs novelty score and recommendations
- ▌ Prefill · chanw-research bundleSeed wiki/foundations/ with domain background knowledge so subsequent /ingest does not create duplicate concept pages for textbook material
- ▌ Discover · chanw-research bundleBuild a ranked shortlist of candidate papers (anchor-driven, topic-driven, or derived from current wiki state) that the user — or an upstream skill — may decide to feed into `/ingest`. Use whenever the user asks "what should I read next", "find papers similar to this one", "recommend related work", "what's around this topic", or whenever `/ingest` is invoked with `--discover`. Does not ingest; only proposes.
- ▌ Exp Eval · chanw-researchExperiment verdict gate — Review LLM independently judges results → 4 verdict paths → auto-update claims confidence, ideas status, graph edges
- ▌ Rebuttal · chanw-researchParse review comments → atomize concerns (Rvx-Cy) → map to wiki claims → check evidence → Review LLM stress-test → generate rebuttal
- ▌ Research · chanw-researchEnd-to-end research orchestrator — idea discovery → experiment design → execution → verdict → paper writing, with human gates and session-resumable state
- ▌
- ▌ Exp Design · chanw-researchClaim-driven experiment design — scope target claims → design experiment blocks (baseline/validation/ablation/robustness) → build run order → optional Review LLM review → write to wiki
- ▌ Exp Status · chanw-researchView the status of all running experiments; optionally auto-collect completed experiments and advance the pipeline
- ▌ Paper Plan · chanw-researchCompile a paper outline from the claim graph — evidence map → narrative structure → section plan + figure plan + citation plan, Review LLM review mandatory
- ▌ Daily Arxiv · chanw-researchDaily arXiv pull, relevance filtering, auto-ingest of high-priority papers, and SOTA update detection
- ▌ Paper Draft · chanw-researchDraft a LaTeX paper from PAPER_PLAN — write each section from wiki sources + generate figures/tables + BibTeX verification + de-AI polish
- ▌ Variable Map · chanw-researchCompare how an empirical variable or construct is measured across papers, including data sources, model roles, and local-project availability
- ▌ Paper Compile · chanw-researchLaTeX compile → PDF — latexmk compile + auto-fix + page count/anonymity/font/[UNCONFIRMED] checks + submission checklist
- ▌ Empirical Ingest · chanw-research将一篇经管实证论文摄取为实证研究 wiki:论文卡片 + 变量 + 数据 + 模型 + 机制 + 识别 + 稳健性 + 异质性 + 表格线索
- ▌