Incorrect citation metadata can undermine manuscripts and delay publication. This skill compares references with authoritative sources and produces evidence-based corrections.

Full paper translation can lose figures, tables, and source context. This skill creates a grounded Markdown reader with Chinese-English blocks, source anchors, and figure placement.

Scientific papers are difficult to evaluate when claims, methods, and evidence are scattered across sections. This skill creates a structured, traceable Paper Card with explicit limits.

Researchers often need a clear presentation from a dense paper. This skill turns papers into concise Chinese PPTX decks with figures, notes, and QA checks.

Keeping current with research requires repeated searching, filtering, reading, and organizing. This skill defines a configurable workflow for recurring discovery, delivery, and archival.

Scientific figures often fail because story, evidence, export, and review checks are separated. This skill guides Claude, Codex, and Claude Code through one publication-ready workflow.

Scattered laboratory notes make experiments difficult to review and reproduce. This skill organizes mixed source material into structured Markdown records with linked attachments.

Finding authorized full text across publishers, repositories, and institutional portals is slow. This skill routes requests and verifies downloaded academic files.

Researchers need defensible citations that match each manuscript claim and journal scope. This skill segments text, searches Nature/CNS-family metadata, and exports reference-manager files.

Researchers need reliable literature discovery across fragmented academic indexes. This skill coordinates source routing, citation checks, MeSH planning, and citation file conversion.

Lemon8 research often requires searching posts, profiles, topics, and trends across several endpoints. This skill routes requests to MaxHub APIs and returns concise discovery, comparison, and analysis results.

Content teams need fast signals from public hot lists before topics fade. This skill fetches TopHub trends and asks Claude to turn them into practical topic ideas.

Misleading media often pairs authentic pixels with false captions, while detector scores create false certainty. This skill prioritizes provenance, physical consistency, and transparent limits.

Reverse image results often confuse similarity with provenance and can expose sensitive material. This skill guides multi-engine searches, preprocessing, source validation, and responsible confidence grading.

Xiaohongshu research is slow when teams inspect posts manually. This skill searches public notes, sorts results, and returns structured outputs for review.

Teams need fast visibility into public Douyin trends. This skill searches keywords and returns structured video, image, author, and engagement data.

Clean webpage content is hard to collect when pages include navigation, scripts, and formatting noise. This skill extracts readable markdown or text from known URLs through Tavily.

Unstructured web search can turn stale or repeated claims into false confidence. This skill routes verification through target types, source tiers, freshness checks, and abstention rules.

Current research requests need sources beyond model training data. This skill uses the Skywork API to search the web and save source-backed results.

Long videos are hard to review and cite later. This skill extracts YouTube transcripts and creates structured summaries for research, learning, and documentation.