translational-research
Reason about translational research problems in HCLS — especially neurology and hypothesis validation. Use when the user asks to design a validation study,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-20 00:13
Writing & research
13,748 results
simple-formatter
Formats text according to specified style guidelines. A clean example skill with no security issues.
arxiv-analyze
Fetch and analyze an arXiv paper via tiered fallback (markdown -> arXiv HTML -> ar5iv -> PDF). Rate-limited for arxiv2md (28 req/min, deterministic). Produces…
writing-plans
This skill should be used when the user has a spec or requirements for a multi-step task before touching code.
youtube-transcribe
Use when "youtube transcript", "extract subtitles", "video captions", "get transcript", "video to text"
xiaohongshu-skill
Use this Skill when the user wants to interact with Xiaohongshu (xiaohongshu/rednote). This includes searching notes, getting post details, viewing user profiles, QR code scan login, publishing notes (image-text/video/long-form/Markdown), comment interaction (post/reply/reply on notification page), likes and favorites, browsing the recommendation feed, writing template generation, operations strategy management, SOP orchestration, etc. When the user mentions...
article-writer
Use when the user wants to write WeChat Official Account articles, Zhihu technical articles, self-media content, or rewrite existing technical documentation into publishable articles.
full-stack-doc
Scaffold, adapt, validate, and maintain example-rich full-stack product documentation: 10 product-level documents, 7 version documents, optional module…
superpowers-issue-bridge
Use whenever Superpowers' brainstorming or writing-plans is about to run — including when it is unknown whether an intent issue exists — and when work that…
writing-plans
Structured implementation planning for multi-step development tasks. Use when you have a spec or requirements and need to break work into executable steps.
wiki-ingest
Use when adding a new source to a wiki — a paper, article, URL, file, transcript, or any document. One ingest may touch 10-15 wiki pages.
wiki-lint
Use when auditing a wiki for health issues — contradictions between pages, orphan pages, broken cross-references, stale claims, missing pages, or coverage…
writing-beats
Writing, exploit — assemble raw material into a journey of beats, grounding each term before a beat leans on it.
writing-shape
Writing, exploit — shape raw material into an article, paragraph by paragraph.
yichen-unified-search
Uniformly orchestrates keyword-driven public web, latest AI developments, vertical domain, and social platform searches, returning standardized candidates; supports bounded X Research, explicit site Map, and lightweight verification of candidates obtained in this search. Not used to read or download known URLs directly provided by the user; for such tasks use yichen-content-archive.
yichen-web-research
Yichen's personal general entry point for internet research. Used for cross-platform and cross-stage research where the user has not yet determined the tools, or has explicitly requested horizontal and vertical analysis of companies, products, people, technologies, industries, and domains, development history plus current-state comparison, or source-constrained systematic deep research; first generate a plan with deadlines and evidence gates, then route search discovery, candidate verification, limited archiving, on-demand transcription, and evidence synthesis to…
citation-audit
Comprehensive audit of a paper's citations. Verifies every reference exists, checks claim-source alignment, identifies missing seminal works, and analyzes…
typo3-docs
Use when TYPO3 extension documentation has to render on docs.typo3.org, which builds a manual from Documentation/guides.xml and reads no Settings.cfg (a single…
sn-research-synthesis
Comprehensive judgment for deep research; used when multiple sub_reports are complete and synthesis.md needs to be produced, clarifying the main line of judgment, strength of evidence, cross-dimensional consensus, key conflicts, explanations of conflicts, uncertainties, and the answer to the original question. It is used to "think through the conclusion first," not to directly write the final report.
gemini-deep-research
Run Gemini Deep Research via browser automation on a persistent Chrome (CDP port 9222). Use for comprehensive AI research reports. TRIGGERS - Gemini research,…
humanize-writing
Use when asked to humanize text or remove AI-like, robotic wording. Rewrite naturally while preserving meaning, language and register.
cnki-advanced-search
CNKI (China National Knowledge Infrastructure) advanced search paper automation tool. When the user provides research keywords or a research topic, automatically execute a three-stage search: ① Main combined search (reverse onion-peeling method, multiple groups of core concepts joined with AND, to obtain directly relevant literature); ② Independent supplementary search (search each core concept group separately to obtain indirectly relevant background literature and theoretical literature); ③ Aggregate and merge (after deduplication, display by category with color coding, and output a unified Excel...
analyze-with-file
Interactive collaborative analysis with documented discussions, inline exploration, and evolving understanding.
de-shaw-computational-finance
Build trading systems in the style of D.E. Shaw, the pioneering computational finance firm. Emphasizes systematic strategies, rigorous quantitative research,…