Google Colab GPU integration for training and evaluation. Provides sync commands, completion detection, and troubleshooting.
Orchestrate Google Colab Pro/Pro+ GPU instances as remote training backends via SSH. Compounds /agent-browser (to launch Colab sessions and install colab-ssh) with SSH (to operate…
Colab file paths after unzipping repo. Trigger when: (1) API key file not found, (2) file path errors in Colab, (3) configuring notebook paths, (4) 'yfinance fallback' despite…
Set the collaboration style for a session — step-by-step (guided), deep-think (research-first recommendations), or pair (equal partners switching roles).
Collaboration planning tool — analyze content overlap between you and potential collaborators, propose win-win collaboration formats (cross-posts, interviews, co-authored content,…
Use when you want to understand what Claude contributed vs what you drove in a session. Triggers on: /collab-proof, session retrospective, ai contribution analysis, collaboration…
Async collaborative brainstorming between multiple human+Claude pairs via a shared folder — write-once block files, assembly on read, no merge conflicts.
Collects research sources with quality evaluation. Use when gathering or finding sources, building a source library, searching for academic papers, or performing RADAR assessment.
Generate comprehensive lab member rosters in both markdown and CSV formats. Analyzes member profiles, git history, and alumni information to create detailed rosters with — from…
Research current color trends from Pantone, architecture, film, and design. Use when user asks about trending colors, popular palettes, or wants research-backed color inspiration.
Use when revising a Communication Research (CR) manuscript after a revise-and-resubmit. CR requires two independent reviews to advance, so the hard problem is satisfying two…
Use when defending the research design of a Communication Research (CR) manuscript — experiments (lab/online), panel surveys, and content analysis with intercoder reliability.
Use when building tables and figures for a Communication Research (CR) manuscript so exhibits are self-contained, accessible, and formatted to APA.
Use when deciding whether a communication project fits Communication Research (CR) and is shaped as quantitative, theory-testing social science.
Build and operate the "Community Feedback Harvesting for research and development labs" capability for research and development labs.
Generates complete comorbidity-oriented shared-biomarker bioinformatics research designs from a user-provided disease pair and validation direction.
Search and inspect New Zealand Companies Register records through read-only public website endpoints.
Conduct comprehensive company research and due diligence. Analyze business model, competitive landscape, management, and market position.
Run company research using Primr. Use when the user asks to research, analyze, or investigate a company, or provides a company URL.
Create a company research brief with executive quotes, product strategy, and org context. Use when preparing for interviews, competitive analysis, partnerships, or market — from…
Compare competing hypotheses on a decision-shaped question using an ACH-style evidence matrix (hypotheses × evidence-for/against).
Performs deep 13-dimension competitor analysis with quantitative scoring rubric. Produces a competitor dossier
Research UI component patterns across 60 component types and 95 production design systems (2,676+ examples from component.gallery).
11 academic writing skills. Trigger: writing paper sections, structuring arguments, academic prose. Design: section-by-section guides (abstract, intro, methods, discussion) with…
Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls — from claudianus/superliora
Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls — from majiayu000/claude-skill-registry
Use when a task needs the judgment of a Computer and Information Research Scientist — designing an ablation to attribute an empirical gain, budgeting an NSF CISE proposal against…
Use when a task needs the judgment of a Postsecondary Computer Science Professor — diagnosing why a course's DFW (D/F/withdraw) rate spiked, redesigning an intro programming…
Performs systematic literature review following PRISMA guidelines with search strategy documentation.
Use when auditing an ACM CoNEXT submission for HotCRP readiness, covering the choice between the December and June cycles, the mandatory paper-registration step, the ACM acmart…
Use when writing or revising ML or AI conference papers for venues such as NeurIPS, ICML, ICLR, ACL, AAAI, or COLM, especially when the workflow is conference-first rathe — from…
Use conference poster pitch for academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries.
Constructed language design beyond phonetic palettes — morphology, syntax, the Sapir-Whorf hypothesis as worldbuilding tool, and the conlang-to-culture pipeline.
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedbac — from…
Multi-agent council engine (v2: planner → researcher → critic → synthesizer, plus opt-in tool_executor + coder; CitationLinter verifies every path:line).
把已完成并验证的 R 或 Python 分析打包为客户可独立复现、可直接阅读且保留真实溯源的咨询交付物。用于“给客户交付”“打包结果”或在 05_reports/ 建正式结果包；不用于未完成分析或内部探索。上游为 biostat-principles，文本终审配合 academic-humanizer，签发配合 epi-project-audit。
Record and organize a complex, multi-party, evolving situation involving a contact — a dispute, a scam, a crisis, a "two sides tell opposite stories" tangle, anything that takes…
When two skills, agents, or independent research tracks produce conflicting verdicts on the same output, reads the conflict as a signal rather than an error and harvests new skill…
Detect context drift, rehydration loops, hypothesis sprawl, scope creep, active-mode loss, and durable-state gaps. Recommend the smallest corrective action.
Automatically fetch latest library/framework documentation for Claude Code via Context7 API — from BenedictKing/context7-auto-research
Academic forum for mission-driven project proposals. Climate, education, urban systems, health, civic tech, and ethics.
Contextual Retrieval implementation for RAG - chunks clinical notes with LLM-generated context prepended to each chunk before embedding.
Give MCP clients hosted browser tools for scraping, crawling, structured extraction, search, and computer-use browser automation.
Generates complete conventional non-oncology bioinformatics research designs from a user-provided disease context, process-related gene family or biological theme, and va — from…
Run a finite, high-coverage formal review of an exact candidate against a frozen acceptance contract, using independent perspectives and executable oracles, batching repairs, and…
Provides expertise in converting Figma designs to HTML/CSS using Figma MCP tools, with data attributes for content tracking and comprehensive analysis.
面向中文学术论文的降 AIGC 检测率 Skill。针对知网、万方、维普、Turnitin 中文版的检测机制，识别并消除中文大语言模型的 17 类结构化写作痕迹。采用"定位 → 诊断 → 改写 → 自评 → 复查"五步闭环工作流，分章节差异化策略（摘要/引言/文献综述/方法/结果/讨论/结论），保持学术严谨性前提下通过检测。
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, conn — from…
Drive a live Rocq/Coq proof session through the coqtail-mcp MCP server — start a session from a .v file, step forward/backward to any line, inspect the current goal and hypothesis…
Find authoritative answers from official docs, RFCs, standards, and academic sources — never from blogs or opinions
Board Paper und Business Judgment: Erstellt Entscheidungsunterlagen für Vorstand/Geschäftsführung/Aufsichtsrat mit Informationsgrundlage, Alternativen, Risiken und KI-Ein — from…
Benchmark current research-query and direct lexical baselines against experimental vector, BM25, typed concept-graph PPR, and RRF source selection without replacing production…
Multi-model parallel benchmark methodology for finding harness deficiencies and driving autoresearch-style recursive self-improvement of the CORTEX harness itself.
Personal assistant for university management (Uniremington). Orchestrates Moodle Navigator and ClickUp Manager to sync courses, track deadlines, and manage study materials.
Verification-first methodology for Section I (War Crimes) of the Court of Bosnia and Herzegovina. Citations are verified against the Court of BiH, the ICTY/IRMCT archives and…
Turns a court or tribunal order into a tracked compliance record — every obligation the order actually imposes, its deadline, the responsible party, the evidence needed to show…
Use when the research design is the bottleneck for a 《中国行政管理》 manuscript — choosing and stress-testing a quantitative, qualitative, or normative design and matching it to the…
Use when drafting or revising the literature-review section for a 《中国行政管理》 manuscript, when the public-administration theory anchor is missing, or when the Chinese-governance /…
Use when a 《中国行政管理》 manuscript is at the topic-selection stage and the public-administration theory frame, the research question, or the venue match are unsettled.
Cour Pénale Spéciale de la République Centrafricaine (CPS) / Special Criminal Court in the Central African Republic (SCC-CAR) research, drafting, and analysis.