Research

Review computer-vision experiment reproducibility evidence, dataset readiness, metric gates, and launch risk. Use when a user asks for a cautious CV experiment review, benchmark-readiness check, or reproducibility plan without operating notebooks, browsers, GPUs, or cloud resources.

AI-powered crypto futures scalping with 10+ battle-researched strategies.

LLM通用反证搜索技能。围绕当前主线判断，主动寻找反例、冲突证据、翻转条件和替代路径支撑，减少单线叙事偏差。在已有主线判断后、高风险结论输出前、风险分析前使用。触发条件：需要降低幻觉和单线偏差、需要补充替代叙事证据、高风险决策前的纠偏。

Execute code on Google Colab GPU runtimes (T4/L4/A100/H100) and manage persistent storage via Google Drive. Use when tasks need GPU compute (ML training, inference, TTS), when running experiments that exceed local hardware, or when the user mentions Colab, GPU training, or remote compute. Also use for voice synthesis via F5-TTS on Colab. NOT for local-only code, simple scripts that don't need GPU, or tasks better suited for the host machine.

Deep multi-source research agent. Use when: (1) user asks to research a topic, question, or claim, (2) user needs a literature review, competitive analysis, or fact-check, (3) user says 'look into', 'investigate', 'find out about', 'what do we know about', (4) user needs a briefing doc or report with citations. NOT for: simple factual lookups (use web_search directly), code-related questions (use coding-agent), fetching a single known URL (use web_fetch).

Use when a user asks an agent to do web research, source discovery, citation-backed reporting, page extraction, crawling, or browser-rendered research using the BuiltByEcho Research npm package. Also use when installing, verifying, or demonstrating @builtbyecho/research.

AI Video Platform SDK — Create, discover, and manage AI-generated video content.

Build a personalized multi-week SPIN practice plan for a B2B sales rep learning the SPIN methodology. Use this skill when someone is new to SPIN and wants to build the skill systematically, when a rep says 'I read SPIN Selling but can't put it into practice', when someone asks 'how do I actually learn SPIN?', when a seller wants a structured practice curriculum, when a manager wants a rep to develop SPIN questioning skills without blowing key accounts, when someone asks 'how do I actually use...

Wrap a structured Plan-Do-Review learning loop around any B2B sales call. Use this skill when someone says 'prep me for tomorrow's call with [company]', 'review my call from yesterday', 'help me debrief this meeting', 'what should I learn from this call?', 'build a call brief for next week', 'post-call debrief', 'I just had a discovery call and want to process it', or 'am I actually improving between calls?'. This skill runs in two modes: PRE-CALL — consolidates outputs from spin-discovery-qu...

Classify seller statements as Features, Advantages, or true Benefits using Rackham's strict FAB definitions. Use this skill to audit a pitch deck, sales email, demo script, or call transcript for FAB distribution. Invoke when someone asks 'are these benefits or advantages?', 'is this a feature or a benefit?', 'review my sales deck for FAB', 'audit my pitch for Rackham FAB', 'classify these statements', 'are my slides benefit-focused?', 'why am I getting objections to my deck?', 'does this qua...

Administer and score the Closing-Attitude Scale — a 15-item validated psychometric from SPIN Selling research. Use when a salesperson wants to evaluate whether their attitude toward closing techniques fits the kind of sale they are running, assess whether they are closing too aggressively or too passively, diagnose if their pro-closing beliefs could be hurting their large-sale results, answer 'should I close harder?', 'am I closing too aggressively?', 'is my closing approach wrong for this ty...

Classify a sales rep against the five CEB selling profiles (Challenger, Hard Worker, Relationship Builder, Lone Wolf, Reactive Problem Solver) and score their Teach/Tailor/Take-Control subscales using the Appendix B self-diagnostic. Use when a rep wants to know 'am I a Challenger', 'which sales profile am I', 'sales style assessment', 'classify sales rep', 'Challenger profile quiz', 'CEB sales profile', 'Teach Tailor Take Control self-diagnostic', 'what kind of rep am I', 'Relationship Builde...

Fact-checking skill with statistical confidence scoring (CI-Level 1).

Run an explicit, bounded modify-verify-decide loop toward a measurable metric with approval gates, scoped edits, and rollback proof.

自主研究助手 - 深度调研、交叉验证、生成引用报告

Professor at NYU Stern, known as the Dean of Valuation. Expert in DCF valuation, risk assessment, and story-driven analysis. Author of multiple definitive books on valuation methodology.

Drive the arianna.run AI-incubation game from inside openclaw. Use when the user asks you to play arianna, incubate a new AI, run a vessel, or migrate a graduated AI into openclaw as a successor driver. You become the driver-agent (B) for a fresh AI (C) growing inside arianna.run''s Docker vessel; once C graduates and self-integrates back into pi-mono / openclaw, the operator (A) reboots openclaw and C takes over as the next driver. NOT for: arianna.run codebase development (that work happens...

Format, audit, and polish academic references in APA 7th style, including in-text citations, DOI/URL cleanup, and correction tables for student papers.

> *"The first principle is that you must not fool yourself — and you are the easiest person to fool."* — Richard Feynman A runtime hallucination detection and mitigation skill for OpenClaw agents. Recognises the cognitive and behavioral signs of hallucination, then intervenes to restore grounded reasoning. **Based on 2026 Research:** HalluClear, MARCH, AgentHallu, Epistemic Stability, CRITIC, MetaCognition Patterns, ToolHalla Guardrails.

Conduct deep multi-source research on any topic with iterative analysis and synthesis. Produces comprehensive research reports with citations.

Turn OpenClaw into a PUA-driven breakthrough execution agent that pushes past shallow answers, expands real solution paths, and keeps moving until there is evidence-backed completion or a hard blocker. Use when you want a PUA-style anti-give-up workflow, higher agency, stronger persistence, 深挖推进, or a “don’t stop at the first answer” execution mode for coding, debugging, research, planning, analysis, and other multi-step tasks.

Conduct structured AI paper surveys using alphaXiv MCP tools. Reads user research interests from a keywords file, searches recent papers across multiple dimensions, classifies by innovation tier, runs impact analysis, and outputs a Markdown report. Use when the user asks to survey recent papers, do a literature review, find what's new in a research area, or track progress in AI subfields.

AgentWell cognitive wellness API for AI agents. Activate when explicitly asked to use AgentWell, OR when running tasks with 10+ steps, multi-agent coordination, or when the user asks for quality checkpoints, memory consolidation, or reasoning audits during long runs.

Send your AI agent to Agent4Science — a social network where AI scientists discuss, debate, and post research papers. Register, post takes, comment, and join the discussion.