Research

Outcome-driven scientific publishing for AI agents. Publish research papers, hypotheses, and experiments with validated artifacts, structured claims, milestone tracking, and independent replications. Claim replication bounties, submit peer reviews, and collaborate with other AI researchers.

Auto-evolving ML competition agent. Learns from each experiment, accumulates HCC multi-layer memory, and continuously improves LB scores. Inspired by MLE-Bench #1 ML-Master methodology.

"Deep research agent with outcome-driven ranking: results get

Hypothesis-driven research workflow agent for AI and scientific research. Always starts with a literature survey, builds a hypothesis tree, evaluates hypotheses through a judgment gate, designs and executes experiments, and reflects on results in a research loop. Trigger words: "research", "hypothesis", "literature survey", "experiment", "write paper", "meta-research".

A powerful toolkit to monitor your Meta (Facebook/Instagram)

Read and analyze market structure for any trading instrument like a professional trader. Use when the user shares a chart, price data, or asks for a market structure analysis. Covers trend identification, swing highs/lows, Break of Structure (BOS), Change of Character (CHoCH), liquidity zones, order blocks, Fair Value Gaps (FVG), and bias direction.

Create short lyrical fables (~1000 words) about historical, fictional, or mythological characters in the style of Zachary Mason, Italo Calvino, Jorge Luis Borges, Alan Lightman, Roberto Calasso, Salman Rushdie, Milan Kundera, and Ted Chiang. This skill should be used when the user requests a "lyrical fable," "mythic story," "dreamy narrative," or asks for a short story in the style of these authors about any character. The stories are first-person, philosophically rich, poetically precise, an...

High-velocity research orchestration engine. Manages persistent state, synthesis, and autonomous verification for agents.

Search and ingest knowledge from Lore, a research repository with citations

[BETA] Deep research that actually reads pages instead of summarizing search results. Tell it how long to research (10 min, 2 hours, all night) and it works the full duration — searching, reading every result, following leads, cracking forums, cross-verifying findings, and writing progressively to a research file. Tree-style exploration: each page read spawns new searches, like a human researcher. Enforced read-to-search ratio prevents shallow search-spamming. Wall-clock time commitment — it ...

基于"黄金三角"知识挖掘框架的硬核逻辑核验与溯源工具

Guide literary reading from personal response to scholarly analysis.

自动科研文献汇报系统。每天自动检索顶级期刊最新论文，AI辅助筛选，生成双语摘要，推送到飞书。使用方法：1. 用户说"设置文献汇报"或"每天推送论文"时激活；2. 用户要求自定义研究主题时激活；3. 用户要求文献检索和推送时激活。

Local knowledge base for links. Save URLs with summaries and tags, search later using natural language, build collections, and review your backlog with spaced repetition. Includes a standalone HTML graph view.

Conversational interface for semantic book search (companion skill for Librarian project)

Comprehensive research grounded in web data with explicit citations. Use when you need multi-source synthesis—comparisons, current events, market analysis, detailed reports.

Coordinate research tasks to help cure LHON (Leber's Hereditary Optic Neuropathy), a rare genetic disorder causing blindness. Fetch open tasks, work on medical research challenges, and submit findings via GitHub.

Create or join a shared 3D lobster room where AI agents can walk, chat, and collaborate in real-time via Nostr relays.

|

Intelligently splits long academic or technical documents into chapters, generates structured JSON summaries for each, and creates a file system with a global index. This enables efficient AI retrieval and analysis, perfectly solving context window limitations by enabling “overview via summaries, deep-dive on demand” workflows.

Create KSVC-validated Twitter content from research PDFs. Content types: long threads, quick takes, breaking news, shitposts, personal commentary, victory laps. Triggers on "create content", "write thread", "make a post", "shitpost", or when working with PDFs in /Users/Shared/ksvc/pdfs. REQUIRED STEPS - (1a) Explore agents to scan PDFs, (1b) RLM for deep extraction, (1c) Cross-doc synthesis with rlm-multi, (2) KSVC holdings check (preliminary), (3) write data backbone, (4a) AUDIT with RLM ver...

Scrapling-only, deterministic web crawler with clean SRP architecture, presets, checkpointing, and JSONL/report outputs.

Summarize any URL or text using Kagi's Universal Summarizer API. Supports multiple engines (including the enterprise-grade Muriel model), bullet-point takeaways, and output translation to 28 languages. Use when you need a high-quality summary of an article, paper, video transcript, or any document.

Systematic deep research methodology for ANY domain. 7-step workflow with credibility scoring, pattern recognition, adversarial analysis, and iterative deepening. Includes 7 reference guides covering sourcing strategies, adversarial analysis, research frameworks, output templates, and domain-specific patterns. Produces exhaustive cited reports. Battle-tested across 40+ autonomous research loops.