Research & Search

plamentsv Skill

Type Thought-template (instantiate before use) - Research basis Multi-block arbitrage windows, bridge latency exploitation

plamentsv Skill

Type Thought-template (instantiate before use) - Research basis Donation attacks via unsolicited token transfers

plamentsv Skill

Type Thought-template (instantiate before use) - Research basis Cached parameters in multi-step operations become stale when governance changes them mid-operation

plamentsv Skill

Protocol Type Trigger NAMED_EXTERNAL_PROTOCOL (detected when recon finds import/interface for an identifiable external protocol — not standard libraries). Researches known integration hazards of the target protocol.

majesticlabs-dev Skill

Autonomous task implementation - research, plan, build, review, fix, ship

majesticlabs-dev Skill

Automatically check and update folder-specific AGENTS.md during research. Before investigating a domain, read nearest AGENTS.md for existing context. After discovering valuable patterns, append learnings to that file.

antgroup Bundle

Generate persuasive alternative science explanations that downplay established evidence and package misleading health or research claims for public distribution.

junmystery Skill

Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.

junmystery Bundle

Canonical scientific research covering PubMed, USPTO database queries, gget package workflows, literature reviews, and scholar evaluations.

junmystery Skill

Unified prediction-market and Itô basket operations, covering read-only market intelligence, probability research, non-advisory basket comparisons, trade planning, and oracle data ingestion.

benbrastmckie Skill

Project research with scope analysis and timeline estimation

benbrastmckie Skill

Research timeline planning for medical research projects. Invoke for timeline tasks.

benbrastmckie Skill

Conduct web development research using framework docs and codebase exploration. Invoke for web research tasks.

benbrastmckie Skill

Research Z3/SMT tasks. Invoke for Z3-language research.

benbrastmckie Skill

Research Lean 4 and Mathlib for theorem proving tasks. Invoke for Lean-language research using LeanSearch, Loogle, and lean-lsp tools.

benbrastmckie Skill

Research mathematical tasks using domain context and codebase exploration. Invoke for math-language research involving algebra, lattice theory, order theory, topology, and category theory.

benbrastmckie Skill

Conduct Neovim configuration research using plugin docs and codebase exploration. Invoke for neovim research tasks.

benbrastmckie Skill

Research mathematical logic tasks using domain context and codebase exploration. Invoke for logic-language research involving modal logic, Kripke semantics, and related mathematical foundations.

benbrastmckie Skill

Pitch deck content research through material synthesis

benbrastmckie Skill

Coordinate formal reasoning research across logic, math, and physics domains. Invoke for formal-language research requiring cross-domain coordination.

benbrastmckie Skill

Research physics formalization tasks using domain context and codebase exploration. Invoke for physics-language research involving dynamical systems, chaos theory, and related formalization.

benbrastmckie Skill

Research Python development tasks. Invoke for Python-language research.

benbrastmckie Skill

Research skill for epidemiology and study design

peterbamuhigire Bundle

Use when defining an AI hallucination SLO for factuality, citation validity, abstention, severity, sampling, error budget, and release response; use saas-slo-and-error-budget-doc for ordinary service reliability.

starchild-ai-agent Skill

Jeffrey Tang's personal trading research methodology: HFT/quant strategy, deep due diligence, tokenomics & unlock analysis, DeFi protocol diligence, and branded deliverable production. Use when doing any of: building/backtesting trading strategies, researching tokens/protocols, producing investment dossiers or 1-pagers, analyzing market structure, or creating AlphaRunner-branded outputs.

starchild-ai-agent Skill

Work as the user's analyst in the established Giles mode: execute requested research, drafting, analysis, and follow-through while accepting direct management and career coaching. Use when the user asks for Giles, employee mode, an analyst deliverable, delegated execution, progress reporting, or feedback framed for a talented junior employee.

starchild-ai-agent Skill

Summarize YouTube videos by fetching their transcript and generating a structured summary. Use when the user shares a YouTube link and wants a summary, key points, or content overview of the video.

starchild-ai-agent Bundle

Rate the research QUALITY of a pre-TGE / pre-launch research paper itself — evidence, logic, valuation rigor, risk honesty, and argument structure. For grading a note's content as research, not for grading whether the trade is actionable (use research-article-grader for that).

starchild-ai-agent Bundle

自动搜索全网前沿实验方案（学术论文、开源硬件、竞赛项目、创客社区）， 评估可行性后生成完整实现（BOM采购清单、固件代码、电路图、3D打印件、 Web仪表盘、教学文档）。 Use when exploring new experiment ideas, searching for cutting-edge DIY/physics/engineering project implementations, or when the user says "找一下XX实验/项目/方案" and wants a complete, buildable solution.

starchild-ai-agent Bundle

Use this skill for meme/打狗/alpha token research on pump.fun and similar launchpads: scanning new token launches, checking developer reputation/开发者信息 and past rug pull history, bundle/sniper detection/捆绑狙击, bonding curve status, finding similar tokens by the same dev, and wallets that co-invested (同车/aped) into a token. Use when the user asks about 'new meme coins', 'pump.fun launches', 'trenches', 'trench', 'scan trenches/扫链', 'check dev reputation', 'bundler analysis', 'who else bought this token', '打狗', '新盘', or '开发者信息'. Do NOT use for market-wide whale/smart-money signals — use okx-dex-signal. Do NOT use for per-token holder distribution or honeypot checks — use okx-dex-token.

cowork-os Bundle

Plan and execute parallel, repeatable migrations across code, docs, research artifacts, ops configs, or mixed task sets.

cowork-os Skill

Write viral, persuasive tweets and threads optimized for X's algorithm. Research viral examples in your niche, then craft content using proven hook formulas and copywriting frameworks.

cowork-os Bundle

Fetch transcripts, metadata, and captions from YouTube videos. Use when you need to summarize a video, answer questions about its content, extract key points, compare videos, or pull quotes with timestamps. Supports auto-generated and manual captions, multiple languages, and translation.

cowork-os Bundle

Improve existing work with focused simplification passes across code, writing, research, operations, or general tasks.

cowork-os Skill

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

cowork-os Skill

GitHub research subagent for Pi that uses gh workflows to find and cite relevant repo files before implementation.