Research skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
web-navigation-strategies
Strategic navigation patterns and selector guides for thorough web exploration using Playwright MCP. Provides decision trees, navigation strategies, and site-specific selectors for reading multiple pages systematically. Use when planning how to navigate websites, determining reading depth, or finding the right selectors for Playwright MCP commands.
ak-rss-digest
Curate a Chinese reading digest from a fixed bundle of RSS and Atom feeds, with a strong preference for AI agent thinking, frontier AI commentary, deep interviews, and non-boring high-signal essays. Use when Codex needs to pull the latest week's posts by default, or a specific day's posts when explicitly requested, summarize them, score each article on a 10-point scale, and output only the posts scoring above 7 in a concise Chinese daily-brief style.
ccf-experiment-designer
Design CCF paper evidence packages: datasets, baselines, metrics, ablations, robustness tests, result-table templates, and real-result figure/table presentation. Use for experiment design, benchmark planning, baseline selection, ablation design, result tables, publication figures from supplied numbers, 设计实验, 对比实验, 消融, 结果图表. Do not invent results.
ccf-idea-optimizer
Turn rough CCF research directions into concrete problem, gap, insight, method, novelty, and evidence plans. Use for idea optimization, fuzzy idea concretization, research direction shaping, early direction exploration, salvage routes, 优化idea, 具象化idea, 研究思路优化, 找方向, 方向探索. Do not rank or score multiple ideas as the main output.
ccf-idea-reviewer
Strictly score, rank, compare, and triage early CCF research ideas with prior-art awareness and venue-fit risk. Use only for explicit idea scoring, idea ranking, idea review, acceptance-potential triage, idea评分, 选题评分, 选题排名, 严格评审. Do not polish manuscripts, brainstorm directions, or optimize a single idea unless scoring is explicit.
ccf-literature-monitor
Monitor arXiv, OpenReview, conference feeds, labs, projects, and competitor papers for new work that may overlap with a user's idea. Use for arxiv-watch, novelty-check, trend-scouting, competitor-tracking, paper tracking, 竞品监控, 新论文追踪, 论文跟踪, 类似 idea 监控. Link findings to ccf-literature-searcher, ccf-idea-reviewer, ccf-idea-optimizer, ccf-paper-writer, and ccf-integrity-auditor.
ccf-literature-searcher
Search and screen literature, related work, datasets, benchmarks, citation evidence, and research opportunity maps for CCF workflows. Use for literature search, related work, prior art, benchmark search, direction scouting, 文献检索, 相关工作, benchmark搜索, 方向调研. Do not audit only already-cited references or write the manuscript as the main task.
chatgpt-web-research
Use the user's already signed-in official ChatGPT website account, especially GPT-5.5 Pro / ChatGPT Pro, to perform product research, market research, competitor research, second-opinion research, or any browser-only work. Load chrome:control-chrome first, then computer-use:computer-use for fallback. Save verified Markdown reports. Do not use free-account routes, OpenAI API, local models, web search, or memory when the real ChatGPT web page is available.
influencer
Research influencers on Instagram, TikTok, and X/Twitter through your browser