Research skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

staking-receipt-tokens

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

264 repo starsObserved in 1 repos
Research

pm-data-discovery

用于先搞清楚“有哪些数据可看、怎么搜索目标市场、怎么落地数据样本”的技能。只做数据发现与取数,不做策略假设。

261 repo starsObserved in 1 repos
Research

synthesizer

将多个研究智能体的发现综合成连贯、结构化的研究报告。解决矛盾、提取共识、创建统一叙述。当多个研究智能体完成研究、需要将发现组合成统一报告、发现之间存在矛盾时使用此技能。

260 repo starsObserved in 5 repos
Research

got-controller

Graph of Thoughts (GoT) Controller - 管理研究图状态,执行图操作(Generate, Aggregate, Refine, Score),优化研究路径质量。当研究主题复杂或多方面、需要策略性探索(深度 vs 广度)、高质量研究时使用此技能。

260 repo starsObserved in 4 repos
Research

research-executor

执行完整的 7 阶段深度研究流程。接收结构化研究任务,自动部署多个并行研究智能体,生成带完整引用的综合研究报告。当用户有结构化的研究提示词时使用此技能。

260 repo starsObserved in 4 repos
Research

azure-naming-research

Research Azure naming constraints and CAF abbreviations for a given resource type. Use when you need to look up the official CAF slug, naming rules (length, scope, valid characters), and derive validation/cleaning regex patterns for an Azure resource. Triggers on: CAF abbreviation lookup, Azure naming rules research, resource naming constraints.

260 repo starsObserved in 3 repos
Research

designing-the-analysis

Use when you have an approved research question and need a concrete analysis plan, before touching outcome data or fitting any model

260 repo starsObserved in 2 repos
Research

dispatching-parallel-investigations

Use when facing 2+ independent investigations that can proceed without shared state - parallel literature survey, multi-dataset replication, or pre-specified robustness checks

260 repo starsObserved in 2 repos
Research

framing-research-questions

You MUST use this before any data analysis or investigation - before exploring a dataset, loading or profiling data, running a model, computing a statistic, or testing an idea, and before any outcome data is touched

260 repo starsObserved in 2 repos
Research

subagent-driven-analysis

Use when executing a pre-registered analysis plan with mostly independent steps in the current session

260 repo starsObserved in 2 repos
Research