Research
Research, evidence gathering, literature, reports, investigation, and synthesis
Browse research skills
Showing 19,609–19,632 of 22,697 skills
Collects project state, materials, constraints, and desired output for the Research Architect workflow.
Builds an evidence bank, claim register, and figure plan from available results or executed study outputs.
Builds the first complete research-paper draft from the confirmed spine, evidence bank, claim register, citation bank, and writing rationale matrix.
Converts a confirmed research spine into an executable study, experiment, analysis, or validation plan.
Builds a claim-level citation support bank for background, positioning, methods, interpretation, and limitations.
Converts a raw topic or scattered materials into feasible research-question candidates and candidate research spines.
Audits the first-paper workflow artifacts and draft for spine clarity, evidence traceability, citation integrity, copying risk, and overclaiming.
> Summarize any webpage or article into key points.
This skill is used when Mira needs to analyze SEC disclosure itself, not merely cite SEC as a source. It supports two routes: - `sec_supplement`: lightweight SEC fact verification inside another research workflow. - `sec_filing_deep_dive`: dedicated analysis of a filing such as 10-K, 10-Q, S-1, 8-K exhibit, DEF 14A, 13F, or Form 4.
这个 skill 用于解读券商、卖方、机构、专家或投资者研究报告。它的目标不是复述研报,而是把一份报告拆成可验证 claim、隐含假设、预期变量、估值驱动和对 Mira thesis 的增量影响。 研报在 Mira 中默认是 `sellside_and_expert_research`,通常是 `L3 secondary / signal`。它可以帮助识别框架、预期差、变量优先级、估值方法和叙事变化,但不能替代公司披露、监管文件、官方数据、市场数据或可复算模型。
这个 skill 用于把宏观经济分析转成可执行的资产定价判断。 它不是宏观背景介绍,也不是经济学教材式综述。它服务于一个核心问题: > 当前宏观状态是否正在改变目标资产的盈利路径、贴现率、风险溢价、流动性、仓位或催化剂时间表?
这个 skill 用于把一个不清晰的产业概念快速拆成可研究、可跟踪、可映射到标的的产业链框架。 典型输入包括: - `存储` - `CPU` - `GPU` - `ABF` - `HBM` - `CPO` - `液冷` - `先进封装` 它不是单票研究,也不是主题营销材料。它的目标是回答: > 这个概念到底是什么,产业链谁负责什么,利润池和瓶颈在哪,哪些环节有定价权和放量弹性,哪些公司最值得进入下一轮单票研究。
这个 skill 用于查找新上市、即将上市、已提交申请或刚被媒体/发行人宣布的 ETF/ETP。 它是 `etf-listing-analysis` 的前置发现层: ```text ETF listing discovery -> new-etf-watchlist -> ETF listing analysis ``` 它不负责深度判断 ETF 是否值得买入,只负责把候选产品找出来、去重、补齐关键字段、排序,并决定哪些进入 `etf-listing-analysis`。
这个 skill 用于分析新上市 ETF、即将上市 ETF、ETF 申请文件和 ETF 产品线扩张。 它不把 ETF 新上市直接等同于买入信号,也不要求新 ETF 在首轮分析中已经完成资金验证。新上市本身首先是一个 `product signal`:发行人为什么现在愿意把某类暴露做成产品,想卖给谁,底层持仓和权重机制会把这个信号传导到哪里。 核心目标是回答: 新 ETF 上市到底代表真实配置方向、交易工具需求、资产可达性变化、用户偏好,还是主题营销和周期尾声包装?
这是当前主 research skill,用于在单次研究中统一处理: - 基本面 - 财务质量 - 宏观经济与金融条件 - 技术面节奏 - 事件与舆情 它不是多个独立 skill 的简单拼接,而是一个面向 `research package` 的主 skill。 这个 skill 现在采用: - 一个统一输出骨架 - 一个 upstream analysis router - 一个 thesis horizon router - 一个 framework router - 一个 overlay selector - 多个可切换研究框架 也就是说,输出仍然统一,但研究顺序、证据权重和结论重心会随时间跨度和标的的定价主导变量变化。 在主框架之外,还允许叠加专题 `overlay`,用于补充特定研究路径。
这个 skill 用于对单家公司的一份季报、半年报或年报做结构化分析。它服务于 `research package`,但输出重点从完整投资 memo 收窄到财报质量、经营变化和预期差。 默认时间跨度是 `near_term_execution` 到 `medium_term_revision`。只有当本期财报证据触及长期驱动变量,并且被订单、客户、产能、现金流、同行或产业链证据支持时,才允许把结论升级为 `long_term_thesis` 或 `regime_transition`。
这个 skill 用于在 Mira 研究中判断数量型结论是否需要可复算数据、工具计算或显式降级。 它不是一个独立数据分析插件,也不绑定 Data Analytics、Python、Spreadsheet 或外部 API。它的职责是把 LLM 从“直接给数字结论”约束为: - 先提出数据需求 - 再判断是否必须计算 - 决定是否需要征求用户同意动用工具 - 记录公式、口径、来源和限制 - 对没有完成计算的数量型结论降级
这个 skill 用于研究实物大宗商品、商品期货曲线、资源周期和商品价格对资产的传导。 它不是泛宏观综述,也不是资源股单票模板。它服务于一个核心问题: > 当前商品价格到底由供需平衡、库存、成本曲线、政策/地缘风险、金融条件还是仓位驱动?这个驱动是否足以改变目标资产的盈利、估值、风险溢价或交易节奏?
Insert, format, and cross-reference academic citations in Word (.docx) documents. Supports GB/T 7714-2015 (Chinese), IEEE, and APA 7th.
Use when generating or publishing Project Sentinel midday or close reports and report quality must be checked before AI narration or publishing.
Parallel autonomous ML research agents with a Director, git worktrees for per-agent experiment branches, a Skills library for validated technique reuse, a Synthesizer that distills collective knowledge overnight, and circadian rhythm (leisure 03:00–06:00 for paper reading and creative thinking). Uses OpenClaw sessions_spawn, cron, and steer natively. Use when: (1) start or run ML research agents overnight, (2) check agent status or experiment results, (3) view leaderboard or morning digest, (...
Run and troubleshoot privacy-preserving, local DSPy RLM security audits for large legacy .NET codebases. Use when asked to scan repositories for vulnerabilities, tune RLM/tool limits, fix truncation/stall issues, or produce actionable markdown/json audit outputs without loading entire codebases into model context.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
End-to-end research workflow skill for investment analysts and policy researchers. Three scope modes the user picks at trigger time — light (4-5 page decision memo, ~15 min, 0 charts), medium (12-15 page topic brief, ~1 h, 6-10 charts), heavy (flagship report 30-40 pages / 15k+ words, ~2-3 h, 25-35+ charts, multi-stage workflow, multi-LLM, PDF + Word + WeChat + HTML derivations). Reports default to English; the AI replies in the user's chat language. Battle-tested on real macro/policy/equity ...