Back to Details

research-ops-skills

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Research Operations — Domain Orchestrator

研究运营——领域编排器

The Research Operations surface is how the enterprise plans, funds, scopes, and synthesizes research across four workstreams: clinical R&D, R&D finance, market research, and product research. This orchestrator forks its context, routes your inquiry to one of four sub-skills, then returns a digest. Heavy intake (protocol drafts, program ledgers, survey exports, interview transcripts) stays in the forked context.
This is the enterprise counterpart to the academic 
research/
domain. If your question is about finding literature, grants, or patents, use 
research/
. If it is about planning, funding, scoping, or synthesizing research as an operational discipline, you are in the right place.
研究运营模块是企业跨四大工作流（临床研发、研发财务、市场研究、产品研究）进行研究规划、资助、范围界定及成果整合的核心工具。该编排器会拆分上下文，将你的请求路由至四个子技能中的一个，然后返回摘要。大量输入内容（方案草案、项目台账、调研导出数据、访谈记录）将保留在拆分后的上下文中。
这是学术
research/
领域的企业端对应工具。如果你的问题是关于查找文献、资助或专利，请使用
research/
；如果你的问题是关于将研究作为运营学科进行规划、资助、范围界定或成果整合，那么你使用的工具是正确的。

When to invoke

调用场景

SymptomSub-skill
"We're designing a Phase 2 trial — what's the endpoint and sample size?"
clinical-research
"What's our R&D program burn, and is this cost CapEx or OpEx?"
research-finance
"What's the TAM for this product, and how do we survey the segment?"
market-research
"How many users do we interview, and how do we synthesize the findings?"
product-research
需求场景子技能
"我们正在设计II期试验——终点指标和样本量应该怎么定？"
clinical-research
"我们的研发项目资金消耗率是多少？这项成本属于资本支出还是运营支出？"
research-finance
"这款产品的TAM是多少？我们该如何调研目标细分市场？"
market-research
"我们需要访谈多少用户？如何整合研究发现？"
product-research

Routing logic (deterministic)

路由逻辑（确定性）

Same two-signal threshold pattern as 
commercial-skills
. Single-signal → clarifying question. Mixed signals → highest-confidence first, chain second in a follow-up turn. Never silently chain.
与
commercial-skills
采用相同的双信号阈值模式。单信号→提出澄清问题；混合信号→优先选择置信度最高的领域，后续回合再处理第二个领域。绝不静默串联多个子技能。

Signal table

信号对照表

Signal classKeywordsSub-skill
CLINICALclinical trial, study design, protocol, endpoint, sample size, power, phase 1/2/3, biostatistics, eligibility, feasibility, estimand
clinical-research
RD_FINANCER&D budget, program budget, burn, runway, F&A, indirect rate, overhead, capitalize vs expense, R&D capex, portfolio ROI, rNPV
research-finance
MARKETTAM, SAM, SOM, market sizing, survey design, sampling, margin of error, segmentation, competitive intelligence, market research
market-research
PRODUCTuser interview, JTBD, usability test, concept test, prototype test, discovery research, research repository, insight synthesis, saturation
product-research
信号类别关键词子技能
临床研究clinical trial、study design、protocol、endpoint、sample size、power、phase 1/2/3、biostatistics、eligibility、feasibility、estimand
clinical-research
研发财务R&D budget、program budget、burn、runway、F&A、indirect rate、overhead、capitalize vs expense、R&D capex、portfolio ROI、rNPV
research-finance
市场研究TAM、SAM、SOM、market sizing、survey design、sampling、margin of error、segmentation、competitive intelligence、market research
market-research
产品研究user interview、JTBD、usability test、concept test、prototype test、discovery research、research repository、insight synthesis、saturation
product-research

Workflow (Matt Pocock grill discipline)

工作流（Matt Pocock grill准则）

Derived from Matt Pocock's 
grill-with-docs
pattern: explore-then-ask, one question per turn with a recommended answer, walk the decision tree depth-first, track dependencies, anchor every challenge in the research canon (
references/
of each sub-skill).
源自Matt Pocock的
grill-with-docs
模式：先探索再提问，每回合一个问题并给出推荐答案，深度遍历决策树，跟踪依赖关系，每个挑战都锚定研究规范（各子技能的
references/
目录）。

Step 1 — Explore before asking

步骤1 — 提问前先探索

Check the user's working directory first:
  • Is there a protocol draft, program ledger, TAM model, or interview guide already in the workspace?
  • Does the inquiry already disambiguate the lane (e.g., "what sample size for a two-arm trial" — that's 
    clinical-research
    , no question needed)?
  • Is there an artifact filename that resolves the lane (
    protocol.json
    → clinical; 
    program-budget.json
    → finance; 
    tam-model.json
    → market; 
    interview-guide.md
    → product)?
If the workspace resolves the lane, route silently.
首先检查用户的工作目录：
  • 工作区中是否已有方案草案、项目台账、TAM模型或访谈指南？
  • 请求是否已明确领域（例如“双臂试验的样本量是多少”——明确属于
    clinical-research
    ，无需提问）？
  • 是否存在能确定领域的工件文件名（
    protocol.json
    →临床；
    program-budget.json
    →财务；
    tam-model.json
    →市场；
    interview-guide.md
    →产品）？
如果工作区能确定领域，则静默路由。

Step 2 — If still ambiguous, ONE forcing question with a recommended answer

步骤2 — 若仍有歧义，提出一个明确问题并给出推荐答案

Matt's rule: never bundle. Always recommend.
Pattern:
Q1/1: [precise question naming the two candidate lanes]
Recommended: [Lane X, because <signal-table rationale>]

(Confirm, or override?)
Matt的规则：绝不捆绑多个问题，始终给出推荐选项。
格式：
Q1/1: [明确指出两个候选领域的精准问题]
推荐选项: [领域X，因为<信号对照表依据>]

（请确认，或选择其他领域？）

Step 3 — Decision-tree walk for multi-lane inquiries

步骤3 — 多领域请求的决策树遍历

If the inquiry legitimately crosses two lanes (e.g., "design this trial AND budget it" = CLINICAL + RD_FINANCE), walk depth-first:
  1. Highest-confidence lane first → run sub-skill in forked context → digest
  2. Ask: "Now run [second lane]? Recommended: yes, because [dependency]."
  3. Confirm before chaining.
Never silently chain.
如果请求确实涉及两个领域（例如“设计试验并制定预算”=临床+研发财务），则按深度优先遍历：
  1. 优先处理置信度最高的领域→在拆分的上下文中运行子技能→生成摘要
  2. 询问：“是否现在运行[第二个领域]？推荐：是，因为[依赖关系]。”
  3. 获得确认后再串联子技能。
绝不静默串联。

Step 4 — Invoke sub-skill in forked context

步骤4 — 在拆分的上下文中调用子技能

Forward original prompt + structured inputs (protocol JSON, program ledger CSV, market model, observation export).
转发原始提示+结构化输入（方案JSON、项目台账CSV、市场模型、观测导出数据）。

Step 5 — Return digest with cited canon challenge

步骤5 — 返回带有规范引用挑战的摘要

≤ 200 words: analyzed, top 3 findings (anchored to a canon citation), top 3 next actions (named human owner where applicable), artifact path, and one grill challenge for the user. Examples:
  • "Your power calc assumes a 0.5 effect size with no published anchor. ICH E9 requires a justified, clinically meaningful difference. Where did 0.5 come from?"
  • "Your TAM is a single top-down number (1% of a $40B market). Bessemer market-sizing discipline requires a bottoms-up cross-check. What's units × price × adoption?"
摘要≤200字：包含分析结果、Top3研究发现（锚定规范引用）、Top3后续行动（注明对应负责人）、工件路径，以及一个针对用户的追问挑战。示例：
  • “你的功效计算假设效应量为0.5，但无已发表依据。ICH E9要求有合理的、具有临床意义的差异说明。0.5这个数值的依据是什么？”
  • “你的TAM是单一自上而下的数值（400亿美元市场的1%）。Bessemer市场测算准则要求进行自下而上的交叉验证。请提供单位×价格×渗透率的数据？”

Forcing-question library (grill-with-docs pattern)

追问问题库（grill-with-docs模式）

Grill the user on lane-defining decisions before invoking the sub-skill. One per turn, recommended answer, canon citation:
  • CLINICAL lane: "Is your primary endpoint a clinical outcome or a surrogate — and if surrogate, is it validated for this indication? Recommended: clinical outcome unless the surrogate is on FDA's validated table. Canon: FDA Surrogate Endpoint Table; BEST glossary."
  • RD_FINANCE lane: "Is this spend in the research phase or the development phase, and can you evidence technical feasibility? Recommended: research = expense; development = capitalize-candidate only with feasibility evidence, routed to a named finance owner. Canon: IAS 38; ASC 730."
  • MARKET lane: "Is your TAM top-down or bottoms-up — and have you computed it both ways to triangulate? Recommended: both; reconcile the delta. Canon: Bessemer / a16z market-sizing; Fermi estimation."
  • PRODUCT lane: "Is this study generative (discover problems) or evaluative (test a solution)? Recommended: name it first; the method follows. Canon: Rohrer's landscape of UX research methods (NN/g)."
Never run a sub-skill until the lane-defining decision is locked.
在调用子技能前，针对领域定义相关决策追问用户。每回合一个问题，给出推荐答案并引用规范：
  • 临床领域：“你的主要终点是临床结局还是替代指标？如果是替代指标，是否针对该适应症经过验证？推荐：除非替代指标在FDA验证列表中，否则优先选择临床结局。规范：FDA替代指标列表；BEST术语表。”
  • 研发财务领域：“这笔支出属于研究阶段还是开发阶段？你能否提供技术可行性证明？推荐：研究阶段=费用化；开发阶段=仅在有可行性证明时可列为资本化候选，需路由至指定财务负责人。规范：IAS 38；ASC 730。”
  • 市场领域：“你的TAM是自上而下还是自下而上测算的？是否通过两种方式计算以进行三角验证？推荐：两种方式都采用，调和差异值。规范：Bessemer / a16z市场测算方法；费米估算。”
  • 产品领域：“这项研究是生成式（发现问题）还是评估式（测试解决方案）？推荐：先明确类型，再选择方法。规范：Rohrer的UX研究方法全景图（NN/g）。”
在领域定义决策确定前，绝不运行子技能。

Onboarding-first (per sub-skill)

优先完成配置（按子技能）

Before invoking a sub-skill for the first time in a workspace, point the user at that skill's onboarding questionnaire so the tools run pre-configured to their context:
bash
python3 skills/<sub-skill>/scripts/onboard.py          # interactive Q&A
python3 skills/<sub-skill>/scripts/onboard.py --show    # questions + current config
Each sub-skill has its own question set (clinical: area/alpha/power/dropout/owners · finance: area/F&A/runway/standard/owner · market: profile/confidence/MoE/method · product: profile/insight-threshold/method/stakes). Answers persist to 
~/.config/research-ops/<sub-skill>.json
(or 
./.research-ops/<sub-skill>.json
with 
--scope project
) and are consumed automatically by every tool in that skill. Customization is mandatory discipline here, not decoration — surface the onboarding step when a user starts a fresh research workstream.
首次在工作区调用子技能前，引导用户完成该技能的配置问卷，以便工具根据用户上下文预配置运行：
bash
python3 skills/<sub-skill>/scripts/onboard.py          # interactive Q&A
python3 skills/<sub-skill>/scripts/onboard.py --show    # questions + current config
每个子技能都有专属的问题集（临床：领域/alpha值/功效/脱落率/负责人 · 财务：领域/间接成本/资金 runway/标准/负责人 · 市场：用户画像/置信度/误差边际/方法 · 产品：用户画像/洞察阈值/方法/风险等级）。答案将保存至
~/.config/research-ops/<sub-skill>.json
（使用
--scope project
参数时保存至
./.research-ops/<sub-skill>.json
），并被该技能下的所有工具自动读取。自定义配置是强制要求，而非可选项——当用户启动新的研究工作流时，需展示配置步骤。

Autoresearch handoff (isolated, opt-in)

自动研究交接（隔离式、可选）

Each sub-skill ships its own 
scripts/ar_evaluator.py
— an isolated bridge to 
engineering/autoresearch-agent
. Invoke autoresearch only when the user explicitly asks to "optimize", "improve", or "run a loop". The handoff is per-skill (no shared coupling): the loop edits the skill's input file and the evaluator scores it (clinical → 
feasibility_composite
higher; finance → 
runway_months
higher; market → 
tam_divergence
lower; product → 
validated_insights
higher). Never auto-start a loop; never let the loop edit the evaluator.
每个子技能都附带
scripts/ar_evaluator.py
——一个与
engineering/autoresearch-agent
连接的隔离式桥梁。仅当用户明确要求“优化”“改进”或“运行循环”时，才调用自动研究功能。交接按技能独立进行（无共享耦合）：循环会编辑技能的输入文件，评估器对其打分（临床→
feasibility_composite
得分更高；财务→
runway_months
数值更高；市场→
tam_divergence
数值更低；产品→
validated_insights
数量更多）。绝不自动启动循环；绝不允许循环编辑评估器。

Assumptions

假设前提

  1. User has research authority OR is preparing analysis for someone who does.
  2. User wants deterministic decision support, not the final answer — a clinician approves the protocol, a controller books the entry, the human picks the market number.
  3. Inputs may be partial — every sub-skill ships a templated sample so the user can see the shape before filling in their own.
  1. 用户拥有研究权限，或正在为拥有权限的人准备分析内容。
  2. 用户需要确定性决策支持，而非最终答案——临床方案需由临床医生批准，账目需由财务主管入账，市场数值需由人工确认。
  3. 输入内容可能不完整——每个子技能都提供模板示例，用户可先查看格式再填写自有内容。

Non-goals

非目标

  • Not an EDC, clinical-trial-management system, accounting system, survey platform, or research repository.
  • Does not give clinical, accounting, or legal advice as fact. Every output is a recommendation + named human owner.
  • Does not store research history across sessions.
  • 并非EDC（电子数据采集系统）、临床试验管理系统、会计系统、调研平台或研究知识库。
  • 不提供临床、会计或法律方面的确定性建议。所有输出均为建议+指定负责人。
  • 不跨会话存储研究历史。

Distinct from

与其他工具的区别

  • research/
    (academic)     — that domain finds literature, grants, and patents. This domain plans, funds, scopes, and synthesizes research.
  • ra-qm-team
     — that's regulatory/QM submission (ISO 13485/14971, MDR, FDA 510(k)/PMA/QSR). clinical-research designs the study; it routes submission out to ra-qm-team.
  • finance/financial-analysis
     — that's corporate close + valuation. research-finance manages R&D program/portfolio spend.
  • research/grants
     — that's funding discovery. research-finance manages money already won.
  • product-team
     — that's persona/journey artifacts, discovery sprints, and live A/B experiments. product-research is the method + repository discipline.
  • marketing-skill
     — that's campaign analytics and demand-gen. market-research is upstream methodology.
  • research/
    （学术领域）    ——该领域用于查找文献、资助和专利；本领域用于规划、资助、范围界定及整合研究。
  • ra-qm-team
    ——该工具用于监管/质量管理申报（ISO 13485/14971、MDR、FDA 510(k)/PMA/QSR）。clinical-research负责设计研究方案，申报工作将路由至ra-qm-team。
  • finance/financial-analysis
    ——该工具用于企业结账+估值；research-finance负责管理研发项目/组合支出。
  • research/grants
    ——该工具用于资金发掘；research-finance负责管理已获取的资金。
  • product-team
    ——该工具用于用户画像/旅程工件、发现冲刺、实时A/B实验；product-research负责方法+知识库规范。
  • marketing-skill
    ——该工具用于营销活动分析和需求生成；market-research负责上游方法论。

Output artifacts

输出工件

Sub-skillArtifact
clinical-research
protocol_synopsis.md
+ 
sample_size.json
research-finance
rd_program_budget.md
+ 
capex_opex_routing.json
market-research
market_sizing.md
+ 
sample_plan.json
product-research
research_plan.md
+ 
insight_synthesis.json
子技能工件
clinical-research
protocol_synopsis.md
+ 
sample_size.json
research-finance
rd_program_budget.md
+ 
capex_opex_routing.json
market-research
market_sizing.md
+ 
sample_plan.json
product-research
research_plan.md
+ 
insight_synthesis.json

Anti-patterns (do not)

反模式（禁止操作）

  • ❌ Present a clinical power/endpoint output as fact — it is an estimate with a named clinical owner
  • ❌ Auto-decide capitalize-vs-expense — route to a named finance owner
  • ❌ Report a market size as a single unsourced number — show method + both-ways triangulation + assumptions
  • ❌ Assert a product insight from a single participant — flag it as an anecdote
  • ❌ Run all 4 sub-skills "to be thorough" — pick one, digest, chain if needed
  • ❌ 将临床功效/终点输出作为事实呈现——这是估算值，需注明临床负责人
  • ❌ 自动决定资本化vs费用化——需路由至指定财务负责人
  • ❌ 报告单一无来源的市场规模数值——需展示方法+双向三角验证+假设前提
  • ❌ 从单个参与者的反馈中断言产品洞察——需标记为轶事
  • ❌ 为“全面起见”运行所有4个子技能——选择一个领域生成摘要，必要时再串联

References

参考资料

  • Clinical canon: ICH E8(R1)/E9/E9(R1), CONSORT, SPIRIT, FDA Multiple Endpoints
  • R&D finance canon: IAS 38, ASC 730, 2 CFR 200, Cooper stage-gate
  • Market canon: Cochran, Dillman, Kotler, Bessemer market-sizing
  • Product canon: Nielsen, Guest et al., Christensen JTBD, ResearchOps/Polaris
  • Path-B build pattern: 
    documentation/implementation/research-ops-expansion-plan.md
  • 临床规范：ICH E8(R1)/E9/E9(R1)、CONSORT、SPIRIT、FDA Multiple Endpoints
  • 研发财务规范：IAS 38、ASC 730、2 CFR 200、Cooper阶段门模型
  • 市场规范：Cochran、Dillman、Kotler、Bessemer市场测算方法
  • 产品规范：Nielsen、Guest et al.、Christensen JTBD、ResearchOps/Polaris
  • Path-B构建模式：
    documentation/implementation/research-ops-expansion-plan.md