research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

research: receipts or it doesn't ship

研究技能:无凭据不交付

Advice built on training data is pattern-matching dressed as knowledge. This skill goes and finds what is true right now, checks it, cites it, and files it where the business can use it again. It is how every other skill earns the right to recommend anything.
  the question
       |
  [ tier ]      quick: minutes, 2-3 sources   standard: multi-angle
       |        deep (opt-in): fan-out + independent fact-check
       |
  [ sweep ]     best engines available, multiple phrasings
       |
  [ verify ]    corroborate across INDEPENDENT sources
       |
  [ file ]      full dossier -> wiki/research/    chat gets the gist + link
Before any step, read
${CLAUDE_SKILL_DIR}/../../CONVENTIONS.md
. This resolves from the installed skill directory to the plugin's shared contract, independent of the founder's working folder. Its receipts, filing, and dedupe rules govern this workflow.
基于训练数据给出的建议只是披着知识外衣的模式匹配。本技能会去查找当前的真实情况,进行验证、引用,并将其归档到企业可再次使用的地方。这是其他所有技能获得推荐权限的前提。
  the question
       |
  [ tier ]      quick: minutes, 2-3 sources   standard: multi-angle
       |        deep (opt-in): fan-out + independent fact-check
       |
  [ sweep ]     best engines available, multiple phrasings
       |
  [ verify ]    corroborate across INDEPENDENT sources
       |
  [ file ]      full dossier -> wiki/research/    chat gets the gist + link
在执行任何步骤之前,请阅读
${CLAUDE_SKILL_DIR}/../../CONVENTIONS.md
。该文件从已安装的技能目录解析至插件的共享协议,与创始人的工作文件夹无关。其凭据、归档及去重规则将指导此工作流程。

Step 0: Preflight

步骤0:预检

Run the shared contract's Universal preflight. A Fresh, Partial, or Wrong-folder result routes to
/co-founder:co-founder-setup
(re-sync for Partial) and stops without researching or filing. On Ready, read the charter's path map and the relevant vault context.
Done when: the founder system is Ready and the dossier destination is known.
执行共享协议的通用预检。若结果为Fresh(未初始化)、Partial(部分完成)或Wrong-folder(路径错误),则跳转至
/co-founder:co-founder-setup
(Partial状态需重新同步),且停止研究或归档操作。若状态为Ready(就绪),则读取章程的路径映射及相关存储库上下文。
完成标志:创始人系统处于Ready状态,且 dossier 的目标位置已明确。

Step 1: Sharpen the question

步骤1:明确问题

Restate what is actually being decided, in one line, and confirm it. "Research newsletters" is not a question; "what open rate should a 2k-subscriber list expect, so we can judge ours" is. A question doing double duty gets split.
Done when: one decision-shaped question is agreed.
Apply the shared parameter gate to any business-specific premise needed to shape or interpret the research. Search the vault, then ask the founder or label the premise as an unverified working hypothesis. Search-tier mechanics are operational; the business inputs are not yours to fill.
Ask before you assert: never present a quantity, duration, sample size, date, or causal motive in prose before asking the founder for it or citing a receipt for it.
用一句话重述实际需要决策的内容,并确认。“研究新闻通讯”不是一个有效问题;“拥有2000名订阅者的邮件列表应该达到怎样的打开率,以便我们评估自身表现”才是。包含双重需求的问题需要拆分。
完成标志:确定一个符合决策场景的问题。
对任何用于构建或解读研究内容的业务特定前提,应用共享参数校验。先搜索存储库,若找不到则询问创始人,或将该前提标记为未经验证的工作假设。搜索层级机制是可操作的,但业务输入不由你补充。
先询问再断言: 在向创始人询问或引用凭据之前,切勿在文本中提及任何数量、时长、样本量、日期或因果动机。

Step 2: Pick the tier

步骤2:选择研究层级

  • Quick: a fact to check, minutes of work, 2-3 sources. Default for small stakes.
  • Standard: a decision input, multiple angles, 5-8 sources.
  • Deep: bet-the-business calls only, and the founder opts in (it costs real time and tokens): full fan-out plus the independent fact-check pass in step 4.
Uncertain resolves upward. State the tier and, for deep, get the yes first.
Done when: the tier is stated.
  • 快速(Quick): 核实单一事实,耗时数分钟,引用2-3个来源。适用于低风险场景,为默认选项。
  • 标准(Standard): 为决策提供输入,涵盖多个角度,引用5-8个来源。
  • 深度(Deep): 仅适用于关乎企业存亡的决策,且需创始人主动选择(会消耗大量时间和token):全面展开搜索,并在步骤4中加入独立事实校验环节。
若不确定则选择更高层级。明确告知所选层级,若选择深度层级,需先获得创始人的同意。
完成标志:确定研究层级。

Step 3: Sweep

步骤3:全面搜索

Use the best engines this environment has, in this order of preference: dedicated search and scrape tools if available (for example, Firecrawl or similar), social-pulse tools (recent posts and community threads), then the harness's native web search and page fetching. The engines vary by machine; the process never does.
Sweep rules:
  • Multiple phrasings per question: the practitioner's wording, the vendor's wording, the skeptic's wording. One phrasing finds one bubble.
  • Prefer primary sources over roundups: the study over the listicle, the pricing page over the review, the practitioner's own numbers over the guru's summary.
  • Capture every candidate claim WITH its source as you go. An uncited claim does not exist.
  • Record the exact query, engine, search date, and result count inspected for every negative finding. A finite search supports "none found in this search," never "none exists."
Done when: each angle of the question has candidate claims with named sources.
使用当前环境中最优的工具,优先级如下:若有专用搜索和抓取工具(例如Firecrawl或类似工具)则优先使用,其次是社交趋势工具(近期帖子和社区讨论),最后是系统自带的网页搜索和页面抓取工具。工具会因设备而异,但流程始终保持一致。
搜索规则:
  • 针对同一问题使用多种表述方式:从业者的措辞、供应商的措辞、质疑者的措辞。单一表述只会找到单一信息圈的内容。
  • 优先选择一手资料而非汇总内容:优先研究报告而非清单式文章,优先官方定价页面而非评测内容,优先从业者的真实数据而非专家的总结。
  • 在搜索过程中记录每个候选结论及其来源。未引用来源的结论视为无效。
  • 对每个未找到结果的搜索,记录确切的查询词、使用的工具、搜索日期及检查的结果数量。有限范围的搜索只能得出“本次搜索未找到相关内容”,绝不能得出“不存在相关内容”的结论。
完成标志:问题的每个角度都有带明确来源的候选结论。

Step 4: Verify

步骤4:验证

STOP. Read
references/verify-checklist.md
before grading any claim: it holds the three traps that make false claims look corroborated, and skipping it is how slop gets certified.
Grade each claim: verified (independent sources agree), stated (one source claims it; carried as a quote, never as truth), contested (sources disagree; both sides carried). Deep tier adds the adversarial pass: each load-bearing claim gets a fresh check whose only job is to break it, using the checklist.
Research findings may be external facts without pretending to know what this business should do. A benchmark applied to this business, a "should" answer, or any other consequential recommendation uses the shared receipts contract: one internal receipt and one verified external source. One floor missing: deliver the factual findings, then write the recommendation in the canonical
PARKED: internal receipt missing
or
PARKED: external receipt missing
shape and name recall or research as the next action. Evidence gaps never move to "Needs your call".
Done when: every claim in the synthesis carries a grade and a source.
Run the shared durable claim admission gate before filing. Reopen every cited page and confirm the passage supports the written claim. Preserve the short supporting quote beside the citation. A source that disappeared or does not contain the evidence is removed; the claim is downgraded to
stated
with its honest source or omitted. Negative findings carry the saved search scope rather than upgrading verified search absence into a universal fact.
Use the shared verified-absence record for every zero-result finding. It may establish the bounded gap and support a PARKED recommendation; it never supplies the external leg for a SURVIVES/DIES call or proves that the missing fact does not exist.
暂停操作。在对任何结论进行评级之前,请阅读
references/verify-checklist.md
:其中列出了三个会让虚假结论看似可信的陷阱,跳过此步骤会导致错误结论被认可。
对每个结论进行评级:已验证(verified)(独立来源达成一致)、已陈述(stated)(仅一个来源提出该结论;仅作为引用呈现,不作为事实)、有争议(contested)(来源存在分歧;需同时呈现双方观点)。 深度层级需增加对抗性校验环节:对每个核心结论进行全新校验,唯一目标是推翻该结论,需遵循检查清单。
研究结果仅为外部事实,无需假装知道企业应采取何种行动。将基准应用于企业、给出“应该”类答案或任何其他重要建议时,需遵循共享凭据协议:需一份内部凭据和一份已验证的外部来源。若缺少其中一项:先交付事实性研究结果,然后以标准格式
PARKED: internal receipt missing
PARKED: external receipt missing
撰写建议,并将召回或研究列为下一步行动。证据缺口绝不能归为“需您决策”类别。
完成标志:综合内容中的每个结论都带有评级和来源。
在归档之前,执行共享的持久结论准入校验。重新打开每个引用的页面,确认内容支持所撰写的结论。在引用旁保留简短的支持性引文。若来源已消失或不包含相关证据,则移除该来源;将结论降级为
stated
并如实标注来源,或直接省略该结论。未找到结果的记录需保留搜索范围,绝不能将“在有限搜索中未找到”升级为“普遍不存在”的事实。
对每个无结果的发现,使用共享的已验证缺失记录。它可以确定明确的信息缺口并支持PARKED类建议,但绝不能为SURVIVES/DIES类决策提供外部依据,也不能证明缺失的事实不存在。

Step 5: File and deliver

步骤5:归档与交付

Write the full dossier to
wiki/research/<slug>.md
with the universal wiki frontmatter, the base five plus sources (
type: research
,
title
,
status
from the overall confidence,
created
,
updated
,
sources:
list), then the question, the synthesis, every claim with its grade and citation,
Parked recommendations
for missing receipt legs, and a "Needs your call" section only for judgment forks the evidence cannot settle. Include a Search record with the exact queries, engines, dates, and inspected-result counts. Update
index.md
, link
hub/research.md
, and append
## [date] research | <question>
to
log.md
.
In chat: the answer in 3-6 lines, the strongest receipt, the link to the dossier. Never paste the dossier into chat; next month's question starts from the file, not from a re-run.
将完整的dossier写入
wiki/research/<slug>.md
,包含通用wiki前置信息、基础五项内容加来源(
type: research
title
status
(基于整体置信度)、
created
updated
sources:
列表),然后依次写入问题、综合内容、每个带评级和引用的结论、因缺少凭据而暂停的建议(
Parked recommendations
),以及仅用于证据无法解决的判断分歧的“需您决策”部分。包含搜索记录,其中需有确切的查询词、工具、日期及检查的结果数量。更新
index.md
,链接
hub/research.md
,并在
log.md
中追加
## [date] research | <question>
在聊天中:用3-6行文字给出答案,附上最有力的凭据链接,以及dossier的链接。切勿将dossier粘贴到聊天中;后续的问题需从归档文件开始,而非重新运行研究。

Mandatory filing gate

强制归档校验

  1. Run
    scripts/graph-audit
    on every touched durable file, including the complete dossier.
  2. Fix every violation and rerun it. The dossier and research event remain incomplete until it exits zero.
Done when: the dossier is filed, indexed, logged, and the founder has the gist with its link.
  1. 对所有涉及的持久文件(包括完整的dossier)运行
    scripts/graph-audit
  2. 修复所有违规问题并重新运行。只有当校验结果为0时,dossier和研究事件才算完成。
完成标志:dossier已归档、建立索引、记录日志,且创始人已收到核心内容及链接。