reg-feed-watcher

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/reg-feed-watcher

Load

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

→ watchlist, materiality threshold, feed config.

Use the workflow below.
Pull each feed. Filter by materiality.
Output: what's new, categorized by materiality tier.

加载

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

→ 监控列表、重要性阈值、信息源配置。

遵循下方工作流程。
获取每个信息源的内容，并根据重要性进行筛选。
输出：新增内容，按重要性层级分类。

Purpose

目的

Pull the feeds. Filter by materiality. Output what's left. The filter is the value — unfiltered feeds are noise.

获取信息源内容，根据重要性筛选，输出留存的内容。筛选是核心价值——未筛选的信息源内容都是噪音。

Load context

加载上下文

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

→ watchlist, materiality threshold, feed configuration, digest output path (if set).

references/source-catalog.md

(in this skill's directory) → curated catalog of RSS/JSON/HTML sources across US federal, US state, EU/UK, international, and secondary/aggregator categories. Use when configuring new sources or when the user's watchlist has coverage gaps (see Step 0).

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

→ 监控列表、重要性阈值、信息源配置、摘要输出路径（若已设置）。

references/source-catalog.md

（此技能目录下）→ 精心整理的RSS/JSON/HTML信息源目录，涵盖美国联邦、美国各州、欧盟/英国、国际以及二级/聚合类信息源。配置新信息源或用户监控列表存在覆盖缺口时使用（见步骤0）。

Workflow

工作流程

Step 0: Coverage check (before pulling)

步骤0：覆盖检查（获取内容前）

Before running the pull, compare the watchlist + feed configuration in CLAUDE.md against

references/source-catalog.md

Which categories (US federal / US state / EU-UK / international) does the user care about per their watchlist?
Which of those categories have zero or very few sources configured?

If there's an obvious gap — e.g., user watches "EU regulators" in the watchlist but has only

edpb.europa.eu

configured in feeds, missing ICO, CNIL, DPC Ireland — surface it once at the top of the digest:

Coverage gap noticed: Your watchlist includes [category], but only [N] feeds are configured. The source catalog lists [X] options in this category (e.g., [top 2-3 names]). Want me to suggest additions? Run
/regulatory-legal:cold-start-interview --redo
to update, or edit
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md
directly.

Don't nag the same gap repeatedly — if the user has explicitly said "skip state AGs for now," respect that. Note state in CLAUDE.md so it sticks.

在获取内容前，将CLAUDE.md中的监控列表+信息源配置与

references/source-catalog.md

进行对比：

根据用户的监控列表，他们关注哪些类别（美国联邦/美国各州/欧盟-英国/国际）？
这些类别中有哪些配置的信息源为零或极少？

若存在明显缺口——例如，用户监控列表包含“欧盟监管机构”，但信息源配置中仅设置了

edpb.europa.eu

，缺少ICO、CNIL、爱尔兰DPC——则在摘要顶部一次性指出：

注意到覆盖缺口： 你的监控列表包含[类别]，但仅配置了[N]个信息源。信息源目录中该类别有[X]个可选选项（例如，[前2-3个名称]）。需要我建议新增信息源吗？运行
/regulatory-legal:cold-start-interview --redo
进行更新，或直接编辑
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md
。

不要反复提醒同一缺口——如果用户明确表示“暂时跳过州检察长相关内容”，请尊重该选择。在CLAUDE.md中记录此状态以便后续遵循。

Step 1: Pull

步骤1：获取内容

Pull from all configured feed tiers. Every installation has Tier 1. Tiers 2 and 3 are additive — use them if configured, skip if not.

Tier 1 — Free feeds (always active)

For each regulator in the watchlist:

Federal Register API (
```
https://www.federalregister.gov/api/v1/documents
```
) — query by agency slug, date range (since last check), document type. Returns structured data: document type, title, abstract, effective date, comment deadline (for NPRMs), and citation. Covers all US federal agencies.
Direct regulator RSS — fetch and parse any RSS URLs in ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md feed configuration (SEC, FTC, CFPB, state agencies, EU DPAs, etc.).

Agency slug reference for common watchlist regulators:

Regulator	API slug
FTC	federal-trade-commission
SEC	securities-and-exchange-commission
CFPB	consumer-financial-protection-bureau
CPPA (CA)	RSS only — cppa.ca.gov/feed
DOL	labor-department
HHS	health-and-human-services-department
FCC	federal-communications-commission

For any regulator not in this list: check federalregister.gov/agencies for the correct slug, or fall back to direct RSS.

Tier 2 — Paid feeds (if configured)

Paid regulatory feed MCP: Query for updates since last check date, filtered to watchlist regulators.
CourtListener MCP: Same.

De-duplicate across tiers — the same document may appear in multiple sources. Prefer the richest source for the enriched output.

No silent supplement. If the feed pull returns few or no results for a regulator in the watchlist, report what was found and stop. Do NOT fill the gap from web search or model knowledge without asking. Say: "The feed check returned [N] items from [regulators hit]. Coverage appears thin for [regulator / topic]. Options: (1) broaden the date window, (2) try a different feed or MCP, (3) search the web — results will be tagged

[web search — verify]

and should be checked against the issuing authority's website before relying, or (4) stop here. Which would you like?" A lawyer decides whether to accept lower-confidence sources; Claude does not decide for them.

Source attribution. Tag every citation and regulatory item with where it came from:

[Federal Register]

[<regulator> RSS]

[CourtListener]

, or the specific MCP tool name for items retrieved via connector;

[web search — verify]

for items from web search;

[model knowledge — verify]

for items surfaced from the model's training data;

[user provided]

for manually-pasted items. Items tagged

verify

carry higher fabrication risk than tool-retrieved items and should be checked first. Never strip or collapse the tags — they are the user's fastest signal about which citations to verify.

Secondary sources. Some catalog entries (IAPP, FPF, Hogan Lovells, Covington, Lexology, JD Supra, Artificial Lawyer, LawSites, and similar commentators/aggregators) report on primary regulatory action but are not the primary source. Tag any item pulled from these feeds with

[secondary source]

in addition to the feed-name tag — e.g.,

[IAPP Daily Dashboard] [secondary source]

. In the digest, when a secondary-source item describes a regulator action, add a note: "→ Trace to primary: [link to regulator site if known, otherwise 'find on <regulator>.gov before relying']." Do not classify a secondary-source item as "Always material" on its own strength — bump it down a tier until the primary source is located.

Tier 3 — Manual entry

If the user has pasted regulatory text or a summary rather than invoking from a scheduled feed check: treat the pasted content as a single item, skip to Step 2 for classification, and record source as "manual entry." No feed pull required. This path works regardless of subscription status.

Record the check timestamp after pulling. Next scheduled run pulls from here forward.

从所有已配置的信息源层级获取内容。每个安装都有层级1。层级2和3为附加层级——若已配置则使用，未配置则跳过。

层级1 — 免费信息源（始终激活）

针对监控列表中的每个监管机构：

Federal Register API (
```
https://www.federalregister.gov/api/v1/documents
```
) — 按机构缩写、日期范围（自上次检查以来）、文档类型进行查询。返回结构化数据：文档类型、标题、摘要、生效日期、意见征集截止日期（针对NPRM）以及引用信息。覆盖所有美国联邦机构。
直接监管机构RSS — 获取并解析
```
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md
```
信息源配置中的所有RSS URL（SEC、FTC、CFPB、州机构、欧盟DPA等）。

常见监控列表监管机构的机构缩写参考：

Regulator	API slug
FTC	federal-trade-commission
SEC	securities-and-exchange-commission
CFPB	consumer-financial-protection-bureau
CPPA (CA)	仅支持RSS — cppa.ca.gov/feed
DOL	labor-department
HHS	health-and-human-services-department
FCC	federal-communications-commission

对于未在此列表中的监管机构：访问federalregister.gov/agencies查询正确缩写，或退而求其次使用直接RSS源。

层级2 — 付费信息源（若已配置）

付费监管信息源MCP： 查询自上次检查日期以来的更新，筛选至监控列表中的监管机构。
CourtListener MCP： 同上。

跨层级去重——同一文档可能出现在多个源中。优先选择信息最丰富的源用于增强输出。

禁止静默补充。 如果针对监控列表中的某监管机构，信息源获取返回的结果极少或为空，请汇报已发现的内容并停止。未经询问，不得通过网页搜索或模型知识填补缺口。应告知用户：“信息源检查从[涉及的监管机构]返回了[N]项内容。[监管机构/主题]的覆盖范围似乎有限。可选方案：(1) 扩大日期范围，(2) 尝试其他信息源或MCP，(3) 进行网页搜索——结果将标记为

[web search — verify]

，在依赖前应核对发布机构的官网，或(4) 在此停止。你希望选择哪种方案？” 应由律师决定是否接受可信度较低的源；Claude不得自行决定。

来源归因。 为每个引用和监管条目标记来源：

[Federal Register]

、

[<regulator> RSS]

、

[CourtListener]

，或通过连接器检索到的条目标记具体MCP工具名称；网页搜索获取的条目标记

[web search — verify]

；模型训练数据提取的条目标记

[model knowledge — verify]

；手动粘贴的条目标记

[user provided]

。标记

verify

的条目比工具检索的条目存在更高的伪造风险，应优先核对。不得移除或合并这些标记——它们是用户快速判断哪些引用需要核对的关键信号。

二级来源。 部分目录条目（IAPP、FPF、Hogan Lovells、Covington、Lexology、JD Supra、Artificial Lawyer、LawSites及类似评论者/聚合平台）报道一级监管行动，但并非一级来源。从这些信息源获取的任何条目，除了信息源名称标记外，还需添加

[secondary source]

标记——例如，

[IAPP Daily Dashboard] [secondary source]

。在摘要中，当二级来源条目描述监管机构行动时，添加注释：“→ 追溯至一级来源：[若已知则链接至监管机构官网，否则为‘依赖前请在<regulator>.gov上查找’]”。不得仅凭二级来源条目将其归类为“始终重要”——在找到一级来源前，应将其层级下调。

层级3 — 手动输入

如果用户粘贴了监管文本或摘要，而非通过定时信息源检查调用：将粘贴内容视为单个条目，跳至步骤2进行分类，并记录来源为“manual entry”。无需获取信息源内容。此路径不受订阅状态限制。

获取内容后记录检查时间戳。下次定时运行将从此时间点开始获取内容。

Step 2: Classify

步骤2：分类

Each item gets a materiality tier per

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

Item type	Match against threshold
Final rule	Usually "always material"
Proposed rule / NPRM	Usually "review-worthy" — and always log comment deadline
ANPR (Advance Notice of Proposed Rulemaking)	Review-worthy for strategy, not compliance — no imposed requirements yet, but signals direction and carries a real comment deadline. Log the comment deadline. Route to `/regulatory-legal:policy-diff` only as a pre-positioning analysis, not as a gap-closure diff.
RFI (Request for Information)	Same as ANPR — pre-rule, no compliance obligation, but comment deadline is real and direction-signaling is the value.
Enforcement action	Sector match → material; related-practice match → review-worthy; neither → FYI or skip
Guidance	Review-worthy
Speech / blog / statement	FYI or skip per threshold
Settlement	Depends — novel theory or big number → review-worthy; routine → skip

ANPR / RFI handling — specific. Pre-rule items are distinct from NPRMs in one important way: they don't change the law, but they do carry comment deadlines and they signal the regulator's direction. Treat them as a separate branch:

Do not classify an ANPR / RFI as "always material" — the compliance impact is zero until a rule issues.
Do classify as review-worthy if any of the issue areas in the notice touch the watchlist's always-material categories (e.g., an ANPR on open banking in a fintech watchlist).

Do log the comment deadline to

~/.claude/plugins/config/claude-for-legal/regulatory-legal/comment-tracker.yaml

with

item_type: ANPR

item_type: RFI

so the downstream tracker can distinguish these from compliance gaps.

Do include in the digest entry a line that says explicitly: "Pre-rule. Comment deadline [date]. Route to
```
/regulatory-legal:policy-diff
```
only as a pre-positioning analysis (no compliance gap yet)." This primes the policy-diff skill to use its compressed pre-positioning branch rather than a full gap-closure diff.
Route to the comment-tracker, not the gap-tracker. Comment-decision items are not compliance gaps; they belong in the comment tracker, and
```
gap-surfacer
```
uses the
```
comment-decision
```
```
gap_type
```
(or declines to ingest, if the team routes these separately).

NPRM comment deadline handling:

For every NPRM classified at any tier above "skip":

Extract comment deadline (Federal Register API returns this as structured data)
If comment tracking is enabled in ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md: append to
```
~/.claude/plugins/config/claude-for-legal/regulatory-legal/comment-tracker.yaml
```
with status "undecided" and the default comment decision owner from ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md
Include comment deadline in the output entry

每个条目根据

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

中的规则分配重要性层级：

条目类型	与阈值匹配规则
最终规则	通常为“始终重要”
拟议规则 / NPRM	通常为“值得审阅”——并始终记录意见征集截止日期
ANPR（拟议规则预先通知）	针对战略值得审阅，而非合规——目前无强制要求，但预示方向且存在真实的意见征集截止日期。记录意见征集截止日期。仅作为预定位分析路由至 `/regulatory-legal:policy-diff` ，而非作为缺口填补差异分析。
RFI（信息请求）	与ANPR相同——预规则阶段，无合规义务，但意见征集截止日期真实，方向预示是核心价值。
执法行动	行业匹配→重要；相关业务匹配→值得审阅；均不匹配→仅供参考或跳过
指南	值得审阅
演讲/博客/声明	根据阈值决定仅供参考或跳过
和解协议	视情况而定——新颖理论或大额金额→值得审阅；常规情况→跳过

ANPR / RFI处理细则。 预规则条目与NPRM的一个重要区别是：它们不会改变法律，但确实带有意见征集截止日期并预示监管机构的方向。将其视为单独分支处理：

不得将ANPR / RFI归类为“始终重要”——在规则发布前，合规影响为零。
若通知中的任何议题涉及监控列表中的“始终重要”类别（例如，金融科技监控列表中的开放银行ANPR），则归类为“值得审阅”。
务必将意见征集截止日期记录至
```
~/.claude/plugins/config/claude-for-legal/regulatory-legal/comment-tracker.yaml
```
，并标记
```
item_type: ANPR
```
或
```
item_type: RFI
```
，以便下游追踪工具区分这些条目与合规缺口。
务必在摘要条目中添加一行明确说明：“预规则阶段。意见征集截止日期[日期]。仅作为预定位分析路由至
```
/regulatory-legal:policy-diff
```
（目前无合规缺口）。” 这将引导policy-diff技能使用其压缩的预定位分支，而非完整的缺口填补差异分析。
路由至意见追踪工具，而非缺口追踪工具。 意见决策条目不属于合规缺口；它们属于意见追踪工具的范畴，
```
gap-surfacer
```
会使用
```
comment-decision
```
的
```
gap_type
```
（若团队单独路由这些条目，则可能拒绝接收）。

NPRM意见征集截止日期处理：

对于所有归类为“跳过”以上层级的NPRM：

提取意见征集截止日期（Federal Register API返回结构化数据）

若

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

中启用了意见追踪：将条目追加至

~/.claude/plugins/config/claude-for-legal/regulatory-legal/comment-tracker.yaml

，状态为“undecided”，并使用

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

中的默认意见决策负责人

在输出条目中包含意见征集截止日期

Step 3: Enrich

步骤3：增强内容

For each item above FYI tier:

One-line summary (what changed)
Why it might matter here (the relevance hook — "this is about [practice you do]")
Link to source
Effective date or comment deadline if applicable

Don't summarize FYI items individually — just count them.

对于所有“仅供参考”以上层级的条目：

一行摘要（发生了什么变化）
为何与我方相关（相关性钩子——“这涉及[我方开展的业务]”）
来源链接
生效日期或意见征集截止日期（若适用）

无需单独总结“仅供参考”条目——仅统计数量即可。

Output

输出

The digest goes into the chat by default. Also write it to a shareable file whenever the output contains one or more items above FYI, unless the user's CLAUDE.md explicitly sets

Digest output → chat only

File output behavior:

Look for

Digest output path

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

. If set, write there. Default if unset:

~/regulatory-legal-digests/reg-digest-YYYY-MM-DD.md

Create parent directories if needed.
Write the full digest as Markdown (same content as the chat output, including the work-product header, source tags, and the verify-citations footer).
If a file already exists at the path for today, append a new section with a timestamped subheader rather than overwriting — the same day may see multiple runs (morning digest, ad-hoc check).
After writing, tell the user: "Digest written to
```
<path>
```
. Share as-is, or convert to .docx with Pandoc:
```
pandoc <path> -o <path>.docx
```
."
If the write fails (permission, missing directory the user didn't authorize creating, disk), fall back to chat-only output and say so — don't silently drop the file request.

Format on disk matches the chat format exactly (below). Markdown renders well in GitHub, Notion, Obsidian, Google Docs (via "Import as Markdown" or Pandoc), and most email clients.

markdown

[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]

摘要默认发送至聊天窗口。只要输出包含一个或多个“仅供参考”以上层级的条目，就需同时写入可共享文件，除非用户的CLAUDE.md明确设置为

Digest output → chat only

。

文件输出行为：

在

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

中查找

Digest output path

。若已设置，则写入该路径。未设置时的默认路径：

~/regulatory-legal-digests/reg-digest-YYYY-MM-DD.md

。

若需要则创建父目录。
将完整摘要以Markdown格式写入（与聊天输出内容相同，包括工作产品标题、来源标记和核对引用的页脚）。
若当日该路径已存在文件，则追加一个带时间戳的子标题的新章节，而非覆盖——同一天可能会多次运行（早间摘要、临时检查）。
写入完成后，告知用户：“摘要已写入
```
<path>
```
。可直接分享，或使用Pandoc转换为.docx格式：
```
pandoc <path> -o <path>.docx
```
。”
若写入失败（权限问题、用户未授权创建的缺失目录、磁盘问题），则退回到仅聊天输出并告知用户——不得静默丢弃文件写入请求。

磁盘上的格式与聊天格式完全一致（如下）。Markdown在GitHub、Notion、Obsidian、Google Docs（通过“导入为Markdown”或Pandoc）以及大多数邮件客户端中均可良好渲染。

markdown

[WORK-PRODUCT HEADER — 按插件配置## Outputs — 因角色而异；参见`## Who's using this`]

Regulatory Feed Check — [date]

监管信息源检查 — [日期]

Period: [last check] to [now] Feeds checked: [list active tiers — e.g., "Federal Register API, FTC RSS, TR"] Items found: [N] total

时间段： [上次检查时间] 至 [当前时间] 已检查信息源： [列出激活的层级 — 例如，"Federal Register API, FTC RSS, TR"] 发现条目： [N] 条

Bottom line

核心结论

[N gaps need action by [date] — top 3: X, Y, Z]

[N] 项缺口需在[日期]前处理 — 前3项：X、Y、Z

🔴 Always material

🔴 始终重要

[Regulator] — [Title] [One-line summary]. [Relevance hook]. Effective [date]. [Link] → Recommend: run policy-diff against [likely affected policy]

[repeat for each]

[监管机构] — [标题] [一行摘要]。[相关性钩子]。生效日期[日期]。 [链接] → 建议：针对[可能受影响的政策]运行policy-diff

[重复每个条目]

🟡 Review-worthy

🟡 值得审阅

[Regulator] — [Title] [One-line]. [Relevance]. [Deadline if any]. [Link]

[NPRMs: include "💬 Comment deadline: [date] — decision pending" if comment tracking enabled]

[repeat]

[监管机构] — [标题] [一行摘要]。[相关性]。[截止日期（若有）]。 [链接]

[NPRM：若启用意见追踪，需包含“💬 意见征集截止日期：[日期] — 待决策”]

[重复每个条目]

📝 FYI

📝 仅供参考

[N] items — [expandable list of titles + links, no summaries]

Last check updated to: [timestamp] Comment tracker: [N] NPRMs with open comment decisions — run /regulatory-legal:comments to review

Verify citations before relying on them. Regulatory citations here were AI-generated and have not been checked against a primary source. Before acting on any rule, guidance, or enforcement action above, confirm it against Westlaw, your firm's research platform, or the issuing authority's website — check accuracy, effective date, and current status. AI-generated regulatory citations are sometimes fabricated, misquoted, or stale. Source tags on each item (e.g.,

[Federal Register]

[web search — verify]

) show where the citation came from;

verify

tags carry higher fabrication risk and should be checked first.

undefined

[N] 项条目 — [可展开的标题+链接列表，无摘要]

上次检查时间已更新至： [时间戳] 意见追踪工具： [N] 项NPRM有待决策意见 — 运行/regulatory-legal:comments进行审阅

依赖前请核对引用。 此处的监管引用由AI生成，尚未与一级来源核对。在根据上述任何规则、指南或执法行动采取行动前，请在Westlaw、贵司研究平台或发布机构的官网上确认其准确性、生效日期和当前状态。AI生成的监管引用有时会存在伪造、误引或过时的情况。每个条目的来源标记（例如，

[Federal Register]

、

[web search — verify]

）显示了引用的来源；

verify

标记的条目存在更高的伪造风险，应优先核对。

undefined

Config-dependent fallbacks

依赖配置的回退方案

This skill reads the watchlist, materiality threshold, and feed configuration from

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

. When a required value is still

[PLACEHOLDER]

or empty, say so in the output — specifically, not generically:

Watchlist empty: stop and say "The watchlist in your configuration is empty. I can't pull feeds without knowing which regulators to watch. Run
```
/regulatory-legal:cold-start-interview --redo
```
or edit
```
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md
```
and add at least one regulator."
Materiality threshold empty: fall back to the default tiers and append: "This output used the default materiality tiers because your configuration doesn't have custom thresholds set. Tune them with
```
/regulatory-legal:cold-start-interview --redo
```
or by editing
```
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md
```
."
Feed configuration empty: run Federal Register API only and append: "This output used only the free Federal Register API because your configuration doesn't list direct RSS or paid feeds. Add feeds with
```
/regulatory-legal:cold-start-interview --redo
```
or by editing
```
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md
```
."

Say nothing about config when the relevant values are populated.

If nothing above FYI: "All quiet. [N] FYI items, nothing needing attention."

此技能从

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

读取监控列表、重要性阈值和信息源配置。当必填值仍为

[PLACEHOLDER]

或为空时，在输出中明确说明——而非泛泛提及：

监控列表为空： 停止操作并告知“你的配置中的监控列表为空。不知道要监控哪些监管机构，我无法获取信息源内容。运行
```
/regulatory-legal:cold-start-interview --redo
```
或编辑
```
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md
```
并添加至少一个监管机构。”
重要性阈值为空： 使用默认层级并追加说明：“由于你的配置未设置自定义重要性阈值，此输出使用了默认层级。运行
```
/regulatory-legal:cold-start-interview --redo
```
或编辑
```
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md
```
进行调整。”
信息源配置为空： 仅运行Federal Register API并追加说明：“由于你的配置未列出直接RSS或付费信息源，此输出仅使用了免费的Federal Register API。运行
```
/regulatory-legal:cold-start-interview --redo
```
或编辑
```
~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md
```
添加信息源。”

当相关值已填充时，无需提及配置。

若没有“仅供参考”以上层级的内容：“一切平静。[N]项仅供参考条目，无需要关注的内容。”

Handoff

交接

To policy-diff: Any "always material" item with a likely policy impact → offer to run the diff.
To gap-surfacer: If a diff finds a gap → tracked.
To comment-tracker: Any NPRM classified above "skip" → comment deadline logged automatically if tracking is enabled.

至policy-diff： 任何“始终重要”且可能产生政策影响的条目→主动提出运行差异分析。
至gap-surfacer： 若差异分析发现缺口→进行追踪。
至comment-tracker： 任何归类为“跳过”以上层级的NPRM→若启用追踪，自动记录意见征集截止日期。

Close with the next-steps decision tree

以下一步决策树收尾

End with the next-steps decision tree per CLAUDE.md

## Outputs

. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.

根据CLAUDE.md中的

## Outputs

，以下一步决策树收尾。根据此技能刚生成的内容自定义选项——五个默认分支（起草X、升级、获取更多事实、观察等待、其他）是起点，而非固定选项。决策树是输出内容；由律师选择。

What this skill does not do

此技能不执行的操作

Read every item in full. It classifies and enriches; deep reading is for the items that survive the filter.
Change the materiality threshold. If the filter is wrong, edit ~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md.
Require TR or CourtListener. Free feeds are the baseline; paid feeds add depth.

完整阅读每个条目。它仅进行分类和增强内容；深度阅读留给通过筛选的条目。

修改重要性阈值。若筛选规则有误，请编辑

~/.claude/plugins/config/claude-for-legal/regulatory-legal/CLAUDE.md

。

强制要求TR或CourtListener。免费信息源是基础；付费信息源增加深度。