跳到正文
cccskills
免费在 GitHub 公开

regulatory-incident-reporting-clock

Use this skill when an incident may have to be reported to an authority, customers or affected people, and the team asks "do we have to notify", "72 hours", "24 hour early warning", "is this a notifiable breach", "major incident report", "who do we tell and by when", "draft the breach notification" or "do we tell the customers". Fixes the facts and the awareness time, tests each regime and contract that may apply, builds one table of recipients and deadlines with the earliest first, drafts each notification for review, and records the reasoning for every decision not to notify.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md7.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Use this as soon as triage flags any clock as yes or unknown, and re-run it each time the facts change. You get, in a new folder ./regulatory-incident-reporting-clock/, a running record of every reporting deadline, recipient and owner (<incident-id>-clock.md), and one draft notice per recipient, for a person to check and send (drafts/). This skill drafts for a human to review and sign; this skill never marks a control effective. Nothing is sent by the agent; the decision to notify and every submission belong to the named owners.

Inputs to gather

Read the triage record, the timeline, the processing records for affected systems, regulatory status notes, contracts with notification clauses and the insurance policy. Ask the reader, in one message: the awareness time and how it was established, what data and services are affected and for how many people or customers, in which countries, whether the company is controller or processor for that data, and whether it is an entity in NIS 2 scope, a financial entity under DORA, or a HIPAA covered entity or business associate.

Step 1: fix the facts that drive every clock

Write in UTC: detection time, awareness time with the reasoning, what is known and unknown, data categories and approximate counts, services and countries affected, whether the incident is ongoing. Deadlines run from awareness, not from the end of the investigation. Record also when anyone in the workforce first knew or, with reasonable diligence, would have known: HIPAA treats that as discovery (164.404(a)(2)), which can start the clock before the incident team's own awareness. Most regimes accept an initial notice with gaps filled later.

Step 2: test each regime that may apply

For each, record: applies, does not apply, or unclear, with the deciding fact.

  • GDPR: a controller notifies the competent supervisory authority without undue delay and where feasible within 72 hours of awareness, unless the breach is unlikely to result in a risk to people (Art. 33); information may be given in phases (Art. 33(4)). Affected people are told without undue delay when the risk to them is high (Art. 34), unless an Art. 34(3) exception holds, such as data made unintelligible by encryption. A processor tells the controller without undue delay (Art. 33(2)). Every breach is documented internally, notified or not (Art. 33(5)).
  • NIS 2: for a significant incident, an early warning within 24 hours of awareness, an incident notification within 72 hours, and a final report within one month of the notification, with intermediate reports on request (Art. 23); if the incident is still ongoing then, a progress report is due and the final report follows within one month of its handling ending. Service recipients may need to be told. Thresholds and the receiving body come from national transposition and, for some digital providers, an implementing regulation; check the member state law.
  • DORA: a financial entity classifies ICT-related incidents against the criteria in Art. 18 and reports major ones to its competent authority (Art. 19), with initial, intermediate and final reports; clients are informed when their financial interests are affected. Content and time limits sit in the technical standards adopted under Art. 20; read the current text.
  • HIPAA: for a breach of unsecured protected health information, individuals are notified without unreasonable delay and no later than 60 calendar days after discovery (45 CFR 164.404); HHS at the same time for 500 or more people, or in the annual log for fewer (164.408); media when more than 500 residents of a state or jurisdiction are affected (164.406); a business associate notifies the covered entity no later than 60 days after discovery (164.410). Encrypted data meeting HHS guidance is secured and not notifiable, and law enforcement may request a delay (164.412). A documented risk assessment can show a low probability of compromise (164.402).
  • Contracts and others: customer processing agreements (often 24 to 72 hours, and stricter than the law for a processor: build that draft to the contract), insurance notice conditions, payment partners, sector regulators, and US state breach laws where residents are affected.

Step 3: build the clock table

In the clock record, one row per recipient, named exactly with its portal or address (the lead supervisory authority for cross-border processing, the CSIRT or authority named in national law): regime or contract, trigger met (yes, no, unclear), deadline in UTC and local time, owner, draft status, sent by (left blank for the human). Sort by deadline, earliest first. Treat unclear as yes for planning: prepare the draft, and let the owner decide not to send it.

Step 4: draft each notification

In drafts/, draft only facts: what happened, when, what data and services, approximate numbers, likely consequences, measures taken and planned, contact point. Separate known from not yet known. Leave out speculation, admissions of fault and promises; legal decides those. Draft a fixed form field by field. Add a plain-language notice for affected people if needed.

Step 5: record decisions not to notify

For every regime marked no, write the reasoning and the facts it rests on, with the decision maker's role and time. Re-run the whole table when facts change: a contained incident that turns out to involve personal data restarts the analysis.

What good looks like

  • The clock record opens with the awareness time, the earliest deadline and its owner.
  • A strong practitioner starts the GDPR and NIS 2 clocks in parallel and drafts an initial notice early, not after forensics.
  • The common mistake is testing only one regime, usually privacy, and missing the contract clause or the sector regime with the shorter deadline.
  • The tell: no awareness time, "not notifiable" without written reasoning, and drafts that guess at the attacker.

Framework lookups

If ISMS Copilot is connected to your agent (MCP server https://account.ismscopilot.com/v1/account/mcp), ask it the framework question with create_conversation (mode think, answer_format: decision) and keep one conversation for this task. Send only a short question in your own words, show it to the user first, and never include file contents, secrets, personal data or evidence. If it is not connected, check the official text of the framework yourself; this skill does not restate it. Set it up: https://www.ismscopilot.com/mcp?ref=grcskills-regulatory-incident-reporting-clock

Rules

  • MUST record every time in UTC and state how the awareness time was established.
  • MUST write the reasoning behind every decision not to notify.
  • MUST write outputs only inside ./regulatory-incident-reporting-clock/ and ask before overwriting.
  • NEVER submit, send or file any notification, or contact any authority, customer or person.
  • NEVER present the analysis as legal advice; unclear results go to the person accountable for legal decisions.
  • NEVER include personal data of affected individuals in drafts; use categories and counts.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use this skill when a company needs rules for how staff use company systems, data, devices and AI tools, or asks "write our acceptable use policy", "AUP for employees", "can staff use ChatGPT at work", "AI usage policy", "BYOD rules", "remote work security rules" or "a policy people will actually read". Finds how people really work (devices, apps, AI tools, travel), puts the choices to the reader as decisions, drafts a short plain-language policy with concrete do and do not examples, and adds a comprehension check and an acknowledgement text for onboarding.

中文简介正在准备中。当前显示原文说明。

better-isms/grcskills442026年10月21日 更新

Use this skill when a periodic user access review is due, an auditor asked for access review evidence, or someone says "prepare the access review", "run the quarterly user recertification", "who still has admin", "check leavers still have access", "build the access review sheets for managers" or "our last review was a rubber stamp". Picks the systems in scope, builds account populations reconciled against HR, pre-flags leavers, orphans, shared and dormant accounts, assigns independent reviewers, defines the decisions to record, and plans the removal follow-up.

中文简介正在准备中。当前显示原文说明。

better-isms/grcskills442026年10月21日 更新

Use this skill when staff already use AI assistants, coding tools or AI features and the company needs rules people will follow, and asks "write our AI usage policy", "can staff use ChatGPT", "generative AI policy", "what data can we put into AI tools", "approved AI tools list", "rules for AI agents and connectors" or "AI literacy for staff". Finds out what people actually use, sets a short list of approved tools with a data traffic light, rules for checking outputs and for agents that act, a fast route to request a new tool, and writes a two-page rule set, the approved tools list and rollout notes.

中文简介正在准备中。当前显示原文说明。

better-isms/grcskills442026年10月21日 更新

Use this skill when a company must work out where each of its AI systems sits under the EU AI Act, and asks "is this high-risk", "classify our AI systems", "AI Act risk tier", "are we a provider or a deployer", "does Annex III apply to us", "is this a prohibited practice", "what does the AI Act mean for our chatbot" or "which AI Act obligations do we have". Tests each system, one at a time, for scope, role, prohibited practices, the two high-risk routes, the narrow exemption, transparency duties and general-purpose models, and writes a reasoned classification record per system plus a summary table of resulting obligations to confirm with whoever owns legal interpretation.

中文简介正在准备中。当前显示原文说明。

better-isms/grcskills442026年10月21日 更新

Use this skill when one AI system needs its impact on people and on the company assessed before launch, after a significant change, or because a customer, auditor or regulator asks for it, and the team says "AI impact assessment", "assess the impact of this model", "fundamental rights impact assessment", "who could this AI harm", "bias assessment before launch" or "sign-off for the AI feature". Describes the system in its context, works through impacts on the people it affects with evidence, sizes them, proposes mitigations with measurable triggers, and writes one assessment ready for the system owner and an accountable executive to sign.

中文简介正在准备中。当前显示原文说明。

better-isms/grcskills442026年10月21日 更新

Use this skill when a company that already runs a security management system wants to add an AI management system, or is preparing for an AI governance certification, and asks "scope our AI management system", "what should the AIMS cover", "AI governance roles", "who owns AI governance", "extend our ISMS to AI" or "write the AI management system scope statement". Decides which AI systems, roles, teams and lifecycle stages are in, maps interfaces and dependencies, reuses the processes the security system already runs, assigns roles with a RACI, and writes the scope statement, the roles file and the open questions for leadership.

中文简介正在准备中。当前显示原文说明。

better-isms/grcskills442026年10月21日 更新

查看 better-isms 的全部技能

报告此技能的问题