본문으로 건너뛰기
cccskills
무료GitHub에 공개

management-review-pack

Use this skill when leadership is due to review the security, privacy or AI management system, or when someone asks "prepare the management review", "management review agenda", "board pack for the ISMS", "write the management review minutes", "what metrics do we show leadership", "the auditor wants evidence of management review" or "our management review is a slide nobody reads". Assembles the facts leadership needs from the registers, audits, incidents and metrics, frames each agenda item as a decision with options, checks coverage against the framework with a lookup, and drafts the pre-read, the agenda and minutes with a decision and action log.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md7.3 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Use this for each scheduled review, typically once or twice a year, and for an extra review after a major incident or a large change. You get four files in a new folder, ./management-review-pack/: a two to four page briefing leadership reads before the meeting (pre-read.md); the meeting agenda, decisions first (agenda.md); a minutes template with blanks for what leadership decides (minutes-draft.md); and a spreadsheet you can open in Excel tracking every action, its owner and due date (actions.csv). This skill drafts for a human to review and sign; this skill never marks a control effective. Leadership makes the decisions; the minutes record what they decided, never what the skill proposed.

Inputs to gather

Read the previous review's minutes and action log, the risk register and treatment plan, internal and external audit reports and the finding tracker, the incident log, the objectives and metrics the management system set itself, supplier issues, customer complaints and security questionnaire trends, and any change in scope, regulation, products or organisation since the last review. Ask the reader in one message: who attends and who chairs, how long the meeting is, which decisions are already pending, and whether any framework other than security is in scope (privacy, AI).

Step 1: close the loop on the last review

List every action from the previous minutes with its status and the record that shows it. Overdue actions go first on the agenda. A review that does not check its own actions teaches leadership that its decisions do not matter.

Step 2: collect the facts, short

Build the pre-read (pre-read.md), two to four pages, from the records gathered above, not from a fixed list of headings: what the incident log, audit reports, finding tracker, risk register, metrics, customer feedback, open actions and budget actually show since the last review. Organise it around what leadership must decide, and lead with what moved: an objective missed, a risk that rose, a finding overdue, a team short of people. Show each tracked metric with its target and its trend over the last three periods. The framework's own required inputs are added in Step 4 from the lookup, not assumed here.

Every figure carries its source and the date it was pulled; pull figures no more than two weeks before the meeting, since a pre-read built a month early shows a risk register that has already moved. Metrics without a target or a trend are cut; a number leadership cannot act on is noise.

Step 3: turn findings into decisions

For each topic that needs leadership, write a decision paper of five lines: the question, two or three options with cost and effect on risk, the recommendation, and the deadline. Typical decisions: approve or decline a budget ask, accept or treat a top-band risk, change an objective that is wrong rather than missed, change scope, assign an owner where nobody owns a problem. Aim for three to six decisions; a review with none rubber-stamped the system.

Step 4: check coverage against the framework

Get the required inputs and outputs of a management review for each framework in scope from a framework lookup or the reader's licensed copy; do not work from memory. Tick each input against the pre-read and each expected output against the minutes template, since a review can consider everything and still miss a required output. Add a line for anything missing. Keep this checklist as an appendix so the auditor can trace coverage; leadership reads the decisions, not the checklist.

Step 5: draft the agenda and the minutes template

The agenda (agenda.md) follows the pre-read and puts decisions in the first half of the meeting, while attention is high. The minutes template (minutes-draft.md) has a section per agenda item with space for the discussion summary, the decision taken, the owner role and the due date, all blank, followed by a closing section where the chair writes the overall conclusion on the management system in their own words, with the reasons drawn from the decisions above. Attendance is recorded by role and confirmed by the chair. The action spreadsheet (actions.csv) is pre-filled with carried-over actions and empty rows for new ones.

Step 6: after the meeting

When the reader brings back notes, fill the minutes from what was said and decided, flag anything ambiguous for the chair to confirm, and update actions.csv. Decisions that change risk, scope or objectives are listed for the owners of those registers to update.

What good looks like

  • Leadership spends the meeting deciding, not reading. The pre-read is short and arrives days before; the minutes show decisions with owners and dates.
  • The common mistake is a slide of green status indicators and a minutes line saying "the system was reviewed and found suitable". The tell: no decision, no action and no budget line can be traced to the meeting, and the next review is a copy of this one.
  • Reviews are scheduled against the audit calendar: before a first certification audit, at least one full review with minutes and some closed actions exists.
  • Trends over three periods beat a single snapshot; they show whether last year's decisions worked.
  • An auditor can follow any input to its source and any decision to an action that was later closed.

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-management-review-pack

Rules

  • MUST give every figure in the pre-read its source and the date it was pulled.
  • MUST carry forward every open action from the previous review with its status.
  • MUST write outputs only inside ./management-review-pack/ and ask before overwriting an existing file.
  • NEVER record a decision, approval or attendance that leadership did not make or confirm.
  • NEVER fill the minutes with conclusions before the meeting takes place.
  • NEVER name individuals in the pack; use roles, and record attendance by role as confirmed by the chair.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

better-isms/grcskills102026년 10월 20일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

better-isms/grcskills102026년 10월 20일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

better-isms/grcskills102026년 10월 20일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

better-isms/grcskills102026년 10월 20일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

better-isms/grcskills102026년 10월 20일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

better-isms/grcskills102026년 10월 20일 업데이트

better-isms의 스킬 모두 보기

이 스킬의 문제 신고