Skip to content
cccskills
FreePublished on GitHub

soa-first-draft

Use this skill when a company has a risk assessment and treatment plan and now needs its first statement of applicability, and asks "build our SoA", "draft the statement of applicability", "which controls apply to us", "SoA from the risk treatment plan", "justify inclusions and exclusions" or "our SoA says implemented everywhere". Drafts one row per control of the reader's framework with the inclusion decision, the risk or obligation behind it, an implementation status taken from records, an evidence pointer and an owner role, and writes a CSV statement plus notes of open decisions.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md7.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Use this after the risk assessment and treatment plan exist, not before: an applicability statement written first is a guess dressed as a decision. You get two files in a new folder, ./soa-first-draft/: a draft statement of applicability as a spreadsheet you can open in Excel, one row per control saying whether it applies, why, how far along it is and where the proof sits (soa.csv), and a short note with the status scale, the mismatches found and the questions for owners (soa-notes.md). This skill drafts for a human to review and sign; this skill never marks a control effective. Control selection is a management decision; the agent proposes it.

Inputs to gather

Read: the scope statement, the risk register and treatment plan, the register of legal, regulatory and contractual obligations if one exists, customer contracts and questionnaire answers that promise specific practices, policies and procedures, and any evidence index or compliance platform export. Then load the list of control identifiers from the reader's licensed copy of the standard or their compliance platform. If neither is available, stop and ask; never reconstruct the control list or its titles from memory. Ask the reader who approves the statement and when the next audit is.

Step 1: collect the reasons to include

For every control identifier, collect every reason it is needed, each with an id, as the first columns of the draft statement (soa.csv):

  • Risk: a treated risk in the register whose treatment names this control or an action it covers (R-012).
  • Obligation: a law, regulation or contract clause that calls for the practice (OBL-04, or the contract reference).
  • Commitment: a customer questionnaire answer, trust page claim or certification promise that says the company does it.
  • Baseline: a practice the company runs as a matter of policy even without a specific risk; say why.

A control with at least one reason is included. Record all reasons, not only the first; the auditor reads the reasons to judge whether the risk assessment drove the selection.

Step 2: test exclusions hard

A control is a candidate for exclusion only when no in-scope activity, asset or process exists for it to act on. Write the fact ("no premises of its own; all staff work remotely; the hosting provider operates the data centres") and where an auditor sees that fact. Three reasons are never enough on their own: "not implemented yet" (that is a status, not applicability), "low risk" without a risk id and score, and "the provider handles it" (outsourcing usually moves the control into supplier management, it rarely removes it). For each exclusion, also check the risk register and the commitments from step 1; a contradiction there reverses the exclusion. For a full exclusion review, use the exclusion justification review skill.

Step 3: set implementation status from records

Use one scale and define it in the notes file (soa-notes.md):

  • Implemented: operating, and a record from the current period exists. Give the path.
  • Implemented, evidence pending: operating, record not yet located.
  • In progress: a treatment action is open; give its id and due date.
  • Planned: decided, not started.

Take status from the treatment plan and the records, never from the policy alone. Where status is unclear, choose the lower one and add a question for the owner.

Step 4: fill the remaining columns

For each row: control id (bare identifier), included (yes, partial or no; for partial, state which part of the scope it covers and the fact for each half, in the same shape the exclusion justification review uses), reasons (ids), justification in one sentence in the company's terms, status, evidence path and date of that record, owner role, linked treatment action. Flag evidence older than the review cadence as stale. Keep justifications specific to the company: "Customer data in three production databases; R-007 and R-015 treated by encryption at rest and key rotation." A sentence that would fit any company adds nothing.

Step 5: reconcile and hand over

Before handing over, check that every identifier from the licensed list has exactly one row; list absent identifiers first in the notes, since a control missing from the statement is a defect good wording elsewhere cannot cure. Then check both directions: every risk the treatment plan says is reduced by a control points to an included row, and every included row has at least one reason. Record mismatches in the notes file with the decision needed, the versions of the register and treatment plan the draft was built from, and an approval block (version, approver role, date) with the rule that a change to scope, register or treatment plan triggers a re-reconciliation and re-approval. Ask before overwriting existing files. Run a framework lookup for what the standard expects the statement to show, instead of assuming the column set.

What good looks like

  • Every included row cites at least one risk, obligation or commitment id; reasons vary row by row.
  • The common mistake is a statement where every control is included and implemented. The tell is a young programme showing no In progress rows, or justifications copied unchanged across dozens of rows.
  • Exclusions are few, factual and checkable, and none contradicts the risk register or what sales has promised customers.
  • Status matches the records: a reviewer opening five random evidence paths finds dated records from the current period.
  • Owners are roles that run the practice, and each open action carries a date.

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-soa-first-draft

Rules

  • MUST cite at least one risk, obligation, commitment or baseline reason for every included control.
  • MUST take control identifiers from the reader's licensed source or platform, never from memory.
  • MUST write outputs only inside ./soa-first-draft/ and ask before overwriting.
  • NEVER exclude a control because it is not implemented yet.
  • NEVER write official control titles or requirement text into the statement; use bare identifiers and the company's own words.
  • NEVER record the statement as approved; the approver named by the reader signs it.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

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.

The English summary is being prepared. Showing the original description.

better-isms/grcskills10Updated Oct 20, 2026

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.

The English summary is being prepared. Showing the original description.

better-isms/grcskills10Updated Oct 20, 2026

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.

The English summary is being prepared. Showing the original description.

better-isms/grcskills10Updated Oct 20, 2026

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.

The English summary is being prepared. Showing the original description.

better-isms/grcskills10Updated Oct 20, 2026

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.

The English summary is being prepared. Showing the original description.

better-isms/grcskills10Updated Oct 20, 2026

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.

The English summary is being prepared. Showing the original description.

better-isms/grcskills10Updated Oct 20, 2026

See all skills by better-isms

Report a problem with this skill