agentleFS
PaulDanielYoungPaulDanielYoung/internal-audit-skills/skills/writing/design-adequacy-procedures/SKILL.md

design-adequacy-procedures

Skill2 starsChanged 42 days agoMITView on GitHub

Write or review procedures for assessing whether a control, if performed as intended, would adequately address the relevant risk. Use when evaluating the design adequacy of a control, including implementation and walkthrough steps.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write procedures for assessing whether a control, if performed as intended, would adequately address the relevant risk or support the …

    line 6
  2. Distinctive:

    Keep the questions separate: implementation evidence establishes what has been put into use.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Write procedures for assessing whether a control, if performed as intended, would adequately address the relevant risk or support the control objective. Return planned actions and evaluation criteria; performing the assessment and reaching a design conclusion belong to the user executing the work.

Writing the procedures

Use numbered steps with one coherent assessment objective per step. Identify what to examine, what to do, and the criterion for evaluating the design. Build the criterion into the step's wording, such as a required timing, threshold, or policy requirement the design must meet. Keep connected actions together when they answer the same question; separate questions that need independent answers. State common context once for the procedure set.

Connect the control mechanism to the relevant process and risk. Specify the comparison or analysis needed to assess that connection. A control description supplies the design to examine; applicable requirements and the risk supply the basis for evaluating it.

Base organization-specific details and evaluation criteria on supplied or retained sources. Preserve their attribution, and distinguish intended design from reported or observed practice. Identify the sources used when drafting from scratch. Mark material unknowns as descriptive bracketed gaps and complete the supported steps around them.

Design coverage

Address the following where relevant to the control's purpose:

  • Risk coverage: how the mechanism prevents, detects, corrects, or supports recovery from the relevant event, including material ways the risk could arise outside the control, or the control could be bypassed or overridden.
  • Performer: the authority, competence, access, and independence or segregation needed for the person or system to perform the control.
  • Scope and timing: whether the activity covers the relevant population, systems, and process paths, and operates at a frequency or trigger and within a time frame that can address the risk.
  • Information and precision: whether the inputs, comparison, decision rule, thresholds, and level of detail are sufficient to identify or respond to the condition the control is intended to address.
  • Exception handling: how identified exceptions are investigated, resolved, or escalated, with supported responsibilities and timing.
  • Dependencies: the information, systems, other controls, or compensating activities necessary for the mechanism to work. Evaluate the control together with those dependencies.

Frame each relevant matter as an assessment action with a supported criterion; a checklist of descriptive attributes alone does not establish design adequacy. Identify evidence that would demonstrate how the mechanism is intended to work, including any required records or outputs, and whether the design produces records sufficient to evidence its performance.

Implementation evidence

When establishing implementation is part of the request, add distinct steps to determine whether the control exists and has been put into use. A walkthrough may trace a supported instance through the relevant people, systems, handoffs, and exception paths, combining inquiry with examination of available evidence. Identify departures between the intended design and actual practice for assessment.

Keep the questions separate: implementation evidence establishes what has been put into use; design evaluation considers whether that mechanism can address the risk. Evidence from a selected instance supports only the scope actually examined unless a broader basis is established.

No identified control

Where the control itself has not been identified, specify the evidence needed to determine whether a relevant control exists. Distinguish missing information from evidence of a missing necessary control.

Review and return

Check that every design coverage matter is either addressed by a step or set aside as not relevant to this control, and that each step names its evidence and a supported criterion. The wording is complete when an experienced auditor with no prior connection to the engagement could perform each step without inventing a missing criterion. Flag contradictions in the supplied control description or assessment basis without silently resolving them in the wording.

Return the procedures with material gaps and evidence limitations. When reviewing existing wording, explain substantive weaknesses and propose revisions only where needed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.