agentleFS
PaulDanielYoungPaulDanielYoung/internal-audit-skills/skills/planning/preliminary-survey/SKILL.md

preliminary-survey

Skill2 starsChanged 42 days agoMITView on GitHub

Develop or refresh an engagement's preliminary survey and its process list. Use when starting engagement planning or building an understanding of the activity under review.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create planning/preliminary-survey.md using the structure in SURVEY-FORMAT.md.

    line 21
  2. Distinctive:

    Every section of the format has sourced content, a stated absence or non-applicability, or a named information gap.

    line 51
  3. Distinctive:

    No open gap prevents understanding the objectives, processes, scale, or material dependencies of that portion.

    line 53
  4. Distinctive:

    Use an earlier engagement's survey of the same activity as a reference and leave it unchanged.

    line 59

≈ “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

Preliminary Survey

Build a sourced understanding of the activity under review: what it aims to achieve, how it is organized, how its processes are intended to work, and what has changed. The survey owns the engagement's process list and Process IDs; later workpapers inherit them.

File Structure

/
└── engagements/
    └── <year>/
        └── <name>/
            └── planning/
                └── preliminary-survey.md

Create planning/preliminary-survey.md using the structure in SURVEY-FORMAT.md. If the file already exists, update it in place.

1. Establish the starting point

Establish why the engagement was commissioned, what has changed since the plan was approved, the initial expectations, and the known boundaries. Prior workpapers can inform the structure and content without establishing current facts.

2. Gather and describe the activity

Inspect available material before identifying additional information needs. Useful sources include org charts, policies, procedures, process maps, system documentation, management risk assessments and risk registers, prior audit reports, other assurance providers' reports, incident and hotline summaries, and meeting notes.

Explain the activity's objectives and how they support the organization's objectives, its locations and scale, process boundaries, responsibilities, dependencies, and operating environment. Capture management's performance measures and established risk tolerance. Describe governance, management's own risk management, and known control arrangements at a level that supports risk assessment. Record the frameworks and requirements evidenced by the sources, with their known editions.

Label each fact's basis: documented, reported, or observed. Preserve differences between bases with their sources; a procedure document shows documented design, not what happens in practice. When a material uncertainty needs a focused discussion, observation, or process walkthrough, state what it must resolve. Walkthroughs that assess control design belong to the RCM.

Record leads for risk assessment as the facts emerge: significant changes, dependencies, incidents, fraud indicators, management concerns, or unresolved prior findings. Fraud indicators include pressures or incentives, opportunities such as manual overrides, weak segregation, or high-value payments, and past fraud or hotline reports. Link each lead to its source and to Process IDs when known.

Continue until every section of the format has sourced content, a stated absence or non-applicability, or a named information gap.

3. Establish the process list

Draft and review each Process Title and Process Description through process-statements, keeping its source references and basis labels.

Preserve Process IDs already established in this engagement, including provisional IDs in downstream workpapers, and resolve conflicting identities before allocating new ones. Allocate new IDs as P-01, P-02, and so on.

4. Report readiness for risk assessment

A portion of the survey is ready for risk assessment when:

  • The activity's objectives are sourced and distinguished from the audit objective statement.
  • The process list covers the activity as far as current sources show, with boundaries and handoffs clear enough to identify risks.
  • Every section of the format has sourced content, a stated absence or non-applicability, or a named information gap.
  • Each lead is linked to its supporting facts, or the survey states that none were identified from the material reviewed. Fraud indicators get the same explicit statement.
  • No open gap prevents understanding the objectives, processes, scale, or material dependencies of that portion.

Report which portions are ready, and which gaps hold back the rest and why. Minor gaps can stay open. Readiness is the basis for risk assessment only; control design and effectiveness are assessed later.

Refreshing an existing survey

Use an earlier engagement's survey of the same activity as a reference and leave it unchanged. Label carried content without current support as "prior engagement; not reconfirmed" and account for it in readiness. Reconcile Process IDs with those already established for the current engagement.

When processes, objectives, or other material facts change, search the engagement's workpapers for affected references. Record the change in Readiness and handoff and flag the affected risk assessment, planning memo, RCM, or later workpapers for review by their owning skills. Edit only the survey; downstream decisions stand until their owners reconsider them.

Done

Reply with a brief account of the activity and significant leads, readiness, remaining gaps, and any downstream workpapers flagged for review.

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.