ask-context
Skill2 starsChanged 40 days agoMITView on GitHub
Answer the auditor's question from the audit methodology and the organization's policies, citing the sections relied on. Use when the auditor asks what the methodology or a policy, procedure, or standard the organization has approved says or requires.
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- exploratory-data-analysisSkill
- create-engagementSkill
- document-request-listSkill
- setup-internal-audit-skillsSkill
- shared-understandingSkill
- planning-memoSkill
- preliminary-surveySkill
- risk-and-control-matrixSkill
- risk-assessmentSkill
- control-statementsSkill
- design-adequacy-proceduresSkill
- operating-effectiveness-proceduresSkill
- process-statementsSkill
- risk-statementsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Very specific: line 19
Search the methodology for every section that bears on the question.
- Distinctive: line 33
When the methodology and a policy both bear on the same part, give each its own block so the auditor sees which source says what.
≈ “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.
Files
Ask Context
Answer the auditor's question from the sources in context/, as a reply in the conversation.
Sources
| Source | Location | Governs | Citation |
| Methodology | context/METHODOLOGY.md | How internal audit does its work | Methodology, {section heading} |
| Policy | Each document in context/policies/ | What the organization holds itself to | {policy title}, {section heading}, effective {effective_date} |
Find every section that bears on the question
Search the methodology for every section that bears on the question. Read the front matter of every document in context/policies/, select each policy whose title or description bears on the question, and read each selected policy in full.
Include sections that apply indirectly, such as definitions, exceptions, approvals, documentation standards, and review cycles. The search is done when each part of the question is matched to a section of a source or confirmed as not addressed by both.
A blank or absent methodology, or an empty context/policies/, contributes nothing; the parts it would have answered are not addressed.
Label each part of the answer
Each part of the answer carries one of three labels:
- Stated: a source says it. Cite it as its row in the Sources table shows and keep its force: a "must" stays a requirement, a "should" stays guidance. Quote prescribed values word for word, such as thresholds, sample sizes, frequencies, required approvals, and retention periods.
- Inferred: it reasonably follows from applying a stated section to the auditor's situation. Cite the section reasoned from and mark the inference as yours.
- Not addressed: neither source covers this part of the question. Say so plainly; that completes the answer for that part. When useful, supplement it with general practice from authoritative external sources, clearly identified as separate from the organization's own sources.
When the methodology and a policy both bear on the same part, give each its own block so the auditor sees which source says what.
Shape the answer
Format the answer as shown below, with one block per part and only the labels the answer uses:
💬 **Answer**
{direct answer to the auditor's question}
---
📖 **Stated** - **{title}**
{what the source says}
📍 {citation}
---
🧩 **Inferred** - **{title}**
{what follows for the auditor's situation}
📍 Reasoned from {citation}
---
⚠️ **Not addressed** - **{title}**
Neither the methodology nor the policies address {part of the question}.
💡 **General practice**: {general practice that helps; otherwise omit this line}
---
➡️ **Recommendation**
{what the auditor should do next}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
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.

