audit-category-pointer
Skill9 starsChanged 5 months agoMITView on GitHub
Pointer to a library of 10 specialized audit/compliance skills — ISACA, COSO, AICPA SOC, Audit Workpapers, NIST 800-53/RMF, NIST CSF 2.0, HIPAA Security Rule, PCI DSS, SOX §302 disclosure controls, and FedRAMP cloud authorization. Use when working on IT audit, internal controls, SOC reporting, audit documentation, federal control baselines, cybersecurity maturity, HIPAA security, PCI DSS payment-security, SOX §302 disclosure-controls certification, or FedRAMP cloud-authorization tasks.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- aicpa-soc-reportingSkill
- audit-workpapersSkill
- coso-internal-controlsSkill
- fedramp-authorizationSkill
- hipaa-security-ruleSkill
- isaca-audit-methodologySkill
- nist-800-53-rmfSkill
- nist-csf-2Skill
- pci-dss-assessmentSkill
- sox-302-disclosure-controlsSkill
- TEMPLATESkill
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 33
Read skills/<skill-name>/SKILL.md (the router).
- Distinctive: line 36
Follow those instructions to complete the request.
≈ “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
Audit Capability Library
This is a pointer skill. The 10 specialized skills are stored on disk to keep your startup context minimal. Counts and framework facts live in each skill (verified against live sources at its G4.5 gate) — this pointer deliberately repeats none of them.
Available skills in this category
- isaca-audit-methodology — ISACA CISA audit methodology, COBIT 2019, ITAF (5th Edition), ITGC/ITAC testing, risk-based audit planning, maturity assessment.
- coso-internal-controls — COSO 2013 ICIF and 2017 ERM, SOX 404 readiness, PCAOB AS 2201 top-down approach, deficiency classification (MW/SD/D), walkthroughs, RCM.
- aicpa-soc-reporting — SOC 1/2/3 engagements, Trust Services Criteria (TSP §100), CUECs/CSOCs, bridge letters, management assertions, opinion determination.
- audit-workpapers — workpaper standards (PCAOB AS 1215, AU-C 230, ISA 230), evidence hierarchy, sampling (MUS/attribute/variables), finding formats, engagement completion.
- nist-800-53-rmf — NIST SP 800-53 Rev 5 control baselines, SP 800-37 RMF steps, FIPS 199 categorization, FedRAMP context, SOC 2/ISO/PCI/HIPAA crosswalks, ATO artifacts.
- nist-csf-2 — NIST CSF 2.0 organizational profiles, tiers, gap analysis, board-level maturity reporting, crosswalks to 800-53/ISO/SOC 2/CMMC.
- hipaa-security-rule — 45 CFR Part 164 Subpart C safeguards, required-vs-addressable dispositions, risk analysis, BAA requirements, OCR readiness, enforcement and (proposed) NPRM context.
- pci-dss-assessment — PCI DSS v4.0.1 scoping and segmentation, SAQ selection, ROC/AOC validation, defined-vs-customized approach, compensating controls, QSA workflow.
- sox-302-disclosure-controls — SOX §302 disclosure controls & procedures (DC&P) certification, DC&P-vs-ICFR boundary, 302-vs-404, the 6-element officer certification, disclosure committee and sub-certification cascade.
- fedramp-authorization — FedRAMP cloud-authorization program (Rev 5): the FedRAMP Authorization Act of 2022 and OMB M-24-15 governance (FedRAMP Board, not the retired JAB), FIPS 199 categorization and the Low/Moderate/High/LI-SaaS baselines (tailored from NIST SP 800-53 Rev 5), the SSP/SAP/SAR/POA&M package, 3PAO assessment, monthly ConMon, and the FedRAMP 20x direction.
How to load a skill
- Identify the skill name above matching your task.
- Read
skills/<skill-name>/SKILL.md(the router); load the chunks its §11 routing table selects for your intent. In an installed environment, read the skill'sSKILL.mdfrom wherever this library was installed. - Follow those instructions to complete the request.
Do not guess best practices — always read from the skill file first.
Quick reference: Which skill to use?
| Task | Skill |
| IT audit planning, COBIT assessment, ITGC/ITAC testing | isaca-audit-methodology |
| SOX 404, internal control evaluation, deficiency classification | coso-internal-controls |
| SOC 1/2/3 scoping, TSC criteria, service org reporting | aicpa-soc-reporting |
| Workpapers, sampling, evidence documentation, findings | audit-workpapers |
| FIPS-199 categorization, 800-53 baselines, ATO/POA&M, FedRAMP | nist-800-53-rmf |
| Cyber maturity profiles, board reporting, framework crosswalks | nist-csf-2 |
| HIPAA safeguards, addressable decisions, BAAs, OCR readiness | hipaa-security-rule |
| PCI DSS scoping, SAQ selection, ROC/AOC, compensating controls | pci-dss-assessment |
| SOX §302 DC&P certification, disclosure committee, sub-cert cascade | sox-302-disclosure-controls |
| FedRAMP authorization, baseline selection, SSP/SAR/POA&M, 3PAO assessment, ConMon, ATO path | fedramp-authorization |
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.