SKILLEMALL.ai
GitHub ↗ RU Sign in

CC soc2-compliance-expert

SOC 2 Type I and Type II compliance management against the Trust Services Criteria. Use for SOC 2 readiness assessments, TSC gap analysis, audit evidence collection, infrastructure control validation, and CPA firm audit preparation.

borghei/Claude-Skills Agent Skills author: borghei 8 files · 3 scripts body ≈ 5 544 tokens Open the sourcegithub.com↗ analyzed 7 h ago

SOC 2 Type I and Type II compliance management against the Trust Services Criteria.

As a process C 56/100 · Has gaps — References files that are not bundled: ../infrastructure-compliance-auditor/, ../nist-csf-specialist/, ../information-security-manager-iso27001/

AnalyzerAWSGoogle CloudAzureInfrastructuretype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
81/100
safety, quality, tests
Safety 60%
87
Quality 40%
73
Run on models
none yet
Process rating
C
56/100
Has gaps
References files that are not bundled: ../infrastructure-compliance-auditor/, ../nist-csf-specialist/, ../information-security-manager-iso27001/
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 13

✓ No critical or high findings

Medium and low: 13
  • low Risky intent intent-offensive-security REFERENCE.md:70
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **Separate Evaluations:** Internal audit (annual minimum), penetration testing (annual minimum, quarterly recommended), third-party assessments, control self-assessments, tabletop exercises.
  • low Risky intent intent-offensive-security REFERENCE.md:163
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **Backup Requirements:** Daily minimum for production, point-in-time recovery for databases, encrypted at rest/transit, monthly restoration testing, 30-day retention minimum (90 recommended), air-gapp
  • low Risky intent intent-offensive-security references/audit-preparation-playbook.md:462
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - [ ] Penetration testing (external, may be quarterly)
  • low Risky intent intent-offensive-security references/audit-preparation-playbook.md:503
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Penetration test** | $10K-$30K | $10K-$30K | Annual, scope-dependent |
  • low Risky intent intent-offensive-security references/audit-preparation-playbook.md:516
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Penetration test** | $10K-$30K | Annual requirement |
  • low Risky intent intent-offensive-security references/infrastructure-security-controls.md:546
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Burp Suite** | Commercial | Manual penetration testing |
  • low Risky intent intent-offensive-security references/trust-services-criteria-guide.md:379
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Commission external penetration testing annually (quarterly for critical systems)
  • low Risky intent intent-offensive-security references/trust-services-criteria-guide.md:388
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Penetration test reports (with remediation status)
  • low Risky intent intent-offensive-security references/trust-services-criteria-guide.md:396
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    - "When was the last penetration test performed and what were the results?"
    quoted
  • low Risky intent intent-offensive-security references/trust-services-criteria-guide.md:401
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Penetration testing not performed in current period
  • low Risky intent intent-offensive-security references/trust-services-criteria-guide.md:678
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Annual penetration testing (quarterly for critical systems)
  • low Risky intent intent-offensive-security SKILL.md:110
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | CC4 | Penetration test reports, vulnerability scans | Third-party/scanner | Annual/Monthly |
  • low Risky intent intent-offensive-security SKILL.md:332
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Penetration testing execution (use infrastructure-compliance-auditor or engage a third-party pentest firm)

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5544 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ../infrastructure-compliance-auditor/
  • warning missing-ref reference to a missing file: ../nist-csf-specialist/
  • warning missing-ref reference to a missing file: ../information-security-manager-iso27001/
  • warning missing-ref reference to a missing file: ../pci-dss-specialist/
  • warning missing-ref reference to a missing file: ../gdpr-dsgvo-expert/
  • warning missing-ref reference to a missing file: ../nis2-directive-specialist/

Process rating: all ten parameters 56/100

Will not run. References files that are not bundled: ../infrastructure-compliance-auditor/, ../nist-csf-specialist/, ../information-security-manager-iso27001/
  • 0Tools and files. 6 referenced file(s) missing: ../infrastructure-compliance-auditor/, ../nist-csf-specialist/, ../information-security-manager-iso27001/
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 5 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 70Execution cost. Instruction body is 5544 tokens
  • 85Steps. 51 steps, 2 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • low 15 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +2Single-language instructions
  • +3Description length 232: enough signal without eating the budget
  • +4Structure: 39 headings
  • +3Step-by-step instructions: 51 items
  • +3Output format is stated explicitly
  • +4Has examples (5 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +3All 3 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.