SKILLEMALL.ai
GitHub ↗ RU Sign in

BC oath

Auditing regulatory compliance (SOC2/PCI-DSS/HIPAA/ISO 27001): maps requirements, checks controls, designs audit trails, implements Policy as Code. Use when compliance auditing is needed.

simota/agent-skills Agent Skills author: simota 12 files body ≈ 6 034 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Auditing regulatory compliance (SOC2/PCI-DSS/HIPAA/ISO 27001): maps requirements, checks controls, designs audit trails, implements Policy as Code.

As a process C 63/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice

AnalyzerSecuritySoftware developmentLegaltype 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
B
89/100
safety, quality, tests
Safety 60%
94
Quality 40%
81
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
When it triggers w 12
20
Running it twice w 4
30
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.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • low Risky intent intent-offensive-security reference/compliance-reporting.md:136
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    - penetration_test_report: "External/internal pentest results"
    quoted
  • low Dangerous commands cmd-privilege reference/policy-as-code.md:140
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo mv conftest /usr/local/bin/
    security skill
  • low Risky intent intent-offensive-security reference/regulatory-frameworks.md:115
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - Vulnerability scanning every 6 months; penetration testing annually
    detector
  • low Risky intent intent-offensive-security reference/vendor-risk-assessment.md:36
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    | Critical | Processes regulated data (CHD/ePHI/special-category), part of the authentication path, outage would cause customer-visible incident in < 1h, **or hosts a foundation model that powers a us
    detector
  • low Risky intent intent-offensive-security reference/vendor-risk-assessment.md:67
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Security addendum | Critical / High tier | Encryption requirements, incident notification window, pentest frequency, right-to-audit |
  • low Risky intent intent-offensive-security reference/vendor-risk-assessment.md:100
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    →  annual SOC 2 / pentest summary refresh

Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6034 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 63/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 7 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Execution cost. Instruction body is 6034 tokens
  • 100Steps. 79 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 17 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 187: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 79 items
  • +3Output format is stated explicitly
  • +4Has examples (4 code blocks)
  • +4Reference files are cited in the instructions (10 of 10)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.