SKILLEMALL.ai
GitHub ↗ RU Sign in

BB building-cloud-siem-with-sentinel

Deploy Microsoft Sentinel as a cloud-native SIEM/SOAR by configuring multi-cloud data connectors (AWS, Azure, GCP), writing KQL detection and hunting queries, and building automated Logic Apps response playbooks. Use when establishing a centralized SOC for multi-cloud environments, migrating from a legacy SIEM, or performing petabyte-scale threat hunting; not for AWS-only setups where Security Hub/GuardDuty suffice or for endpoint EDR needs.

mukul975/Anthropic-Cybersecurity-Skills Agent Skills author: mukul975 Apache-2.0 4 files · 1 script body ≈ 3 053 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Deploy Microsoft Sentinel as a cloud-native SIEM/SOAR by configuring multi-cloud data connectors (AWS, Azure, GCP), writing KQL detection and hunting queries…

As a process B 72/100 · Nearly there — weak spots: failures and branches, running it twice

GeneratorAWSAzureGoogle CloudPeople and hiringtype 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
90/100
safety, quality, tests
Safety 60%
96
Quality 40%
82
Run on models
none yet
Process rating
B
72/100
Nearly there
Failures and branches w 10
0
Running it twice w 4
30
When it triggers w 12
50
the three weakest of ten parameters · all ten

How to improve

    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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Risky intent intent-offensive-security SKILL.md:140
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      // Detect mass S3 object deletion (potential ransomware)
      detector
    • low Risky intent intent-offensive-security SKILL.md:201
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      // Threat hunting query: detect lateral movement across AWS accounts
      detector
    • low Risky intent intent-offensive-security SKILL.md:277
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      3. Build a Fusion detection rule that links Azure AD risk events with subsequent AWS privilege escalation activity
      detector
    • low Risky intent intent-offensive-security SKILL.md:279
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      5. Create a workbook showing the timeline from initial compromise through lateral movement to AWS

    Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "domain"
    • note frontmatter-key unknown frontmatter key "subdomain"
    • note frontmatter-key unknown frontmatter key "nist_ai_rmf"
    • note frontmatter-key unknown frontmatter key "atlas_techniques"
    • note frontmatter-key unknown frontmatter key "nist_csf"
    • note frontmatter-key unknown frontmatter key "mitre_attack"
    • note edit-residue the text marks something as outdated (lines 7): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 72/100

    • 0Failures and branches. Linear process with no failure handling
    • 30Running it twice. 8 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 20 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3053 tokens
    • 100Progress reporting. Reports progress

    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
    • -41 reference files, but SKILL.md never points to them: the model will not open them
    • -31 of 1 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 445: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 20 items
    • +3Output format is stated explicitly
    • +4Has examples (9 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.