SKILLEMALL.ai
GitHub ↗ RU Sign in

BB data-breach-response

Data breach incident response with ENISA severity scoring, notification timelines, and compliance tracking. Use for breach assessment and response.

borghei/Claude-Skills Agent Skills author: borghei 5 files · 2 scripts body ≈ 3 945 tokens Open the sourcegithub.com↗ analyzed 32 h ago

Data breach incident response with ENISA severity scoring, notification timelines, and compliance tracking.

As a process B 75/100 · Nearly there — weak spots: result and completion, inputs and preconditions

ProcedureInfrastructureData and analyticsSecuritytype 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
94/100
safety, quality, tests
Safety 60%
95
Quality 40%
92
Run on models
none yet
Process rating
B
75/100
Nearly there
Inputs and preconditions w 11
0
Result and completion w 14
40
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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • low Risky intent intent-offensive-security references/enisa_methodology.md:108
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      | Malicious | +0.5 | Deliberate attack, insider threat, ransomware, social engineering |
      detector
    • low Risky intent intent-offensive-security references/enisa_methodology.md:210
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Ransomware Cases
    • low Risky intent intent-offensive-security references/enisa_methodology.md:214
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | 01 | Ransomware with proper backup, no exfiltration | 2-3 | 0.50-1.00 | Availability loss only; backup restored quickly | LOW-MEDIUM |
    • low Risky intent intent-offensive-security references/enisa_methodology.md:215
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | 02 | Ransomware without proper backup | 2-3 | 0.50-1.00 | Availability loss, potential permanent data loss | MEDIUM-HIGH |
    • low Risky intent intent-offensive-security references/enisa_methodology.md:216
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | 03 | Ransomware on hospital system with exfiltration | 4 | 1.00 | Health data, malicious, confidentiality + availability | VERY HIGH |

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 75/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 40Result and completion. Does not say what the result is
    • 50When it triggers. No condition that starts the skill
    • 100Tools and files. No external tools needed
    • 100Steps. 60 steps
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3945 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress
    • low 12 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)
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +3Description length 147: enough signal without eating the budget
    • +4Structure: 24 headings
    • +3Step-by-step instructions: 60 items
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)
    • +3All 2 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.