SKILLEMALL.ai
GitHub ↗ RU Sign in

BD it-consulting-workbench-international

IT Consulting & AI Transformation Advisor Workbench — A full-stack automated skill for IT strategic planning, enterprise AI transformation, technical due diligence, vendor selection, enterprise architecture design, digital maturity assessment, IT governance, IT financial management, cybersecurity assessment, cloud migration planning, data strategy & governance, data mesh, business capability platf

ClawHub Agent Skills author: yinjianheng v1.2.0-intl MIT-0 60 files body ≈ 18 212 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

IT Consulting & AI Transformation Advisor Workbench — A full-stack automated skill for IT strategic planning, enterprise AI transformation, technical due…

As a process D 48/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches

GeneratorData and analyticsResearchSecuritytype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
B
77/100
safety, quality, tests
Safety 60%
85
Quality 40%
65
Run on models
none yet
Process rating
D
48/100
Unfinished process
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. 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 · 15

✓ No critical or high findings

Medium and low: 15
  • low Risky intent intent-offensive-security SKILL.md:555
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    | **North America** | $110B+ | 8.5% | AI-powered threat detection, ransomware defense |
    detector
  • low Risky intent intent-offensive-security SKILL.md:559
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Latin America** | $8B+ | 7.8% | Financial sector cybersecurity, ransomware |
  • low Risky intent intent-offensive-security templates/project-acceptance-report-template.md:57
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | NFR-004 | Security | Penetration test with no high-risk vulnerabilities | 0 high-risk | ✅ | Penetration Test Report |
  • low Risky intent intent-offensive-security tools/problem-diagnosis-decision-tree.md:165
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    │   │   ├── Ransomware → Backup + Endpoint security + Security awareness
  • low Risky intent intent-offensive-security tools/problem-diagnosis-decision-tree.md:170
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    │   │   ├── Don't know what vulnerabilities exist? → Penetration testing + Vulnerability scanning
    detector
  • low Risky intent intent-offensive-security workflows/03-strategy-and-solution-design/06-security-strategy-and-risk-management.md:35
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Core Transaction System | System | 100K transactions/sec | Business interruption, $X loss per minute | Ransomware / APT |
  • low Risky intent intent-offensive-security workflows/03-strategy-and-solution-design/06-security-strategy-and-risk-management.md:163
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Lateral Movement Detection | <24h | <1h | <5min |
  • low Risky intent intent-offensive-security workflows/03-strategy-and-solution-design/06-security-strategy-and-risk-management.md:239
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **High** | Can access core systems/data | On-site audit + penetration test + SOC2 Type II | Core system outsourced O&M |
  • low Risky intent intent-offensive-security workflows/03-strategy-and-solution-design/06-security-strategy-and-risk-management.md:283
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ├── Red Team exercises (once every 6 months)
  • low Risky intent intent-offensive-security workflows/04-technology-assessment-and-selection/01-technical-due-diligence.md:51
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Penetration test reports (last 2 rounds)
  • low Risky intent intent-offensive-security workflows/04-technology-assessment-and-selection/01-technical-due-diligence.md:90
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Security Posture** | 20% | 20+ | Penetration testing + vulnerability scanning + compliance review | Security risk matrix |
  • low Risky intent intent-offensive-security workflows/04-technology-assessment-and-selection/01-technical-due-diligence.md:117
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Security Debt | Known vulnerabilities unpatched >90 days, no penetration testing, outdated authentication | H | $0.2-1M |
  • low Risky intent intent-offensive-security workflows/04-technology-assessment-and-selection/01-technical-due-diligence.md:218
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    | Have all internet-facing systems undergone penetration testing? | | |
    detector
  • low Risky intent intent-offensive-security workflows/04-technology-assessment-and-selection/01-technical-due-diligence.md:246
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Regular penetration testing + red team exercises
  • low Risky intent intent-offensive-security workflows/08-delivery-and-closure/02-project-acceptance-and-closure.md:36
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Security Compliance | Penetration test with no high-risk vulnerabilities | Penetration test report | ✅ |

Files scanned: 60. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 18212 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "language"
  • note frontmatter-key unknown frontmatter key "contact"

Process rating: all ten parameters 48/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 10Execution cost. Instruction body is 18212 tokens: crowds the task out of the window
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 15 mutating operations with no state check
  • 60Steps. 35 steps, 8 vague phrases
  • 60Result and completion. Output format stated, no completion criterion
  • 100Tools and files. No external tools needed
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 34 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 400: enough signal without eating the budget
  • +4Structure: 88 headings
  • +3Step-by-step instructions: 35 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.

External checks

ClawHub: suspicious
This is not malware, but it is a broad enterprise consulting skill that can steer users into handling sensitive company, employee, cloud, and credential information without enough guardrails.
LLM: suspicious (high) · VirusTotal: · 14 Jul 2026