SKILLEMALL.ai
GitHub ↗ RU Sign in

BC chief-ai-officer-advisor

Use for AI strategy decisions: API vs fine-tune vs build, EU AI Act or US state risk classification, when self-hosting pays off, or AI hiring order. Runs model_buildvsbuy_calculator.py, ai_risk_classifier.py and ai_cost_economics.py.

alirezarezvani/claude-skills Agent Skills author: alirezarezvani MIT 8 files · 3 scripts body ≈ 3 373 tokens Open the sourcegithub.com↗ analyzed 8 d ago

Use for AI strategy decisions: API vs fine-tune vs build, EU AI Act or US state risk classification, when self-hosting pays off, or AI hiring order.

As a process C 64/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice

ProcedureAI and agentstype 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%
93
Quality 40%
95
Run on models
none yet
Process rating
C
64/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: chief-ai-officer-advisor (alirezarezvani/claude-skills)

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 · 7

    ✓ No critical or high findings

    Medium and low: 7
    • low Risky intent intent-offensive-security references/ai_risk_governance.md:213
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **Tactical AI safety techniques (red teaming, adversarial testing).** See `engineering/agent-designer/`.
    • low Risky intent intent-offensive-security references/ai_team_org_evolution.md:115
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      **Eighth hire: AI safety / red team engineer (IF customer-facing AI).**
    • low Risky intent intent-offensive-security references/ai_team_org_evolution.md:165
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Central safety / red team
    • low Risky intent intent-offensive-security references/ai_team_org_evolution.md:178
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | AI safety / red team | Adversarial testing, jailbreak suite, content safety, model card review | Feature shipping |
    • low Risky intent intent-offensive-security SKILL.md:28
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      CAIO, chief AI officer, AI strategy, model selection, foundation model, fine-tuning, RLHF, DPO, LoRA, QLoRA, build vs buy, AI build-vs-buy, model risk tier, EU AI Act, AI Act Article 6, Article 9, Art
      detector
    • low Risky intent intent-offensive-security SKILL.md:138
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Series C | Manager of AI | ML research scientist (only if model IS the product) | AI safety / red team (if customer-facing AI) |
    • low Risky intent intent-offensive-security SKILL.md:139
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Late-stage | Head of AI → CAIO | Multiple research scientists, platform team, safety/red team | Federated AI leads per business unit |

    Files scanned: 8. 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 64/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 8 mutating operations with no state check
    • 50Failures and branches. 0 branches, has a failure section
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 55 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3373 tokens

    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 233: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 55 items
    • +3Output format is stated explicitly
    • +4Has examples (5 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)
    • +3All 3 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.