SKILLEMALL.ai
GitHub ↗ RU Sign in

AC ai-exposure-analyzer

Analyze any public company's AI exposure using the 8-dimension AI Exposure Index. Fetches last 4 10-K filings (or international equivalents), O*NET data, patents, and earnings transcripts to score vulnerability and adaptive capacity, classifying companies as AI Fortified/Transformer/Bystander/Endangered with valuation overlay. Use whenever the user asks about AI risk, AI readiness, AI exposure, workforce automation, competitive moat durability, or how AI impacts a stock or business. Triggers on "AI exposure", "AI vulnerability", "AI analysis of [company]", "how will AI affect [company]?", "is [company] ready for AI?", "rate this company on AI", "AI risk for [ticker]", or any company evaluation through an AI lens.

ClawHub Agent Skills author: martinpmm v1.0.2 11 files body ≈ 2 669 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 53/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency

AnalyzerSecurityFinanceInfrastructuretype 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
A
98/100
safety, quality, tests
Safety 60%
98
Quality 40%
99
Run on models
none yet
Process rating
C
53/100
Has gaps
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

    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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Risky intent intent-offensive-security data/Occupation_Data.txt:1003
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      55-1015.00	Command and Control Center Officers	Manage the operation of communications, detection, and weapons systems essential for controlling air, ground, and naval operations. Duties include managi
    • low Risky intent intent-offensive-security data/Occupation_Data.txt:1014
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      55-3015.00	Command and Control Center Specialists	Operate and monitor communications, detection, and weapons systems essential for controlling air, ground, and naval operations. Duties include maintai

    Files scanned: 11. 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 53/100

    • 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
    • 30Running it twice. 2 mutating operations with no state check
    • 40Consistency. Frontmatter name (ai-exposure-analyzer) differs from the folder (ai-exposure-analysis-for-investing)
    • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 30 steps
    • 100Execution cost. Instruction body is 2669 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

    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 7 example trigger phrases
    • +3Description length 722: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 30 items
    • +3Output format is stated explicitly
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 99.

    External checks

    ClawHub: clean
    This is a public-data investment research helper with no evidence of credential use, hidden access, persistence, or destructive behavior.
    LLM: benign (high) · VirusTotal: · 29 May 2026