SKILLEMALL.ai
GitHub ↗ RU Sign in

AB evk-live-borrow-proof

Prove that a deployed Euler EVK market can really borrow against the intended collateral path with tiny live canaries or dry-run previews. Use when an agent needs to validate EVK borrowability on an EVM chain after deployment, especially for cross-vault share-token collateral, isolated collateral proofs, controller or collateral rotation in EVC, debt repayment cleanup, or adapting a known Arbitrum proof flow to other assets and chains.

ClawHub Agent Skills author: dave v0.1.3 MIT-0 5 files body ≈ 1 186 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting

AnalyzerInfrastructuretype 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
93/100
safety, quality, tests
Safety 60%
95
Quality 40%
90
Run on models
none yet
Process rating
B
70/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
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 Secrets in code secret-high-entropy-token references/arbitrum-eusdc1-isolated-example.json:4
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "accountAddress": "0x00…EaD",
      fixturequoted
    • low Secrets in code secret-high-entropy-token references/arbitrum-eusdc1-isolated-example.json:23
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "address": "0xaf…831",
      fixturequoted
    • low Secrets in code secret-high-entropy-token references/arbitrum-eusdc1-isolated-example.json:30
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "address": "0x9d…5Fe"
      fixturequoted
    • low Secrets in code secret-high-entropy-token references/arbitrum-eusdc1-isolated-example.json:34
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "address": "0x0a…899"
      fixturequoted
    • low Secrets in code secret-high-entropy-token references/arbitrum-eusdc1-isolated-example.json:39
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "address": "0x78…dFF"
      fixturequoted

    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 70/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 6 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Failures and branches. 4 branches
    • 100Steps. 67 steps
    • 100Result and completion. Output format and completion criterion are stated
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1186 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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)
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 439: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 67 items
    • +3Output format is stated explicitly
    • +4Reference files are cited in the instructions (1 of 1)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

    External checks

    ClawHub: clean
    This is a disclosed crypto testing skill that can perform real on-chain borrow proof transactions only when live mode and its safeguards are deliberately enabled.
    LLM: benign (high) · VirusTotal: · 29 May 2026