CC clawlogic-trader
REAL MONEY: this skill signs and sends transactions on Arbitrum One mainnet from the agent's own wallet. Trades, liquidity, market-creation fees and UMA assertion bonds spend real ETH/WETH and can be lost. Use this skill when the agent needs to interact with CLAWLOGIC prediction markets. This includes: finding open markets, analyzing market questions to form opinions, buying and selling YES/NO positions, providing liquidity, creating new markets (without duplicating existing ones), asserting outcomes via UMA Optimistic Oracle, disputing incorrect assertions, settling resolved markets to claim winnings, and posting bet narratives ("what I bet and why") to the frontend feed. Triggers: - "what CLAWLOGIC markets are open?" / "find a CLAWLOGIC market about..." - "create a market about..." - "what do you think about this CLAWLOGIC market: [question]?" - "buy YES/NO on market..." / "sell my position..." - "provide liquidity to market..." - "assert the outcome of market..." - "dispute the assertion on market..." - "check my CLAWLOGIC positions" - "settle market..."
REAL MONEY: this skill signs and sends transactions on Arbitrum One mainnet from the agent's own wallet.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Shorten the description to 1024 characters.
- 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 · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1075 chars, limit 1024
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 12 mutating operations with no state check
- 40Consistency. Frontmatter name (clawlogic-trader) differs from the folder (clawlogic)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 85Steps. 34 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 3053 tokens
- 100Progress reporting. Reports progress
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1074: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.