AC cofferline
Manage an autonomous agent's on-chain treasury and prediction-market risk via Cofferline — keep a machine wallet funded, gassed, converted, spend-controlled, and accounted for, non-custodially over a REST API; for prediction-market agents (Polymarket) it also vaults trade-scoped credentials write-only, enforces hard risk policies (per-market caps, daily loss stops) server-side from the real books, routes policy-gated LIMIT orders, and journals fills. Use when an agent needs to hold/convert/spend crypto, trade prediction markets under risk limits, set a spending policy, grant scoped revocable signing authority, pay for services in USDC (x402), or produce an audit trail. Cofferline is non-custodial of your wallet and its keys (prepaid fee balances and optional venue credentials are enumerated exceptions in the authority/custody matrix).
Manage an autonomous agent's on-chain treasury and prediction-market risk via Cofferline — keep a machine wallet funded, gassed, converted, spend-controlled…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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: 2. 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 51/100
- 0Result and completion. Does not say what the result is
- 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
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2452 tokens
- 100Running it twice. Mutating operations check current state
- 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)
- +3Description length 846: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 7 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.