AC chainflip-swap
Execute native cross-chain cryptocurrency swaps via Chainflip Broker as a Service. Trigger whenever the user wants to swap, exchange, trade, convert, move, or bridge crypto across chains: BTC, ETH, SOL, DOT, TRX (Tron), USDC, USDT, FLIP. These are real Layer-1 assets, no wrapped tokens and no bridges. Patterns: "swap BTC for ETH", "convert my SOL to USDC", "move DOT to Tron", "get a quote for 1 BTC to ETH", "DCA 5000 USDC into BTC", "what's the rate", "start a swap", "check my swap status", "where do I send my Bitcoin". Also triggers for status checks: "is my swap done", "track swap <id>", "swap stuck". If the user names any of these assets with intent to move or trade them, use this skill.
Execute native cross-chain cryptocurrency swaps via Chainflip Broker as a Service.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 0. 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 62/100
- 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. 9 mutating operations with no state check
- 40Consistency. Frontmatter name (chainflip-swap) differs from the folder (chainflip)
- 70When it triggers. States when to use, but not when not to
- 85Steps. 17 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1364 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (4 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +3Description length 699: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.