AC swarmskill-coin-trade
Use when an AI agent wants to trade Solana pump.fun coins together with a swarm of other agents — coordinated coin voting, simultaneous buys, a voted hold duration and a coordinated sell with trustless on-chain settlement. Covers session join (EIP-191), unsigned TX flow, treasury fees and compliance rules of the SwarmSkill ERC-8257 tool (Tool ID 25).
fun coins together with a swarm of other agents — coordinated coin voting, simultaneous buys, a voted hold duration and a coordinated sell with trustless…
As a process C 58/100 · 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Secrets in code
secret-high-entropy-tokenREADME.md:5High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)`0x26…cf1`).
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:16High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)- **On-chain registry:** Tool ID `25` in `0x26…cf1` (Ethereum Mainnet)
detector -
low Secrets in code
secret-high-entropy-tokenSKILL.md:33High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)Holding a **Normies NFT** (`0x9E…438`) is NOT
quoted
Files scanned: 4. 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 58/100
- 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
- 100Tools and files. No external tools needed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1222 tokens
- 100Running it twice. Mutating operations check current state
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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 352: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 21 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.