AC payql
Get live on-chain data from The Graph, paid per query in USDC over x402 — gasless, keyless, bring-your-own-wallet. Each query spends real USDC (~$0.01) from a wallet you control — use a dedicated, low-balance Base wallet. Discover the right live subgraph, see the price before paying, then pull the data in one loop. Trigger keywords: subgraph, The Graph, GraphQL, on-chain data, DeFi, DEX, pool, TVL, swap, NFT, ENS, token holders, governance, x402, pay per query, USDC, Base, gateway.
Get live on-chain data from The Graph, paid per query in USDC over x402 — gasless, keyless, bring-your-own-wallet.
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Secrets in code
secret-high-entropy-tokenreferences/gateway.md:13High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- **Payment:** the first request returns `402` with the challenge in a base64 **`payment-required` response header** (`accepts[]` → `scheme: exact`, `network: eip155:8453`, `asset:` USDC `0x83…CD6
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/gateway.md:18High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)Query The Graph **network subgraph** (`DZz4…qmp`) with its fulltext index, ranked by curation signal:
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/gateway.md:47High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)Example result (Uniswap V3, `5zvR…NFV`):
quoted
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
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
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (payql) differs from the folder (payqlskill)
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Execution cost. Instruction body is 833 tokens
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
- +1No license
- +2Single-language instructions
- +3Description length 486: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.