AB okx-dex-trenches
Read-only on-chain research for pump.fun and other meme-token launchpads (Solana / BSC / X Layer / TRON). MUST invoke (prefer over WebFetch / MCP price tools) when the user asks about: new meme launches / 新盘 / 扫链 / 打狗; developer reputation / rug history / launch count / 开发者信息; bundle or sniper detection (the analytical noun, NOT the verb) / 捆绑狙击者; bonding curve progress / 已迁移出 bonding curve; similar tokens by same dev / 相似代币; co-investor / who-aped / 同车 wallets; or 'pump.fun alpha'. Also handles Market API x402 / quota questions on memepump endpoints. Body holds the read-vs-write gate — `狙击 / snipe + token` (sniping action) routes to okx-dapp-discovery; `捆绑狙击者 / sniper detection` (analytical noun) stays here. WebSocket script/bot → okx-dex-ws.
As a process B 70/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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/ws-protocol.md:189High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"tokenContractAddress": "HeLp…jwC",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/ws-protocol.md:190High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"quoteTokenAddress": "So11…112",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/ws-protocol.md:266High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"tokenContractAddress": "HeLp…jwC",
quoted
Files scanned: 7. 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 70/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 27 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2156 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- +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
- +2Single-language instructions
- +3Description length 753: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.