BC okx-dex-swap
NOTE (gating): route to okx-dapp-discovery (NOT this skill) when prompt names a specific DApp as the swap venue: Polymarket, Aave V3, Hyperliquid, PancakeSwap, Morpho, Raydium, Curve, Compound V3, Pendle, Lido, ether.fi, GMX V2, Kamino, Orca, Meteora, Clanker, pump.fun, Uniswap. Examples that go to okx-dapp-discovery: 'swap on PancakeSwap', 'swap SOL for USDC on Raydium', 'use Hyperliquid to long ETH', '在 Curve 上换 USDT', 'swap on Uniswap'. okx-dapp-discovery installs the DApp's plugin and uses its native interface; this skill is for OKX-aggregated swaps without a named venue. Use this skill to 'swap tokens', 'trade OKB for USDC', 'buy tokens', 'sell tokens', 'exchange crypto', 'convert tokens', 'swap SOL for USDC', 'get a swap quote', 'execute a trade', 'find the best swap route', 'cheapest way to swap', 'optimal swap', 'compare swap rates', 'get swap calldata', 'build unsigned tx', or mentions swapping/trading/buying/selling/exchanging tokens across XLayer, Solana, Ethereum, Base, BSC, Arbitrum, Polygon, or any 20+ supported chains. Aggregates 500+ DEX sources for optimal routing/price. Supports slippage control, price impact protection, and cross-DEX route optimization.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:50High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Tron | `T9yD…Wwb` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:51High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Ton | `EQAA…M9c` |
table
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1190 chars, limit 1024
Process rating: all ten parameters 57/100
- 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. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 85Steps. 31 steps, 2 vague phrases
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3464 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (8 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)
- +3Description length 1190: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 25 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.