BC okx-dapp-discovery
Plugin router for 20 supported third-party DeFi protocols (Polymarket, Aave, Hyperliquid, PancakeSwap, Morpho, Raydium, Curve, Compound, Pendle, Lido, ether.fi, GMX, Kamino, Orca, Meteora, Clanker, pump.fun, Uniswap) and their protocol-native tokens (HYPE, HLP, eETH, weETH, stETH, wstETH, LDO, GHO, CAKE, CRV, COMP, RAY, ETHFI, GLP, kToken, PT-* / YT-*, $CLANKER). Resolves the named DApp/token to the right plugin, installs it, and forwards the user's prompt — the plugin owns the actual trade/bet/transfer. Fires on: (1) named DApp + action verb (swap/deposit/stake/long/borrow/buy/sell/snipe/farm/claim, EN or ZH 买/卖/换/存/质押/借/做多/做空/狙击); (2) comparison of two-or-more supported DApps with intent to choose ("Aave vs Compound for stables", "Lido vs ether.fi"); (3) Polymarket UpDown intent (`<COIN> 5min updown`, `<COIN> 5 分钟涨跌`, `预测市场`, `place a bet on Polymarket`); (4) protocol-native token alone with action verb ("deposit USDC into HLP", "PT-stETH on Pendle"); (5) pump.fun WRITE verbs (buy/sell/snipe/ape/swap or 买/卖/狙击/梭哈/帮我买). See body for anti-trigger / disambiguation rules.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1088 chars, limit 1024 - warning
body-longSKILL.md body ≈ 11098 tokens (recommended < 5000); move details to references/
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
- 40Execution cost. Instruction body is 11098 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 85Steps. 94 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 13 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (37 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)
- +3Description length 1087: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 38 headings
- +3Step-by-step instructions: 94 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.