AC okx-dex-token
Use this skill for token-level data: search and discover tokens, browse trending/hot tokens (热门, 代币榜单, by trending score or Twitter/X mentions), get liquidity pool info, view holder distribution by tag (whale/巨鲸, smart money, KOL, sniper, sniper holding percentage, sniper percent, bundler percent), check token safety and honeypot risk (貔貅盘, 'is this token a honeypot', 'can I sell this', 'check token safety'), see who created a token and their history, view recent buy/sell trade activity for a token, find top profit addresses, or filter trade history by wallet type. This skill can be invoked on user intent; the specific token address can be provided after. Do NOT use for cross-market whale/signal tracking — use okx-dex-signal. Do NOT use for meme/pump.fun launch scanning, dev reputation, or bundle detection — use okx-dex-trenches. Do NOT use for personal DEX trade history or price charts — use okx-dex-market.
Use this skill for token-level data: search and discover tokens, browse trending/hot tokens (热门, 代币榜单, by trending score or Twitter/X mentions), get liquidity…
As a process C 63/100 · Has gaps — weak spots: result and completion, running it twice
How to improve
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:142High-entropy token-like string (may be an id, hash or a credential)onchainos token advanced-info --address EPjF…t1v --chain solana
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:145High-entropy token-like string (may be an id, hash or a credential)onchainos token top-trader --address EPjF…t1v --chain solana
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:148High-entropy token-like string (may be an id, hash or a credential)onchainos token top-trader --address EPjF…t1v --chain solana --tag-filter 1
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5703 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 3 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
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5703 tokens
- 85Steps. 71 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 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
- +3Description length 921: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 23 headings
- +3Step-by-step instructions: 71 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.