BB okx-growth-competition
Agentic Wallet exclusive trading competitions. Full lifecycle: discover → view rules → join → trade → check rank → claim reward. Triggers: 'list trading competitions', 'show available competitions', 'view competition details', 'show competition rules', 'show prize pool', 'register for competition', 'join trading contest', 'check my competition status', 'view leaderboard', 'check my ranking', 'claim competition reward', 'did I win', 'winners list', 'show registered wallet', 'export wallet'. Do NOT use for: general DEX swaps (use okx-dex-swap); portfolio / PnL queries outside a competition (use okx-wallet-portfolio or okx-dex-market); wallet login or tx history (use okx-agentic-wallet); any non-competition trading activity. Do NOT use when the user says only a single word like 'competition', 'rank', or 'claim' without naming a specific competition.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, execution cost, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Concealment
en-hide-from-userSKILL.md:25Instruction to hide actions from the user (quoted — discussed, not commanded)3. `myRankInfo.userTotal = 0` means the user has not yet hit the qualifying threshold or the backend metric pipeline has not picked up their trades yet — it does **NOT** mean the user's chain is unsup
quoted
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10503 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 16 mutating operations with no state check
- 40Execution cost. Instruction body is 10503 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 146 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 10 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 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (50 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 858: 120–800 characters recommended
- -228 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 37 headings
- +3Step-by-step instructions: 146 items
- +3Output format is stated explicitly
- +4Has examples (19 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: 81.