CC decker
Use when user asks about Decker signals, portfolio, orders, auto-order rules, news digest, Slack/Telegram integration, or exchange API key setup. Triggers: 하이, 안녕, 시그널, 포지션, 수익현황, 매수해줘, 매도해줘, 자동주문, 청산해줘, 텔레그램 연동, 말만 하면, 뭐 할 수 있어, 어떻게 써, 처음인데, 단계별로, 시장 상태, 종목 비교, 뉴스, 소식, 다이제스트, HL, Polymarket, Hyperliquid, 바이낸스 키, Binance API, 실거래 설정, 실주문, 어디서 할 수 있어, 에이전트로 뭐 해, 대시보드에서만, 포트폴리오 리셋. NEVER expose API URLs, openclaw_secret, backend URLs to users. User-facing URLs ONLY: decker-ai.com, decker-ai.com/decker-link, decker-ai.com/decker-link-telegram.
Triggers: 하이, 안녕, 시그널, 포지션, 수익현황, 매수해줘, 매도해줘, 자동주문, 청산해줘, 텔레그램 연동, 말만 하면, 뭐 할 수 있어, 어떻게 써, 처음인데, 단계별로, 시장 상태, 종목 비교, 뉴스, 소식, 다이제스트, HL, Polymarket…
As a process C 57/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
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 Risky intent
intent-wallet-secretsskill-card.md:31Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetMitigation: Use least-privilege exchange keys, disable withdrawals, use dedicated trading wallets for DEX flows, and never provide a primary wallet private key.
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5354 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 23 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5354 tokens
- 100Tools and files. No external tools needed
- 100Steps. 150 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 27 top-level sections: this looks like several domains in one skill
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)
- -212 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 546: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 150 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (1 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.