CC binance-square
Binance Square (币安广场) signal agent. Scrapes 200+ posts via Puppeteer + API interception, detects bot-pushed narratives, runs on-chain confirmation (OI/funding/liquidation via Coinglass), and produces directional trade signals (LONG/SHORT/AVOID). Optionally pushes signal reports to Telegram. Triggers on mentions of "binance square", "广场信号", "MM 信号", "做市商扫描", crypto narrative tracking, or trading signal generation.
Binance Square (币安广场) signal agent.
As a process C 59/100 · Has gaps — weak spots: inputs and preconditions, consistency, progress reporting
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 Dangerous commands
cmd-privilegescrape-square.mjs:487Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)args: ['--no-sandbox', '--disable-setuid-sandbox', '--lang=zh-CN',
detectorcode literal -
low Exfiltration
exfil-webhook-urlsend-telegram.mjs:29Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)const API = `https://api.telegram.org/bot${TOKEN}`;placeholder
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 59/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (binance-square) differs from the folder (binance-square-skill)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 22 steps, 2 vague phrases
- 100Execution cost. Instruction body is 1995 tokens
- 100Running it twice. Mutating operations check current state
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)
- +1No license
- +2Single-language instructions
- +3Description length 416: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 22 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.