BC crypto-whale-alerts
Real-time cryptocurrency whale tracker for AI agents and crypto traders. Monitors large on-chain transactions on Bitcoin, Ethereum, and major altcoins, tracks known whale wallets (exchanges, institutions, smart money), detects accumulation/distribution patterns, and generates actionable alerts. Commands: - whale_alerts.py scan Scan for whale transactions above threshold - whale_alerts.py summary Get whale activity summary - whale_alerts.py watch List tracked whale wallet addresses - whale_alerts.py set-threshold <usd> Set minimum USD threshold Environment: WHALE_MIN_USD (default 100000), WHALE_COOLDOWN (default 60 min). Python 3.9+, zero external dependencies. Uses mock data structure that maps to real Etherscan/Blockchair API responses in production. Whale classification: INFLOW (exchange receiving, potential selling pressure) vs OUTFLOW (cold storage, accumulation signal). Watchlist includes Binance, Coinbase, Grayscale, and notable smart money addresses.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read
-
low Secrets in code
secret-high-entropy-tokenscripts/whale_alerts.py:20High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"0x28…d60": {"label": "Binance Hot", "type": "exchange"},quoted -
low Secrets in code
secret-high-entropy-tokenscripts/whale_alerts.py:21High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"0x21…549": {"label": "Binance 2", "type": "exchange"},quoted -
low Secrets in code
secret-high-entropy-tokenscripts/whale_alerts.py:22High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"0xDF…63d": {"label": "Binance 3", "type": "exchange"},quoted -
low Secrets in code
secret-high-entropy-tokenscripts/whale_alerts.py:23High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"0x3f…0bE": {"label": "Binance 4", "type": "exchange"},quoted -
low Secrets in code
secret-high-entropy-tokenscripts/whale_alerts.py:24High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"0x21…549": {"label": "FTX", "type": "exchange"},quoted
Files scanned: 4. 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 53/100
- 0Result and completion. Does not say what the result is
- 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
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 355 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 987: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 6 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.