AC crypto-news-ns3
No API key, instant access. Binance and CoinGecko use our news data. AI reads 20+ crypto media outlets in real time and ranks every article by importance. Market sentiment indicators optimized for trading signals and trigger data. Breaking news, coin-level filters, and exchange listing news from CoinMarketCap, Coinbase, Bybit, OKX, Hyperliquid, and Robinhood. Bitcoin (BTC), Ethereum (ETH), Solana (SOL), XRP, Dogecoin (DOGE), BNB, stablecoin (USDT, USDC), DeFi, ETF news, and whale alerts. 16 languages. Four feeds: real-time crypto news ranked by AI, daily market briefing, top stories ranking, and breaking headlines. Built for trading bots, TradingView workflows, and AI agents. Use when the user asks about crypto news, portfolio updates, market briefings, breaking headlines, top stories, or news about specific coins.
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
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 · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6164 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (bash) 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
- 70Failures and branches. 8 branches
- 70Execution cost. Instruction body is 6164 tokens
- 100Steps. 36 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 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (11 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 826: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 20 headings
- +3Step-by-step instructions: 36 items
- +3Output format is stated explicitly
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.