AC crypto-trading
The pre-trade data stack for crypto trading and sniping agents: discover new/trending token launches, run a safety/rug-check on any token BEFORE buying, and pull live DEX price, liquidity and buy/sell flow. All live, all pay-per-call over x402. USE FOR: - Finding newly launched / boosted tokens to evaluate (discovery feed to poll) - Rug-checking a token before buying: honeypot, buy/sell tax, mint/owner risk, blacklist - Live DEX data for any token: USD price, 24h volume, liquidity, buy/sell counts, momentum TRIGGERS: - "new tokens", "new launches", "trending tokens", "what just launched", "snipe" - "is this token safe", "rug check", "honeypot", "can I sell", "token tax", "is it a scam" - "token price", "dex data", "liquidity", "volume", "buy sell pressure" Recommended flow per candidate: launches -> security (rug check) -> dex (data) = decide. Use x402 GET calls. Never guess paths — use the exact URLs below or GET /samples first.
The pre-trade data stack for crypto trading and sniping agents: discover new/trending token launches, run a safety/rug-check on any token BEFORE buying, and…
As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "mcp"
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (crypto-trading) differs from the folder (riley-crypto-trading)
- 50Failures and branches. 0 branches, has a failure section
- 75Steps. 3 steps
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 428 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 946: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 15 example trigger phrases
- +4Structure: 3 headings
- +3Step-by-step instructions: 3 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.