AB coingecko
Use this skill for any request involving cryptocurrency market data, coin prices, trading volume, market cap, OHLC charts, historical data, exchanges, derivatives, NFTs, DeFi, on-chain token data, liquidity pools, DEX data, or anything powered by CoinGecko or GeckoTerminal APIs. Trigger this skill whenever the user asks about crypto prices, token data, market trends, or wants to call any CoinGecko or GeckoTerminal endpoint — even if they don't explicitly say "CoinGecko". Also trigger when the user asks about API keys, rate limits, or authentication for these APIs.
As a process B 67/100 · Nearly there — weak spots: result and completion, consistency
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Secrets in code
secret-high-entropy-tokenREADME.md:88High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)> *"What is the current market cap of DZnQ…9Jo from Solana?"*
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/contract.md:90High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"solana": "EPjF…t1v"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/nfts.md:76High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"contract_address": "0xBd…cf8",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/onchain-categories.md:90High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"address": "7dRp…28V",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/onchain-categories.md:114High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"address": "JBMw…gAB",
quoted
Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (coingecko) differs from the folder (coingecko-api)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 40 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Execution cost. Instruction body is 2492 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +3Description length 570: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 40 items
- +4Reference files are cited in the instructions (20 of 20)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.