BD web3-crypto-ops
Universal Web3 & Crypto operating skill for AI agents. 12 domains, 60+ API endpoints, 5 providers: OKX DEX aggregator, Binance Web3 intelligence, Binance/Gate.io/Bitget Spot. Production-grade patterns: RPC health failover, 10-point token safety scoring, honeypot round-trip simulation, V2/V3 smart routing, direct pool turbo execution, Pump.fun/Jupiter auto-dispatch. Commercial risk gates and compliance controls built-in.
As a process D 44/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:129High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)**Wrapped Native**: BSC `0xbb…95c` | ETH `0xC0…Cc2` | Base `0x42…006`
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:236High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)**V2 Routers**: BSC `0x10…24E` | ETH `0x7a…88D` | Base `0x47…D24`
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:237High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)**V3 Routers**: ETH `0xE5…564` | Base `0x26…481` | BSC `0x13…Dd4`
quoted
Files scanned: 2. 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") - warning
body-longSKILL.md body ≈ 8944 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "always" - note
frontmatter-keyunknown frontmatter key "requiredEnv"
Process rating: all ten parameters 44/100
- 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
- 30Running it twice. 9 mutating operations with no state check
- 40Consistency. Frontmatter name (web3-crypto-ops) differs from the folder (web3-crypto-ops-skill)
- 40Execution cost. Instruction body is 8944 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 100Steps. 18 steps
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 23 top-level sections: this looks like several domains in one skill
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
- -239 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 423: enough signal without eating the budget
- +4Structure: 51 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (10 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.