BB chainaware-behavioral-prediction
Use this skill whenever a user asks about wallet safety, fraud risk, rug pull detection, wallet behavior analysis, DeFi personalization, on-chain reputation scoring, AML checks, token ranking by holder quality, airdrop screening, lending risk, token launch auditing, or AI agent trust scoring. Triggers on questions like: is this wallet safe?, will this pool rug pull?, what will this address do next?, score this wallet, detect fraud for address, personalize my DeFi agent, rank this token, top AI tokens, best holders of this token, check this contract, is this token safe?, profile this wallet, KYC this address, pre-screen this user, AML check this wallet, is this address suspicious?, screen this wallet before onboarding, what is the risk score of this address?, analyze on-chain behavior, is this LP safe to deposit?, will this contract rug?, what DeFi products suit this wallet?, segment this user, what is this wallet's experience level?, find strong token holders, which token has the best community?,rank tokens by holder quality, should we list this token?, audit this launch, is this deployer trustworthy?, vet this IDO, launch safety check, screen this airdrop list, filter bots from airdrop, rank these wallets for token distribution, fair airdrop allocation, assess this borrower, what collateral ratio for this wallet?, lending risk for 0x..., what interest rate for this borrower?, should I lend to this wallet?, screen this AI agent, is this agent wallet safe?, agent trust score for 0x..., check the feeder wallet for this agent, can I trust this agent?, route this wallet to onboarding, is this user a beginner?, skip onboarding for this wallet?, or any request to analyze a blockchain wallet address, smart contract, token, or AI agent for risk, behavior, intent, community strength, or trustworthiness. Also use when integrating the ChainAware MCP server into Claude Code, Cursor, ChatGPT, or any MCP-compatible AI agent framework.
As a process B 78/100 · Nearly there — weak spots: execution cost, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1977 chars, limit 1024 - warning
body-longSKILL.md body ≈ 8845 tokens (recommended < 5000); move details to references/ - note
description-budgetdescription takes 1977 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 78/100
- 0Progress reporting. Says nothing while it works
- 40Execution cost. Instruction body is 8845 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web, python) 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
- 100Steps. 219 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 20 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)
- +3Description length 1977: 120–800 characters recommended
- -230 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Structure: 55 headings
- +3Step-by-step instructions: 219 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 45.