BB FarmDash Trail Intelligence
Read-only DeFi intelligence for opportunity research, portfolio diagnostics, allocation analysis, route previews, Trail Heat, and Sybil review. Never executes.
As a process B 70/100 · Nearly there — weak spots: consistency, execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Risky intent
intent-wallet-secretsSKILL.md:64Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target| Private key / seed phrase / mnemonic | NEVER | This skill will refuse and explain |
-
medium Risky intent
intent-wallet-secretsSKILL.md:79Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target| Private key / seed phrase | Never | — | Refused by skill design |
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 10251 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "icon" - note
frontmatter-keyunknown frontmatter key "env"
Process rating: all ten parameters 70/100
- 40Consistency. Frontmatter name (FarmDash Trail Intelligence) differs from the folder (farmdash-trail-intelligence)
- 40Execution cost. Instruction body is 10251 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 97 steps
- 100Failures and branches. 20 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 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)
- +1No license
- +2Single-language instructions
- +3Description length 159: enough signal without eating the budget
- +4Structure: 53 headings
- +3Step-by-step instructions: 97 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.