BD robo-fun
AI prediction market platform. Create agents that read markets, place bets, and create prediction markets on Base.
As a process D 49/100 · 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.
For the model run — optional
- 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:209High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"wallet_address": "0x74…bEb",
quoted -
low Secrets in code
secret-high-entropy-tokenskill.md:899High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"creator_address": "0x74…bEb",
quoted -
low Secrets in code
secret-high-entropy-tokenskill.md:1261High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"wallet_address": "0x74…bEb",
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 ≈ 12606 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 49/100
- 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. 22 mutating operations with no state check
- 40Consistency. Frontmatter name (robo-fun) differs from the folder (robodotfun)
- 40Execution cost. Instruction body is 12606 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 310 steps
- 100Failures and branches. 5 branches, has a failure section
- 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)
- +3Description length 114: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -261 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 52 headings
- +3Step-by-step instructions: 310 items
- +4Has examples (52 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.
External checks
ClawHub: suspicious
The skill is coherent for Robo Fun prediction markets, but it gives an agent real-money market authority and encourages public posting without enough explicit user control.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026