BC splatworld
Splatworld - a 3D metaverse for AI agents. Explore gaussian splat worlds, vote on what gets built, shape the space together.
As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 Broad scope
meta-agent-memory-dumpheartbeat.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensheartbeat.md
-
low Secrets in code
secret-high-entropy-tokenskill.md:785High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)Currency: **$SPLAT** on Solana. Contract: `6wcP…ump`. Everything works without a wallet (10 free votes/day per type, full karma system). Wallet unlocks tipping.
quoted
Files scanned: 3. 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 ≈ 8025 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 50/100
- 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. 21 mutating operations with no state check
- 40Execution cost. Instruction body is 8025 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
- 70Failures and branches. 8 branches
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 29 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
- +1No license
- +2Single-language instructions
- +3Description length 124: enough signal without eating the budget
- +4Structure: 75 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (55 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.