BB gmgn-cooking
[FINANCIAL EXECUTION] Create and launch meme coins and crypto tokens on launchpads (Pump.fun, FourMeme, Bonk, BAGS, Flap, Klik, Clanker, etc.) via bonding curve fair launch, or query token creation stats by launchpad via GMGN API. Requires explicit user confirmation. Use when user asks to create a token, launch a meme coin, cook a coin, deploy on a launchpad, or check launchpad creation stats on Solana, BSC, or Base.
As a process B 74/100 · Nearly there — weak spots: execution cost
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 1
-
high Concealment
en-hide-from-userSKILL.md:617Instruction to hide actions from the user- **File path** → silently run `base64 -i <path>` and pass the result to `--image`. Do not mention "base64" to the user.
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9860 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 74/100
- 40Execution cost. Instruction body is 9860 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. 72 steps
- 100Failures and branches. 18 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 19 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (8 tags): a typed call is more reliable
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)
- -230 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 420: enough signal without eating the budget
- +4Structure: 39 headings
- +3Step-by-step instructions: 72 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.