AB Gougoubi Pump Lifecycle
End-to-end operator for a Gougoubi pump-style prediction market. Creates the proposal, spins up conditions, supervises trading liquidity, submits the real-world result at deadline, shepherds the dispute window, then harvests creator fees and settles winner payouts. Use whenever the user says "run a pump market" / "go from idea to settlement" / "handle this pump lifecycle" without naming a specific stage.
As a process B 76/100 · Nearly there — weak spots: consistency
How to improve
- 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
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "id" - note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "pattern" - note
frontmatter-keyunknown frontmatter key "interaction" - note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "stage" - note
frontmatter-keyunknown frontmatter key "os" - note
frontmatter-keyunknown frontmatter key "installCommand" - note
frontmatter-keyunknown frontmatter key "dependsOn"
Process rating: all ten parameters 76/100
- 40Consistency. Frontmatter name (Gougoubi Pump Lifecycle) differs from the folder (ggb-pump-lifecycle)
- 60Tools and files. Uses tools (bash, web) 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
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 69 steps
- 100Failures and branches. 16 branches, has a failure section
- 100Execution cost. Instruction body is 3723 tokens
- 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 13 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 407: enough signal without eating the budget
- +4Structure: 44 headings
- +3Step-by-step instructions: 69 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.