AC clawfight
Raise and battle a unique lobster pet with evolving personality. Hatch, feed, patrol, fight other lobsters in PvP. Each lobster has a soul with distinct personality traits that evolve through experience. Idle automation with heartbeat integration. Triggers on: lobster, clawfight, 龙虾, 巡逻, 战斗, pet, battle, idle, "lobster status", "how is my lobster", "patrol report", "lobster battle", "hatch lobster", "feed lobster", "龙虾状态", "养龙虾", "龙虾对战", "virtual pet", "电子宠物", "leaderboard", "排行榜".
As a process C 55/100 · Has gaps — 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.
- 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: 7. 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") - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (clawfight) differs from the folder (claw-fight)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 93 steps
- 100Execution cost. Instruction body is 3742 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 18 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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
- +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
- +5Description quotes 8 example trigger phrases
- +3Description length 486: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 93 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.