AB openclaw-soul-forge
Forge a complete lobster soul for your OpenClaw AI Agent. Choose a direction or pull a gacha draw — outputs identity positioning, soul description (SOUL.md), character-driven boundary rules, a name, and an avatar image prompt. If baoyu-image-gen skill is installed, generates a styled avatar automatically. Use when you need to create, design, or customize an OpenClaw lobster soul. Not for: tweaking an existing SOUL.md, non-OpenClaw platforms, or purely tool-type agents with no personality requirements. Trigger words: lobster soul, lobster character, OpenClaw soul, forge lobster, gacha, random lobster, lobster NPC, lobster backstory, lobster persona, soul forge, lobster identity, openclaw soul, lobster spirit, lobster profile.
As a process B 70/100 · Nearly there — weak spots: result and completion
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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 44 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2801 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
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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 734: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.