AB skill-engineer
Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester subagents for quality-gated skill development. Use when user asks to "design skill", "review skill", "test skill", "audit skills", "refactor skill", or mentions "agent kit quality".
As a process B 73/100 · Nearly there — weak spots: result and completion, execution cost
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9673 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 73/100
- 40Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 9673 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (git) that frontmatter does not declare
- 85Steps. 163 steps, 2 vague phrases
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 16 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 17 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 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
- -35 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 334: enough signal without eating the budget
- +4Structure: 58 headings
- +3Step-by-step instructions: 163 items
- +4Has examples (30 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.