AB skill-creator-ProMax
从想法到 Skill 文件的全流程创建器。通过多轮对话帮助用户设计、打磨并生成高质量的 Agent Prompt， 最终输出可直接使用的多平台 Skill 文件（OpenClaw、Claude Code、Cursor、Cline 等）。 Full-cycle Skill creator from idea to file. Helps users design, iterate, and generate production-ready Agent Prompts through multi-turn conversation, then outputs multi-platform Skill files (OpenClaw, Claude Code, Cursor, Cline, etc.). 触发词：生成 skill, 创建 skill, 设计 skill, 新建 skill, skill prompt, agent prompt, system prompt, 生成 agent prompt, 设计 skill prompt, 写个 skill prompt, skill-creator, create skill, design skill, prompt to skill, skill creator, skill builder. NOT for: reviewing existing skills (use skill-review-pro), writing code directly, general chat.
As a process B 74/100 · Nearly there — weak spots: progress reporting
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 "homepage"
Process rating: all ten parameters 74/100
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (write) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4599 tokens
- 100Steps. 328 steps
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 25 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 678: enough signal without eating the budget
- +4Structure: 66 headings
- +3Step-by-step instructions: 328 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.