BB mbti-personality
MBTI personality system for AI agents. Switch your AI's personality, thinking style, and communication tone. Supports 4 presets, 16 MBTI types, 32 custom combos. Trigger when user says: "switch personality", "change MBTI", "change style", "set personality", "personality", "what's your MBTI", "what personality", "切换人格", "MBTI人格", "换个性格", "用ENFP的风格", "变个性格", "你是什么性格", "你的MBTI", "我的MBTI", "我是INTJ", "我是ENFP", "技术大佬", "产品经理", "靠谱学长", "天才队友", "Tech Lead", "Silent Tech Lead", "Visionary PM", "Reliable Mentor", "Genius Teammate", "人狠话不多", "脑洞大开", "带你飞", "天才队友", "L", "小C", "顾学长", "林一", "C", "Sage", "Ace", "叫上", "让xx来", "把xx叫来", "bring in", "call in", "invite", "保存人格", "保存这个人格", "保存性格", "关闭人格", "去掉人格", "当前人格", "save personality", "save this personality", "remove personality", "reset personality", "current personality", "recommend", "推荐", "custom", "自定义", "INTJ", "INTP", "ENTJ", "ENTP", "INFJ", "INFP", "ENFJ", "ENFP", "ISTJ", "ISFJ", "ESTJ", "ESFJ", "ISTP", "ISFP", "ESTP", "ESFP", "Architect", "Logician", "Commander", "Debater", "Advocate", "Mediator", "Protagonist", "Campaigner", "Logistician", "Defender", "Executive", "Consul", "Virtuoso", "Adventurer", "Entrepreneur", "Entertainer", "快乐小狗", "绿老头", "宝剑哥", "紫老头", or mentions any MBTI type in the context of personality or communication style.
As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1303 chars, limit 1024
Process rating: all ten parameters 68/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4707 tokens
- 100Tools and files. No external tools needed
- 100Steps. 112 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
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)
- +3Description length 1302: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 46 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 112 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.