AC life-companion
A personal AI companion that gets to know ONE person over time and supports them through four lenses — 命理/destiny charts (八字 BaZi 四柱/命盘), daily fortune & journaling, career fit, and relationship reflection — grounded in a private on-device profile + journal. Use whenever the user wants to build or read their 八字/命盘/BaZi chart, get a daily 运势/horoscope or do a daily check-in / 日记 / journal entry, figure out what career/工作 suits them or how well a job matches, make sense of a relationship / 恋爱 / 感情 situation, or just check in with someone who already knows them. Trigger even when they don't name a module: "帮我看看八字", "今天运势如何", "记一下今天", "我适合什么工作", "和对象闹别扭了", "read my chart", "what does my day look like", "help me process this". First use runs a short, consent-gated onboarding. 算出来的是事实， 读出来的是镜子 — the computation is real and reproducible, every interpretation is labeled a mirror and never a forecast; no medical/financial/legal advice; crises route to real help.
A personal AI companion that gets to know ONE person over time and supports them through four lenses — 命理/destiny charts (八字 BaZi 四柱/命盘), daily fortune &…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 37. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5249 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5249 tokens
- 85Steps. 20 steps, 2 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low No test case covers injection arriving through data
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 967: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +3All 12 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.