BB chinese-fortune-telling
Chinese fortune telling (算命 / 算卦 / 看八字 / 排盘) grounded in classical source texts: a bundled rule engine computes the chart, then the agent interprets it with an explicit school declaration. Computes BaZi Four Pillars (八字 / 四柱) with true-solar-time and 1986–1991 China DST correction via scripts/cantian (buildBaziFromSolar.ts, convertToTrueSolarTime.ts), pattern and useful-god analysis via scripts/engine/bazi-analysis.js, and Zi Wei Dou Shu palaces and four transformations via scripts/engine/ziwei.js. Also covers Liu Yao (六爻 / 起卦), Mei Hua Yi Shu (梅花易数), Qi Men Dun Jia (奇门遁甲), Da Liu Ren (大六壬), Qi Zheng Si Yu (七政四余), classical Western astrology, and date selection (择吉 / 择日 / 黄道吉日). Use whenever the user asks to 算命 / 算卦 / 批八字 / 看生辰八字 / 排盘 / 看命盘, asks about 运势 / 大运 / 流年 (luck cycles), 合婚 / 合盘 (compatibility), 择日 / 挑日子 (picking an auspicious date), wants a 起卦 / 占卜 / 问事 reading on one specific question, or asks whether a third-party fortune-telling app report (测测 / 生辰) is trustworthy. Also use for 术数 classic questions — 子平真诠、滴天髓、穷通宝鉴、三命通会、神峰通考、紫微斗数全书、增删卜易、卜筮正宗、梅花易数、御定奇门宝鉴、六壬大全、协纪辨方书、古典占星、Chinese metaphysics. Not for Tarot, sun-sign horoscopes, numerology, feng-shui layout, or any medical, legal, or investment recommendation. 中文摘要：以《子平真诠》《滴天髓》《穷通宝鉴》《协纪辨方书》等典籍为判据的命理推理引擎，排盘由随包脚本计算（含真太阳时与 1986–1991 夏令时校正），解读须声明流派并标注典籍出处。覆盖八字四柱、紫微斗数、六爻起卦、梅花易数、奇门遁甲、大六壬、七政四余、古典占星、合婚合盘、择日择吉。触发词：算命、算卦、看八字、批八字、生辰八字、排盘、看命盘、运势、流年、大运、合婚、合盘、择日、择吉、起卦、占卜、紫微斗数、六爻、梅花易数、奇门遁甲、子平真诠、滴天髓、穷通宝鉴。不做塔罗、星座运势、生命灵数、风水布局与医疗／法律／投资建议。
Chinese fortune telling (算命 / 算卦 / 看八字 / 排盘) grounded in classical source texts: a bundled rule engine computes the chart, then the agent interprets it with…
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions
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: 42. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1502 chars, limit 1024 - note
description-budgetdescription takes 1502 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "description_zh" - note
frontmatter-keyunknown frontmatter key "description_en" - note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "read_when" - note
frontmatter-keyunknown frontmatter key "not_for"
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 47 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2747 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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
- +3Description length 1502: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 20 headings
- +3Step-by-step instructions: 47 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (14 of 14)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.