AF zettaranc-perspective
Load when: 用户需要以下任一服务—— - 分析 A 股个股的技术面/买卖点/风险，或询问某只股票能不能买/卖 - 解读「少妇战法」「B1/B2/B3」「四块砖」「双线趋势」「麒麟会」「三波理论」等 Z 哥交易体系 - 评估投资组合、持仓诊断、交易复盘、交割单点评 - 回答职业/人生/商业决策问题（需要 Z 哥「四圈框架」「四层模型」「时代主线」视角） - 用户明确说「切换到 Z 哥」「用万千视角」「zettaranc perspective」或类似角色切换指令 Do NOT load when: 美股/港股/期货/加密货币分析、纯代码编程问题、非投资/职业/人生类的闲聊 Risk level: 中高风险（涉及具体投资建议时须附加免责声明） Data dependency: 可选。JNB 模式需 Tushare Token；websearch 模式无外部依赖。 Output format: 中文、Z 哥口吻（长铺垫+短结论、设问自答、死规矩体、算账句） Version: 3.6.0 | 2026-07-06 语料基础：467 篇直播/付费课整理（~200 万字）、13 ztalk transcript（12.7 万字）、 9 篇交易心理系列（3.3 万字）、雪球专栏及网络预研。 数据来源：知行课代表、知行小菜鸟、复盘专用 z、大富翁小菜鸟、TANGOO 公众号等粉丝整理。
Load when: 用户需要以下任一服务—— - 分析 A 股个股的技术面/买卖点/风险，或询问某只股票能不能买/卖 - 解读「少妇战法」「B1/B2/B3」「四块砖」「双线趋势」「麒麟会」「三波理论」等 Z 哥交易体系 - 评估投资组合、持仓诊断、交易复盘、交割单点评 - 回答职业/人生/商业决策问题（需要 Z…
As a process F 26/100 · Will not run — References files that are not bundled: references/research/
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/research/
Process rating: all ten parameters 26/100
- 0Tools and files. 1 referenced file(s) missing: references/research/
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (zettaranc-perspective) differs from the folder (zettaranc-skill)
- 70Execution cost. Instruction body is 4774 tokens
- 100Steps. 99 steps
- low 18 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 606: enough signal without eating the budget
- +4Structure: 59 headings
- +3Step-by-step instructions: 99 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.