AC oscillators-contrarian
当用户问摆动指数（RSI/KD/%R/MACD/ROC/动力指数）的超买超卖、背离，或相反意见理论（看涨一致数字、 COT 持仓报告、看跌/看涨期权比）的情绪极端信号，并需要理解"趋势市 vs 横盘市用法相反"时激活。 不适用于：趋势方向/均线交叉（转 moving-averages）、画趋势线（转 trend-tools）。 关键 trigger 词：RSI 超买超卖、KD 金叉死叉、MACD 背离、%R、相反意见、看涨一致数字、市场情绪、COT。 Activate when the user asks about oscillator (RSI/KD/%R/MACD/ROC/momentum) overbought/oversold and divergences, or contrary-opinion theory (bullish consensus, COT report, put/call ratio) sentiment extremes, and needs to understand that "usage in trending vs range-bound markets is opposite". Not applicable: trend direction / MA cross (-> moving-averages), drawing trendlines (-> trend-tools). Key trigger words: RSI overbought/oversold, KD cross, MACD divergence, %R, contrary opinion, bullish consensus, market sentiment, COT.
当用户问摆动指数（RSI/KD/%R/MACD/ROC/动力指数）的超买超卖、背离，或相反意见理论（看涨一致数字、 COT 持仓报告、看跌/看涨期权比）的情绪极端信号，并需要理解"趋势市 vs 横盘市用法相反"时激活。 不适用于：趋势方向/均线交叉（转 moving-averages）、画趋势线（转…
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "source_book" - note
frontmatter-keyunknown frontmatter key "source_chapter" - note
frontmatter-keyunknown frontmatter key "related_skills"
Process rating: all ten parameters 59/100
- 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
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 47 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 685 tokens
- 100Running it twice. No mutating operations
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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 757: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 47 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.