AC elliott-wave
当用户要数艾略特波浪（数浪/第几浪，五浪上升/三浪下跌）、判断延长浪、用菲波纳奇比例（38.2%/50%/61.8%）测回撤与 目标，或应用 4 浪不重叠/交替规则/调整浪三浪等数浪约束时激活。 不适用于：时间周期择时（转 time-cycles）、头肩/双顶形态（转 reversal-patterns）。 关键 trigger 词：数浪、第几浪、浪型、艾略特、五浪三浪、延长浪、菲波纳奇、浪 1-5、调整浪、1.618。 Activate when the user wants to count Elliott waves (wave counting / which wave, five-up/three-down), identify extension waves, use Fibonacci ratios (38.2%/50%/61.8%) for retracement and targets, or apply counting constraints such as "wave 4 does not overlap", alternation, and "correction is three waves". Not applicable: time-cycle timing (-> time-cycles), head-and-shoulders / double-top (-> reversal-patterns). Key trigger words: wave count, Elliott, five-three waves, extension, Fibonacci, waves 1-5, corrective wave, 1.618.
当用户要数艾略特波浪（数浪/第几浪，五浪上升/三浪下跌）、判断延长浪、用菲波纳奇比例（38.2%/50%/61.8%）测回撤与 目标，或应用 4 浪不重叠/交替规则/调整浪三浪等数浪约束时激活。 不适用于：时间周期择时（转 time-cycles）、头肩/双顶形态（转 reversal-patterns）。 关键…
As a process C 55/100 · 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 55/100
- 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
- 40Consistency. Frontmatter name (elliott-wave) differs from the folder (elliott-wave-2)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 52 steps
- 100Execution cost. Instruction body is 654 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 743: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 52 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.