AC wickworks
Stateless OHLC primitives service — candlestick bars in, technical indicators + Smart-Money-Concepts objects out. Single POST / takes a bars array + an indicators selection map and returns computed primitives; GET /metadata is the output-path catalog; GET /health. 67 primitives across trend (SMA/EMA + 15 more MAs, slope, Donchian, Ichimoku), momentum (RSI, MACD, Stoch, StochRSI, ADX, MFI, CCI, Williams %R, ROC, MOM, TSI, TRIX, UO, Fisher), volatility (ATR, NATR, Bollinger, Keltner, Squeeze), volume (VWAP, VWMA, OBV, AD, ADOSC, CMF, KVO), and SMC (order blocks, fair-value gaps, BOS/CHoCH, swing structure, S/R levels, liquidity, retracements, sessions, previous-period H/L) plus pre-baked summaries. camelCase, NaN-safe JSON. Unified REST + MCP (streamable-HTTP at /mcp — tools health / list_indicators / metadata / compute). Auth-less by default. Use when the user wants technical indicators or Smart-Money-Concepts primitives computed from OHLC candlestick bars.
Stateless OHLC primitives service — candlestick bars in, technical indicators + Smart-Money-Concepts objects out.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1982 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Description length 970: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Structure: 9 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.