BC bgsub
BGsub — X-ray diffraction (SAXS/WAXS/XRD) background subtraction toolkit for 2D images and 1D curves. X射线衍射(SAXS/WAXS/XRD)数据背景扣除工具，覆盖2D图像处理和1D曲线处理。 Use this skill whenever the user's task involves ANY of the following, even if they don't explicitly mention "BGsub" or "background subtraction": 请在以下场景触发此 skill，即使用户未明确提及 "BGsub" 或 "背景扣除"： - "背景扣除", "background subtraction", "扣除背景", "去掉背景", "减背景" - "基线校正", "基线扣除", "基线拟合", "baseline correction", "baseline subtraction", "subtract background", "background estimation" - "SAXS", "WAXS", "XRD", "GIWAXS", "散射", "衍射", "小角散射背景扣除", "small-angle scattering background subtraction", "diffraction pattern" - "SSRF电离室", "电离室", "ionchamber", "ion chamber", "ionchamber file", "透射率校正", "透射率修正", "transmission correction", "transmission", "透过率", "T-背景", "T-background", "T修正", "T-correction" - "批量处理TIFF/EDF/H5文件", "batch process images", "batch background subtraction", "批量背景扣除", "格式转换", "图像格式转换", "file format conversion", "convert TIFF to EDF" - "PBS数据", "生物SAS", "biological SAS", "蛋白散射", "protein scattering", "生物样品散射" - "1D曲线处理", "1D curve processing", "曲线背景扣除", "XY曲线", "XY data", "积分曲线", "integrated curve", "curve smoothing", "基线拟合" - "形态学背景", "morphological background", "形态学", "多项式拟合", "polynomial fit", "滚球算法", "rolling ball" - User uploaded .Ionchamber files and needs X-ray data processing - User wants to subtract a known background image from signal images - User wants to estimate and subtract background from 1D diffraction curves - User mentions "T-背景", "T-background", "透射率修正", or asks how to correct for transmission in XRD data
As a process C 56/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency
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: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1588 chars, limit 1024 - note
description-budgetdescription takes 1588 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 56/100
- 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 (bgsub) differs from the folder (diffraction-scatter-background-substract)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 10 steps
- 100Execution cost. Instruction body is 2412 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)
- +3Description length 1587: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 38 example trigger phrases
- +4Structure: 20 headings
- +3Step-by-step instructions: 10 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 7 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.