AC teacher-grading-pipeline
Design or implement a bilingual lightweight teacher grading pipeline for K12 paper exams and homework. Use when the user discusses or asks to build workflows involving scanners, document cameras, mobile scanning apps, RFID/QR divider pages, teacher-provided answer keys, AI OCR/vision APIs, dual-provider verification, local deterministic scoring, teacher/student memory archives, Excel/Web/PDF reports, printable feedback, or HermesDesktop/OpenClaw skills for grading, marking, reviewing, exam analysis, wrong-question collection, and class learning analytics. 设计或实现中小学纸质试卷/作业批改流水线：高拍仪/扫描仪/手机扫描、RFID/二维码分隔页、教师标准答案、大厂 OCR/视觉接口、双接口校验、本地判分、教师与学生记忆库、成绩表、Web 可视化、PDF 打印报告、错题归集和班级学情分析。
Design or implement a bilingual lightweight teacher grading pipeline for K12 paper exams and homework.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 60/100
- 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. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (teacher-grading-pipeline) differs from the folder (u-autoclaw-teacher-grading-pipeline)
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 84 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2199 tokens
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 680: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 84 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.