AB grade-english-homework
Standardized grading and feedback prompt for grading elementary school English written homework (grades 3-6). Use when the user asks to check, grade, correct, review, or mark English homework, writing assignments, compositions, fill-in-the-blank, sentence rewriting, translation, or any written English exercises from Chinese primary school students in grades 3 through 6. Triggers on phrases like '批改英语作业', '改英语作文', 'check English homework', 'grade English writing', '批改作业', '英语书面作业批改', '小学英语批改', '改错', 'check my English'.
Standardized grading and feedback prompt for grading elementary school English written homework (grades 3-6).
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, progress reporting
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: 0. 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 66/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 13 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1159 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 523: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 13 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.