AC course
PKU Teaching Platform (北大教学网/Blackboard Learn) CLI tool built in Rust. Use this skill when working on the course crate, debugging course commands, adding features to the teaching platform CLI, or when the user mentions 教学网, Blackboard, course downloads, assignment submission, video downloads, or PKU teaching. Also use when dealing with HTML scraping via the scraper crate, Blackboard SSO callback, or multipart file uploads. **NOT for course schedule / 课表 / weekly timetable questions — for those use the `treehole` skill (`treehole course`), which is the canonical source and includes 辅修/双学位.** This `course` crate only deals with the Blackboard teaching platform (assignments, files, recordings, announcements).
As a process C 51/100 · 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: 2. 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 51/100
- 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 (course) differs from the folder (pku-course)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 16 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 477 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 715: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.