AB course-ta
Virtual course teaching assistant for Discord. Answers student questions using RAG over course materials (slides, PDFs, notes) placed in the workspace memory directory. Use when: (1) a Discord message asks a course-related question, (2) a student needs concept explanation or study guidance, (3) the professor wants to set up or update course materials. Responds in English by default, Chinese when the student writes in Chinese. Enforces strict course-scope boundaries — refuses off-topic, homework solutions, and grade inquiries.
As a process B 65/100 · Nearly there — weak spots: when it triggers, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6374 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6374 tokens
- 100Steps. 118 steps
- 100Failures and branches. 9 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (76 tags): a typed call is more reliable
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)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +3Description length 531: enough signal without eating the budget
- +4Structure: 41 headings
- +3Step-by-step instructions: 118 items
- +3Output format is stated explicitly
- +4Has examples (18 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.