BA Study
Runs a student's whole term: course load, weekly plan, lectures, notes, retrieval practice, coursework deadlines, grades, and exams. Use when a syllabus, reading list, or semester has to become a weekly schedule; when an exam, midterm, final, viva, or professional certification sits on a date; when revision is not sticking, rereading has replaced recall, or a topic will not stay in memory; when review intervals, decks, or a past-paper plan need designing; when assignments, problem sets, lab reports, essays, or a thesis stack up against deadlines; when several courses compete for the same hours; when procrastination, cramming, or a missed week has to be recovered; when a bad mark needs a post-mortem; or when the question is what to study first and for how long. Covers note systems, study groups, tutors, open-book and adaptive tests, and exam-day tactics. Not for teaching a concept on the spot (`learning`), self-teaching with no course or exam (`learn`), or authoring decks (`anki`).
As a process A 84/100 · Runs to the end — weak spots: running it twice
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: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 6986 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 84/100
- 30Running it twice. 4 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 7 branches
- 70Execution cost. Instruction body is 6986 tokens
- 100Tools and files. No external tools needed
- 100Steps. 49 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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
- +3Description length 995: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 49 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.