AB Anki
Builds and repairs Anki decks: card writing, FSRS and SM-2 deck options, leeches, review workload, imports, and sync. Use when making cards from notes, PDFs, lectures, textbooks, or vocabulary lists; when reviews pile up, take too long, or a backlog builds after time off; when retention drops, cards keep failing, or a deck falls into ease hell; when choosing FSRS vs SM-2, or setting desired retention, new cards per day, learning steps, and leech thresholds; when a deck asks to upload or download in a one-way sync, loses media, or fails Check Database; when importing CSV/TSV, an .apkg, or a shared deck, or migrating from Quizlet, Memrise, or SuperMemo; when cards are due but nothing appears; and when a fixed exam date forces a study plan. Covers language decks, medical and board decks, code and math material, and personal decks such as names and faces or poetry. Not for generic flashcard writing outside Anki, spaced-repetition algorithm theory, study-session planning, or add-on development.
As a process B 67/100 · Nearly there — weak spots: inputs and preconditions, running it twice, 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: 22. 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) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70Execution cost. Instruction body is 4723 tokens
- 100Tools and files. No external tools needed
- 100Steps. 49 steps
- 100Consistency. Name and required fields are in place
- 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 1004: 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: 76.