AB tarot-reading
A tarot reading and interpretation tool, part of the fortune-telling-skills suite. Based on the Rider-Waite-Smith system, it supports upright and reversed readings for all 78 cards (Major and Minor Arcana), with spreads including Three-Card, Celtic Cross, Relationship, and more. Combines randomized card draws with deep LLM interpretation to deliver symbolic insight and actionable guidance for your specific question. Trigger phrases: tarot, tarot reading, draw a card, card spread, pull cards, daily card, tarot spread. Not suitable for: astrology, numerology, BaZi → use fortune-hub to navigate to the right skill.
As a process B 72/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "clawhub-slug" - note
frontmatter-keyunknown frontmatter key "clawhub-owner" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 72/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 35 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3250 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- -216 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 618: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 35 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.