AB skill-picker
Discovers and recommends the best agent skills based on user intent — not just keywords. Activates when users ask "how do I do X", "find a skill for X", "is there a skill that...", or whenever a task would benefit from a specialized skill. Also activates proactively when the agent detects repeated manual tasks, workflow gaps, or missing capabilities mid-conversation. Supports English and Chinese. Recommends skill combinations, not just single skills. This skill only suggests install commands — it never executes installs autonomously. All installs require explicit user confirmation.
As a process B 72/100 · 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "tools" - note
frontmatter-keyunknown frontmatter key "binaries"
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
- 30Running it twice. 1 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2434 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 588: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 25 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.