AB AgentTherapy
Use when an agent is stuck, uncertain, repeatedly wrong, corrected by the user, at risk of hallucinating, or outside its current ability range. Helps the agent fail honestly, recover calmly, offer fallback options, and adapt to the owner's correction style.
As a process B 76/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
How to improve
For the model run — optional
- 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: 3. 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)
Process rating: all ten parameters 76/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 22 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 886 tokens
- 100Running it twice. No mutating operations
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)
- +2Single-language instructions
- +3Description length 257: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 22 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.
External checks
ClawHub: clean
This is an instruction-only skill for helping an agent handle uncertainty and failures more honestly, with no executable code or hidden access requests.
LLM: benign (high) · VirusTotal: · 29 May 2026