AC ClawSpa
Agent wellness & maintenance suite. Memory cleanup, security scanning, prompt injection detection, alignment adjustment, skills auditing, and health diagnostics. Use when: user says /spa, /spa-quick, /spa-memory, /spa-security, /spa-health, /spa-align, 'run a spa session', 'agent maintenance', 'clean up my agent', 'memory cleanup', 'health check', 'scan my skills', 'context optimization', 'check alignment', 'instruction contradictions'. Local-first scans, optional cloud analysis on clawspa.org.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 11. 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 "url" - note
frontmatter-keyunknown frontmatter key "source"
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 800 tokens
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)
- +3Output format is not stated: the model decides each time
- -214 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 499: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (6 of 8)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.