AB keepmyclaw
OpenClaw backup and restore. Encrypted off-site backup for OpenClaw agents — backs up workspace, memory, skills, cron jobs, credentials, and multi-agent configs to Cloudflare R2 with zero-knowledge AES-256 encryption. Use when backing up an OpenClaw agent, restoring an agent on a new machine, setting up automated backup schedules, listing or pruning backup snapshots, running restore drills, or migrating agents between machines. Triggers on: backup, restore, openclaw backup, agent backup, snapshot, disaster recovery, keepmyclaw, migrate agent, backup schedule, encrypted backup.
As a process B 66/100 · Nearly there — weak spots: result and completion, running it twice
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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: OpenClaw backup and restore. Encrypted off-site backup for OpenCla… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 4 branches
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2275 tokens
- 100Progress reporting. Reports progress
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
- +1No license
- +2Single-language instructions
- +3Description length 583: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (13 code blocks)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.