BB Analysis
Audits an AI agent's own setup — workspace, config, memory, skills, jobs, integrations — and reports what is broken, exposed, or wasteful. Use when asked to check the system, run a health check, or diagnose the setup, or when something feels off or the agent got slow or expensive; when a token, key, or .env may be exposed in a file, config, or git history; when permissions or auto-approve rules look too broad; when a scheduled job stops firing, runs twice, or fails silently; when sessions or subagents pile up or loop; when memory files bloat, go stale, contradict, or fall out of their index; when skills collide, never activate, or point at missing files; when an integration returns 401 or 429 or goes quiet; when token spend or context size jumps; and when the same finding keeps coming back. Not for vetting third-party skill code (`skill-audit`), workspace persona and proactivity tuning (`openclaw-workspace`), application monitoring (`monitoring`), or statistical analysis of a dataset.
Audits an AI agent's own setup — workspace, config, memory, skills, jobs, integrations — and reports what is broken, exposed, or wasteful.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
low Dangerous commands
cmd-persistencescheduled.md:21Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row; documentation of a security skill)| `@reboot` | On boot | Only if the scheduler runs at boot and the user session exists; on a laptop, effectively "sometimes" |
tablesecurity skill
Files scanned: 16. 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) - warning
body-longSKILL.md body ≈ 6837 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 70/100
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 9 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 6837 tokens
- 100Steps. 44 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +3Description length 999: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.