AC lexi
Filesystem librarian for OpenClaw environments. Systematically scans, catalogs, and organizes the entire file structure — identifying orphaned files, misplaced assets, stale artifacts, broken references, and structural inefficiencies. Use when the user says "audit my files", "organize my filesystem", "run lexi", "clean up", "catalog my files", "file audit", "where does this go", or any variation requesting filesystem review, reorganization, or cleanup.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Dangerous commands
cmd-cron-mentionscanning-framework.md:139Mentions editing / listing crontab (documentation table row; documentation of a security skill)| **Cron paths** | `crontab -l` | Command strings |
tablesecurity skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 85Steps. 119 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2396 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 456: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 119 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.