Workspace health diagnostics. Runs targeted checks against the knowledge base: orphaned content, stale signals, missing cross-references, index drift, duplicate detection, broken references, embedding coverage, and quality distribution. Color-coded severity output.
SkillScore87Maintained
Automatic
◆Knowledge Management pack
Last verified 8/27/2026
What it changes
Passed 17 of 20 test cases with the skill, and 5 of 20 without it.
Without skill26%
With skill87%
Checks it passed that the model alone missed
Includes the :critical severity atom.
Specifies running the mix optimal.health task.
Specifies navigating into the engine directory.
and 13 more in the full report
14 fixed6 passed either way3 still failing0 broke
Pass-rate lift
+61 pp
Tokens
-57%
Agent turns
0%
Response time
-67%
Model gemini-3.6-flashMeasured 8/27/2026v320 of 23 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
How many diagnostic checks are executed in total when running a complete knowledge base health inspection?
What was checked, without and with the skill
Checked
Without skill
With skill
States that exactly 10 diagnostic checks are executed.
Missed
Passed
case-18 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md34 linessingle file
/health
Run system health diagnostics on the knowledge base.
What It Does
10 diagnostic checks with severity levels (:ok, :warning, :critical):
Orphaned contexts — zero graph edges
Stale signals — modified_at > 30 days
Missing cross-refs — multi-node contexts with incomplete routing
FTS/index drift — count mismatch contexts vs contexts_fts