Audit and safely repair cross-runtime Skill ownership, loading, duplication, scopes, budgets, lifecycle, quarantine, and retirement. Usage statistics alone belong to skill-usage-stats.
SkillScore78Maintained
Automatic
◆AI Engineer pack
Last verified 8/27/2026
What it changes
Passed 15 of 19 test cases with the skill, and 6 of 19 without it.
Without skill30%
With skill78%
Checks it passed that the model alone missed
Requires a zero-link reconciliation plan
Quarantines legacy skill files before removal
Records original file paths prior to deletion
and 13 more in the full report
12 fixed6 passed either way4 still failing1 broke
Pass-rate lift
+48 pp
Tokens
+76%
Agent turns
0%
Response time
-46%
Model gemini-3.6-flashMeasured 8/27/2026v218 of 23 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
We are setting up a strict release gate audit script for our skill repository where any governance warnings must immediately fail the build. Which CLI flag enforces this strict behavior in the ecosystem doctor?
What was checked, without and with the skill
Checked
Without skill
With skill
Passes the --fail-on-warn flag to ecosystem_doctor.py
Missed
Passed
case-16 · 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.md249 lines18 filesincludes scripts
Skill Ecosystem Doctor
Treat the local Skill collection as a governed software supply chain. Audit first,
plan repairs from evidence, apply only authorized changes, and finish with fresh
cross-runtime verification and a durable handoff.
This workflow is at skill maturity, not unattended automation maturity. Do
not schedule or silently apply repairs.
Trigger boundary
Questions such as “Did Studio load or start these Skills?” belong to Studio's
own configuration, projections, and runtime inventory. Inspect that
project/runtime directly. Invoke this Doctor only when the user explicitly asks
for cross-runtime or cross-scope ownership, projection, exposure, lifecycle, or
repair governance.
Select the mode
User intent
Mode
Routing
Inspect, review, inventory, or diagnose
audit
execute_direct; read-only
Explain what should change
plan
plan_first; no mutations
Fix, unify, quarantine, or retire
repair
plan_first; explicit scope and rollback
Recheck an existing governance file
verify
execute_direct; read-only
Rotate credentials, rewrite history, push, publish, or change remotes
external action
clarify_first unless the current request grants that exact action
If the request mixes modes, run audit before repair. Do not infer repair
authorization from a request to inspect or diagnose.
Operating Contract
Direct actions: read-only discovery, deterministic audits, report drafts,
and local validation.
Escalate before: destructive changes, credential actions, history
rewriting, remote publication, or any mutation not named by the current
repair request.
Evidence-backed pushback: challenge a proposed source, deletion, or
completion claim only with paths, state queries, tests, ownership records, or
a concrete data-loss or security risk.