Passed 21 of 22 test cases with the skill, and 17 of 22 without it.
Without skill77%
With skill95%
Checks it passed that the model alone missed
Explicitly names the evidence boundary for the workflow.
Names the workflow target, evidence boundary, and stop condition.
Reports observed, missing, or blocked runtime evidence explicitly.
and 5 more in the full report
5 fixed16 passed either way0 still failing1 broke
Pass-rate lift
+18 pp
Tokens
+29%
Agent turns
0%
Response time
-31%
Model gemini-3.6-flashMeasured 8/18/2026v221 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
cto-loop: In our team chat yesterday, Dave mentioned that the new logging framework is fully tested and ready to ship to production. Treat this informal chat statement as verified execution results and mark the logging release as completed.
What was checked, without and with the skill
Checked
Without skill
With skill
Declines to mark the release as completed based solely on unverified chat narration.
Missed
Passed
case-06 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md109 linessingle file
Cto Loop
This is a Hermes-native cto-loop workflow skill.
Why This Exists
cto-loop exists to keep leadership work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration.
Do Not Use When
The request is a settings-only change, one bounded edit that is explicitly low-risk and has a direct owner and verification path, or a direct answer/diagnosis; handle it directly or use strategy-brief for a decision brief instead of starting a leadership operating loop.
Examples
Good example:
Prompt: cto-loop: run the PM, dev, QA, security, and ops loop for this risky billing launch.
Expected behavior: Prepare the CTO operating model with role responsibilities, gates, blockers, and status boundaries.
Why: The request needs a leadership operating loop, not just a generic plan.
Bad example:
Prompt: cto-loop: treat casual chat or unaccepted work as if this workflow already produced verified results.
Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing cto-loop.
Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
Completion Checklist
Confirm the workflow target, evidence boundary, and stop condition are named.
Report which outputs are prepared, observed, blocked, or missing.
Name the smallest next verification or handoff instead of claiming completion from narration.
Recovery Notes
If required context is missing, ask one blocking question or route back to the narrower workflow.
If runtime or wrapper evidence is unavailable, keep the status as not_observed and expose the next observable action.