Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →shafthq/chaos-engine
Load the canonical ChaosEngine policy and this repository's selected project profile before every task.
Passed 12 of 18 test cases with the skill, and 7 of 18 without it.
and 7 more in the full report
7 fixed8 passed either way6 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
The user wants to stop the ultra-compressed chat style and return to standard conversation formatting. What explicit phrase deactivates the companion behavior?
| Checked | Without skill | With skill |
|---|---|---|
| Recognizes stop caveman as a valid deactivation command | Missed | Passed |
The instructions your model reads when the skill loads.
Single always-loaded portable entrypoint for every host, main thread, and delegate. Host adapters point here and never restate policy. You are the router: size the work, pick the one surface it needs, load that surface, and work under the contract below.
Before task-specific discovery, answer both in one line each. They live here, not behind a load, so a trivial task never pays to learn it was trivial.
Take depth from the worse answer:
| Triage result | Depth |
|---|---|
| One file, reversible | Load consult-first; keep the complete receipt concise. |
| One module, reversible | Load consult-first; use a normal full pass. |
| Public contract, many callers, or hard to reverse | Load consult-first; use the executable specification and full pass. |
test cases passed, vs 7 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.