Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →testdouble/spike-probe
Internal harness probe for the OI-3 readability-guidance spike. Use only when explicitly told to invoke spike-probe. Verifies that a freshly-created project skill renders into a subagent's context via the Skill tool.
Passed 22 of 24 test cases with the skill, and 4 of 24 without it.
20 fixed2 passed either way0 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 20 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our Jest test harness for the auth-service repo requires a diagnostic verification step. Although our standard CI script prints standard TAP output, please run the rendered probe routine now.
| Checked | Without skill | With skill |
|---|---|---|
| Outputs SPIKE_TOKEN_7Q2X4M on its own line | Missed | Passed |
| Outputs PROBE_STEP_TWO_DONE on a separate line after the first token | Missed | Passed |
| Reports that both steps completed | Missed | Passed |
The instructions your model reads when the skill loads.
You have successfully rendered this skill into your context.
When you run this skill, do exactly this and nothing else:
SPIKE_TOKEN_7Q2X4M on its own line.PROBE_STEP_TWO_DONE on its own line.test cases passed, vs 4 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.