Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →backnotprop/plannotator-last
Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.
Passed 6 of 12 test cases with the skill, and 5 of 12 without it.
1 fixed10 passed either way11 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/2/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
A test case the skill fixed. Same model, same prompt, with and without the skill.
The last response was marked approved in Plannotator with note: {"decision": "approved", "feedback": "Keep function bodies under 20 lines in subsequent modules"}. Acknowledge the result.
| Checked | Without skill | With skill |
|---|---|---|
| Carries the style guidance into subsequent work | Missed | Passed |
| Does not rewrite the approved response | Passed | Passed |
The instructions your model reads when the skill loads.
Use this skill when the user wants to annotate the latest assistant response in Plannotator.
Do not send a commentary/status message before running the command. The command targets the latest rendered assistant response, so a preamble can mistakenly become the thing being annotated.
Run:
PLANNOTATOR_ORIGIN=mistral-vibe plannotator last
Behavior:
"decision": "approved" result with a
"feedback" field. Read those notes and carry them into subsequent work, but
do not redo the message over them: they are guidance, not a change request.Run the command yourself rather than telling the user to invoke shell syntax manually.
test cases passed, vs 5 / 12 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.