Skip to main content

plannotator-last

Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.

Source facts

Repository
backnotprop/plannotator
Last source activity
October 28, 2026 at 00:50
Detected SKILL.md language
English
Stars
9,916
Forks
749

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

Showing SKILL.md

SKILL.md
Source instructions · Read-only preview
name
plannotator-last
description
Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.
disable-model-invocation
true
# Plannotator Last (Qwen Code) 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: ```bash plannotator last ``` Run it with the shell tool's `is_background: true`, and no trailing `&`. The command waits until the person finishes in the browser, which often takes longer than the shell tool's foreground limit (2 minutes by default, 10 at most); a foreground run would be stopped and the annotations lost. Then end your turn without stopping the task. When the task finishes, read its output (the tool result names the output file) and act on it. Behavior: 1. If feedback is returned, incorporate it into the follow-up response. 2. If the session closes without feedback (the output is empty, or a JSON object with `"decision": "dismissed"`), acknowledge it in one sentence and stop. Do not begin any work: closing the session is not approval. 3. An approval may still carry notes — a `"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.
View on GitHub