一键导入
immediate-update
Pull in updates from the parent branch to improve this Mind's skills, prompts, and configuration. Use only when prompted by the user.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Pull in updates from the parent branch to improve this Mind's skills, prompts, and configuration. Use only when prompted by the user.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Submit a bug report to libraries within the `mngr` project (eg, `mngr`, its plugins, `minds`, etc). Use to report bugs you encounter while running that seem to be issues with the `mngr` code itself, rather than with your own code or configuration.
Run commands to explore the current state of mngr and any relevant running agents. Use this skill when you need to debug issues with mngr tasks, or understand what tasks are currently running and their states.
Handle events from the mngr/agent_states source about sub-agent state transitions (finished, waiting, done, etc). You **MUST** use this skill (and *carefully follow the process in this doc*) whenever you receive a message from the "mngr/agent_states" source!
Clean up old agents, their output directories, and other historical data. Use during nightly cleanup or when the system has accumulated stale data.
Handle unexpected situations where the Minds system does not appear to be working as expected. Use when you encounter behavior that seems to contradict what your docs and prompts and skills say should happen, or when something seems broken and you are unsure how to proceed.
Create a sub-agent to perform a task. Use when you need to delegate work to another agent, for example, a working agent (for actually accomplishing some task) or a verifying agent (for deciding what to do about the output of a working agent).
| name | immediate-update |
| description | Pull in updates from the parent branch to improve this Mind's skills, prompts, and configuration. Use only when prompted by the user. |
This skill pulls changes from the parent repository (tracked in .parent) into this Mind.
This is how upstream improvements to skills, prompts, and configuration get incorporated.
PARENT_URL=$(git config --file .parent parent.url)
PARENT_BRANCH=$(git config --file .parent parent.branch)
PARENT_HASH=$(git config --file .parent parent.hash)
# Fetch the latest from the parent
git fetch "$PARENT_URL" "$PARENT_BRANCH"
# Check if there are new commits
NEW_HASH=$(git rev-parse FETCH_HEAD)
if [ "$NEW_HASH" = "$PARENT_HASH" ]; then
echo "Already up to date."
exit 0
fi
# See what changed
git log --oneline "$PARENT_HASH".."$NEW_HASH"
If there are no new commits, there is nothing to do.
git merge FETCH_HEAD --no-edit
If the merge succeeds cleanly, skip to Step 4.
If there are conflicts, they will typically be in files you have locally modified (e.g., memories, customized skills, configuration).
For each conflicted file, decide:
git checkout --theirs <file>)git checkout --ours <file>)After resolving all conflicts:
git add .
git commit --no-edit
git config --file .parent parent.hash "$NEW_HASH"
git add .parent
git commit -m "Update parent hash to $NEW_HASH"
After merging, check if thinking/onboarding.md has any new unchecked items.
If so, create tickets for them (see handle-mind-onboarding).
Post to the Work Log:
Pulled updates from parent ($PARENT_BRANCH): <N> new commits merged. Most important changes: <describe>
Also post to the conversation where the user asked for the update, and be sure to include:
start_of_day should remind the user that they pulled updates and reference back to the conversation where they asked for it, so they can review the changes if they haven't already.