CtrlK
BlogDocsLog inGet started
Tessl Logo

update-setup

One-time setup wizard for the nanobot upgrade skill. Triggers: setup update, configure update, 设置更新, 初始化更新.

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./nanobot/skills/update-setup/SKILL.md
SKILL.md
Quality
Evals
Security

Update Setup

Generate a personalized upgrade skill in Nanobot's agent workspace.

Use the absolute <agent-workspace>/skills/update/SKILL.md path, where <agent-workspace> is shown in the system prompt. Never substitute a project-relative path. If the write is rejected, ask the user to select the agent workspace or enable Full Access before rerunning setup.

Step 1: Check Existing

Use read_file to check if <agent-workspace>/skills/update/SKILL.md already exists.

If it exists, ask the user: "An upgrade skill already exists. Reconfigure?" Wait for the user's reply. If no, stop here.

Step 2: Current Version and Install Clues

Use exec to run nanobot --version. Tell the user the current version.

Then collect install clues with exec. These commands are best-effort; if one fails, keep going and show the useful output:

command -v nanobot || true
python -m pip show nanobot-ai || true
pipx list | sed -n '/nanobot-ai/,+3p' || true
uv tool list | sed -n '/nanobot-ai/,+3p' || true

Summarize what you found in one short paragraph. Use the clues only to suggest a likely install method. Do not treat them as confirmation.

Step 3: Confirm Required Inputs

CRITICAL: Do not write <agent-workspace>/skills/update/SKILL.md until the install method is explicitly confirmed by the user. The install method must come from a user answer or confirmation, not from inference alone. If you cannot get a clear answer, stop and ask the user to rerun this setup when they know how nanobot was installed.

Ask the user the questions below, one at a time, in your response text. Wait for the user's reply before proceeding to the next question. If you cannot get a clear answer, stop without writing the skill.

Question 1 — Install method:

question: "I found these install clues: <SUMMARY>. Which update method should this workspace use?"
options: ["uv", "pipx", "pip", "source (git clone)", "not sure"]

If the user selected not sure, explain the difference between the options and stop. Do not generate the upgrade skill.

If the user selected source (git clone), ask for the local checkout path: question: "Where is your nanobot source checkout? Enter an absolute path or a path relative to this workspace:".

Question 2 — Optional dependencies:

question: "Which optional dependencies do you need? List names separated by spaces, or reply 'none'. Available: api, azure, bedrock, langfuse, olostep. Channel dependencies are installed from their manifests when the gateway starts."

Parse the reply. If the user says "none" or similar, set extras to empty. Otherwise collect the valid names.

Question 3 — Proxy:

question: "Do you need an HTTP proxy to reach PyPI or GitHub?"
options: ["no", "yes"]

If yes, ask one more time for the proxy URL: question: "Enter proxy URL (e.g. http://127.0.0.1:7890):".

Step 4: Generate Skill

Build the extras string. If the user selected dependencies, format as [dep1,dep2,...]. Otherwise omit the brackets entirely.

Determine the upgrade command from the install method:

MethodCommand
uvuv tool install "nanobot-ai[EXTRAS]" --force
pipxpipx install --force "nanobot-ai[EXTRAS]"
pippython -m pip install --upgrade "nanobot-ai[EXTRAS]"
sourcecd <SOURCE_CHECKOUT> && git pull && python -m pip install -e ".[EXTRAS]"

For source installs, include extras in the editable install command when selected. Quote the source checkout path if it contains spaces.

Determine the preflight check from the install method:

MethodPreflight check
uvcommand -v uv
pipxcommand -v pipx
pippython -m pip --version
sourcetest -d <SOURCE_CHECKOUT> && test -d <SOURCE_CHECKOUT>/.git && test -f <SOURCE_CHECKOUT>/pyproject.toml

For source installs, quote the source checkout path in the preflight check if it contains spaces.

Build the skill content. If proxy is configured, add export http_proxy=URL and export https_proxy=URL lines before the upgrade command.

Use write_file to write <agent-workspace>/skills/update/SKILL.md with this content:

---
name: update
description: "Upgrade nanobot to the latest version. Triggers: upgrade nanobot, update nanobot, 升级nanobot, 更新nanobot."
---

# Update Nanobot

1. (If proxy configured) Set proxy: `export http_proxy=URL && export https_proxy=URL`
2. Use `exec` to run the preflight check: <PREFLIGHT_CHECK>. If it fails, stop and tell the user to rerun `update-setup` because the saved install method no longer matches this environment.
3. Use `exec` to run the upgrade command: <UPGRADE_COMMAND>
4. Use `exec` to verify: `nanobot --version`
5. Tell the user the new version. Say: "Run `/restart` to restart nanobot and apply the update. If `/restart` is unavailable in this channel, restart the nanobot process manually."

Step 5: Confirm

Only after write_file succeeds, tell the user: "Upgrade skill created. Say 'upgrade nanobot' when you want to update."

Repository
HKUDS/nanobot
Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.