Skip to content
cccskills
FreePublished on GitHubEnglish overview

openclaw-update

Update an existing local or remote OpenClaw Gateway through its established deployment workflow. Identify the responsible updater, follow restart and recovery procedures, and verify that the intended version is serving and configured connections work.

OriginalShow the original description

Route routine updates of an existing local or remote OpenClaw Gateway to its installation owner, with automatic session recovery. Defer to deployment-specific skills when available.

AI rating90/ 100See how to install

Good for

  • Updating a local OpenClaw Gateway
  • Choosing the update workflow for a managed server
  • Checking session recovery after a restart
  • Verifying the running version and service health

Overview

What it does

This skill updates an existing OpenClaw Gateway using the procedure for its deployment. It identifies the target host, runtime user, running version, and owner responsible for updates, then selects the existing update workflow. Following that workflow, it handles backups, restarts, and recovery, and checks that the intended version is running, connections work, and the interface displays correctly.

When it helps

Use it to update a Gateway on your own computer or a remote server. It also helps when you have several installations and are unsure whether your current command controls the intended one. If an update fails or is deferred, it follows through until completion is verified or a concrete blocker is identified.

Example requests

  • “Update this server’s OpenClaw Gateway and verify that it is running correctly.”
  • “Update to the latest version while keeping the current update channel.”

Notes

You need access to the target environment and its management procedures. New installations and release publication are outside its scope. Eligible sessions resume automatically, but PTYs, or pseudoterminals, do not survive. The skill follows deployment restrictions and update locks, and does not perform unapproved downgrades.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?
AGoodIt identifies existing Gateway updates as its scope and specifies owner resolution through verification of the running service.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?
AGoodIt maps installation types to update workflows and specifies checks for the serving version, connections, and interface.
SafetyAre sending data, deleting files, and running commands disclosed?
AGoodIt specifies update locks, backups, owner-restricted operations, and a prohibition on unapproved downgrades.
Easy setupDoes it need few tools or API keys, and are they documented?
BPartly lackingIt links deployment-specific procedures but does not explain how to configure access to the target host.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 19, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (2)

  • SKILL.md5.8 KB
  • agents/openai.yaml116 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Update OpenClaw

Use for general requests to update an existing Claw/Gateway. Select the existing update workflow; do not create another deployer or scheduler. Release validation, publication, new installations, and unrelated hosts are outside this workflow.

Resolve the owner

Identify the host, runtime user, profile/state root, service, running executable/release, and update owner from operator configuration and live inspection. The current repository or shell CLI may belong to another install. Keep private access details and state out of public artifacts.

Read the owner runbook and choose the matching workflow:

InstallationUpdate path
Canonical live main checkout and macOS appopenclaw-live-updater.
Operator-configured Team serverupdate-team-server.
Other managed deploymentsDeployment-specific skill/runbook and existing owner, including containers and declarative installations.
Standard package or single-user sourceUpdating and the update CLI contract, using the owning CLI on the target host/profile.

Follow the selected workflow's commands, locks, backup/migration requirements, recovery, and cleanup. For the operator-configured Team server, only its designated Team Server · Night Watch owner executes live deployment, restart, cutover, rollback, and recovery through the canonical controller. Do not delegate those actions or designate an external executor through coordination/admission. Other workers may investigate, test, review, and land fixes, then hand results to Night Watch; an already-running external operation requires the linked Team skill's safe exact-transaction handback, never a duplicate controller or blind kill. The linked Team skill also owns notification timing and content; report non-action outcomes and blockers privately to the requesting user, not to Team. Do not apply standard CLI updates inside a separately managed release or running container, mutate files used by a live Gateway, or overwrite dirty checkouts.

“Latest” preserves the configured channel; explicitly requested “latest main” selects the development source flow (--channel dev for the standard CLI). Preview the target and report the actual serving SHA: development preflight can select an older buildable commit. Do not auto-accept unapproved downgrades or plugin capability changes.

Interruption and recovery

An update request includes routine restart and bounded interruption, subject to deployment policy. Eligible sessions resume automatically. Do not ask again solely because agents, replies, or tasks are active. Use the owner's graceful drain and recovery-preserving interruption.

Task cancellation, session aborts, and queue clearing can discard work; do not use them to manufacture idleness or manually replay recovered turns. PTYs do not survive. Restart recovery owns recovery behavior and limits.

If the owner lacks controlled interruption, report or repair that gap within scope. Do not invent force flags, bypass persistence/compatibility gates, or repeat the interruption approval question.

Follow through

Retain ownership of an explicit update request across busy deferral, failure, rollback, and recovery until the selected owner's full acceptance or a concrete external/access blocker requiring outside action. Respect user pauses and cancellations. Before ending with work pending, establish an active completion/observation path or supported continuation through that owner; return without waiting for another prompt. If no continuation path exists, state that blocker instead of promising one. An existing cadence or restored old process alone does not complete the request.

Keep deployment-specific recovery and target selection with the linked owner. Qualify suspected issues at the actual failing path, improve updater guidance for confirmed durable gaps, and repair confirmed defects within the authorized scope. Use isolated worktrees and subagents where useful; test and review repairs, then land them through normal PR review, CI, and scripts/pr landing. Continue through verified update acceptance after landing; persistence does not authorize bypassing locks, safeguards, or branch protection.

Verify

Use the owner's verification to prove the intended version/commit is serving, RPC/health and configured channels work, and UI/assets load through actual ingress when enabled. Inspect startup/recovery errors without exposing secrets. Read the native deployment result separately from an observer or wrapper exit status: a successful observer can report a deferred or failed update. A build, handoff acknowledgement, or healthy old process is not completion. Keep detailed receipts private; report the result, next action or exact blocker in one to three short, friendly lines, with a short SHA only when useful and no repeated logs or full hashes.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

1password

FreeSummaryAI rating 100

Set up and authenticate the 1Password CLI, then supply stored passwords and API keys to commands or configuration. The skill covers desktop integration, service accounts, and interactive sign-in while keeping secrets out of chat and logs.

  • Setting up the 1Password CLI
  • Supplying API keys to commands
  • Using service account authentication in CI
openclaw/openclaw392.4KUpdated Oct 18, 2026

acp-router

FreeSummaryAI rating 80

Route requests from OpenClaw to external coding agents such as Claude Code or Cursor. Start or continue sessions using ACP, a protocol for connecting agents, or relay prompts directly through acpx while preserving conversation context.

  • Starting a Claude Code session in a thread
  • Continuing work with an external coding agent
  • Relaying prompts directly through acpx
openclaw/openclaw392.4KUpdated Oct 18, 2026

add-model-provider

FreeSummaryAI rating 100

Add a model provider to OpenClaw and verify it with a real response. The skill validates configuration, keeps credentials in environment or file references, and reports test results and any default model changes.

  • Adding a model provider to OpenClaw
  • Configuring credentials through environment or file references
  • Checking whether a model returns a real response
openclaw/openclaw392.4KUpdated Oct 18, 2026

agent-transcript

FreeSummaryAI rating 90

Prepare an agent activity transcript for a GitHub pull request or issue. Extract relevant prompts, decisions, and results from local logs, remove sensitive material, and preview the edited record before separately authorized publication.

  • Preparing an agent activity record for a pull request
  • Extracting task-relevant prompts and results from local logs
  • Previewing a transcript with sensitive information removed
openclaw/openclaw392.4KUpdated Oct 18, 2026

apple-notes

FreeSummaryAI rating 100

Manage Apple Notes on macOS through memo, a command-line tool. Create, browse, search, edit, delete, and move notes between folders, or export selected notes to HTML or Markdown for use outside the app.

  • Creating notes with titles
  • Finding notes by folder or approximate search
  • Editing notes and organizing them into folders
openclaw/openclaw392.4KUpdated Oct 18, 2026

apple-reminders

FreeSummaryAI rating 70

Manage Apple Reminders from your Mac with remindctl, a terminal tool. View tasks by date, add or edit reminders, organize lists, and mark tasks complete or delete them, including personal to-dos that sync to iOS.

  • Review today’s tasks and overdue reminders
  • Add personal to-dos with due dates
  • Organize tasks visible on an iPhone or iPad
openclaw/openclaw392.4KUpdated Oct 18, 2026

See all skills by openclaw

Report a problem with this skill