DevOps skills

Configure a software delivery workflow that turns selected feedback and maintenance signals into verified, reviewed changes. Define information sources, schedules, working directories, and separate permissions for actions such as implementation, merging, deployment, and notifications.

• Choose connected sources for feedback and maintenance signals
• Set separate permissions for implementation, merging, and deployment
• Configure supported schedules, worktrees, and notifications

Monitor explicitly authorized software delivery tasks, verify which work has stopped, and send reminders only when a concrete next step is due and the configured notification policy allows it.

• Find stalled delivery tasks during scheduled checks
• Verify the current state of a task's pull request or worktree
• Send permitted reminders without repeating unchanged notices

An experimental workflow for delivering software changes through configured checks, pull requests, review updates, and merge verification. It follows project permissions and release conditions, and reports missing evidence or checks before treating delivery as complete.

• Publishing verified changes through a pull request
• Updating code after review feedback
• Checking merge conditions before release

Check the beta connection address for a bb instance and turn that connection on or off. Inspect connection states and shared port URLs, including ports exposed from other enrolled machines.

• Find the beta connection URL for a bb instance
• Turn the beta connection on or off
• Check connection errors and offline states

Inspect and adjust how many BB threads can run at once, globally or on a specific host. Pause new work with a zero limit, remove the global cap, or restore processor-based automatic host limits.

• Inspect current thread concurrency limits
• Set a global limit on simultaneous work
• Adjust the limit for a specific host

Inspect automatic retries for failed Codex and Claude Code turns in bb after provider overloads or subscription usage windows. Check pending retry times and recorded decisions, send a scheduled retry immediately, or cancel it.

• Check retry schedules after provider overloads
• Find out why a retry was scheduled or skipped
• Run a pending retry immediately

Set up reusable cloud machines on Modal from BB, customize their base image, and manage pause and resume operations. The skill also covers connection checks, project setup, filesystem snapshots, and separate sandboxes for testing image changes.

• Create a cloud development machine from BB
• Customize and test a development image
• Pause a machine and resume from saved files

Share a local HTTP server through BB Connect so it can be opened remotely with the owner's getbb.app session. Check access status, provide the share link, and remove shared ports when finished.

• Open a local web app from another device
• Check BB Connect remote access status
• Remove a share after stopping a server

Manage the getbb.app account linked to a bb server. Check which account remote access and hosted services use, sign in through a browser or pairing code, and sign out to revoke the server's credential.

• Check which account a bb server uses
• Sign in through a browser or pairing code
• Switch the account linked to a bb server

Configure and diagnose Account Pooler in BB, including accounts, authentication, quota-based routing, and failover, which switches to another account. Inspect account and routing state, plus Provider Retry decisions after pooled rate-limit failures.

• Inspect registered accounts and routing state
• Configure account login or credential import
• Investigate quota routing and account failover

Recover missed Observal session deliveries, upgrade or downgrade the command-line tool, and roll back version changes. After specified connection or configuration failures, it can also create local Agent files when explicitly requested.

• Recover missed session deliveries
• Upgrade or downgrade the CLI
• Roll back a CLI version change

Administer Observal users, settings, submission reviews, identity configuration, and security investigations. Also manage local server upgrades, rollback, and database schema migrations, checking the resulting state and protecting sensitive values throughout privileged operations.

• Managing users, permissions, and submission reviews
• Configuring SAML sign-in and SCIM user provisioning
• Investigating security events and audit logs

Manage Observal maintainer releases, from creating release branches and backporting fixes to preparing preview and stable versions. Follow the existing release workflow to verify published artifacts, inspect release status, and recover interrupted or failed operations.

• Creating a new release branch
• Backporting merged fixes to maintained versions
• Preparing alpha, beta, RC, and stable releases

Inspect Agent activity in Observal through execution records, sessions, ratings, logs, and insight reports. Use the evidence to investigate telemetry problems, costs, and performance regressions, then identify practical next steps while accounting for limited data.

• Reviewing recent Agent activity
• Diagnosing missing telemetry
• Investigating costs and performance regressions

Prepare software releases by detecting version files, reviewing changes, and writing changelogs in multiple languages. The workflow updates versions, creates annotated tags with release notes, and can publish GitHub Releases or fill in missing historical releases.

• Preparing a new version from recent changes
• Updating changelogs in multiple languages
• Previewing release changes without modifying files

Start the interactive Claude Octopus setup wizard to install and authenticate providers, configure RTK token optimization, choose a work mode, and complete onboarding. This skill directs configuration requests to the existing setup process.

• Setting up Claude Octopus for the first time
• Installing and authenticating providers
• Configuring RTK token optimization

Check which AI providers Octopus can use before running a workflow. Get a compact table of availability, authentication, selected models, and billing categories, followed by prioritized fixes for detected problems.

• Check available AI providers on a new machine
• Investigate a provider skipped by a workflow
• Review authentication and version problems

Diagnose Claude Octopus installation and runtime problems across 15 categories, including provider authentication, configuration, hooks, and scheduling. Get a readable or JSON report, investigate specific areas, and review proposed fixes before approving changes.

• Checking the environment after a plugin update
• Investigating provider authentication problems
• Verifying hooks and scheduled jobs before a demo

Estimate remaining workflow costs from the average spend of completed steps. Show actual spending and projected totals in the status line, warn about configured budget overruns, and suggest a budget profile when estimated costs are high.

• Estimating remaining costs during a workflow
• Checking whether projected spending exceeds a budget
• Displaying spending and estimates in the status line

Publish saved skill and global AGENTS.md changes to a private repository, then check the automated public mirror. The workflow isolates intended edits, preserves unrelated work, and verifies the actual published content.

• Publishing changes to existing skills
• Syncing global AGENTS.md instructions
• Publishing while unrelated local edits are present

Set up and manage automatic Git syncing for shared documents, notes, and skills on macOS. The skill guides repository registration, removal, service checks, and maintenance, with local changes automatically committed and pushed by repo-sync.

• Setting up automatic syncing for shared team notes
• Adding or removing a repository from automatic syncing
• Checking sync failures and maintaining the background service

Manage local development servers and APIs with macOS LaunchAgents, which run background processes. Keep servers running after the shell closes, restart them after crashes, inspect logs, and handle occupied ports when starting a service.

• Keeping a local server running after closing the shell
• Restarting a server automatically after a crash
• Checking server status and logs

Create and manage Boat cloud sandboxes, remote machines for development work, through API, CLI, or SSH. Configure repositories and secrets, prepare reusable templates, manage machine state, and verify coding agents inside the selected environment.

• Create a cloud workspace for a coding agent
• Configure repositories and secrets
• Reuse prepared environments through templates

Prepare read-only PostgreSQL access for AI agents, including SQL files, protected connection settings, and checks that writes and sensitive-table reads fail. A human applies production database changes and agrees which tables agents must not access.

• Prepare a read-only database account for agents
• Exclude tables containing secrets or personal data
• Verify that writes and restricted reads are blocked