Cloud, CI/CD, monitoring, and deployment (6.8K skills)
Update Bifrost Helm charts, the packages used to configure deployments, while keeping settings, schemas, templates, and documentation aligned. Check the published release and group changes into the next unreleased version.
Audit database migration changes before a Bifrost release for lock contention, deadlocks, and delayed application startup. Receive pass, warning, or failure results, a release recommendation, and concrete remediation steps without modifying files.
Helps investigate and modify Apache Beam's automated build and test workflows in GitHub Actions. Explains workflow types, failure logs, targeted reruns, local reproduction, and the cloud credentials needed for workflows that access GCP.
Collect operation events across an AI agent workflow and link them into traceable execution records. Search by tracking ID, time range, or responsible agent, with semantic indexing and local event storage to support audits and investigation.
Record operations across multiple AI agents and connect events into a traceable history. Search records by tracking ID, time window, or responsible component to support audits and investigations, with local storage available when the vector database fails.
Start and manage long-running background services such as development servers. Check their status and output logs, verify listening ports, retrieve local URLs, and restart services while keeping the same service ID.
Find workspaces on remote nodes, inspect their details, browse folders, and read or write files. Supports text files and binary content, such as images, through base64 encoding, a text representation of binary data.
Find user-configured API keys and tokens by listing their names and descriptions, then retrieve a chosen value for scripts. Helps use credentials in API calls or authentication without embedding them directly in code.
Check the health of the HashiCorp Vault instance in an OpenRig environment and manage stored secrets. Use its API to write, read, list, or delete entries and explain how secret paths are organized.
Coordinate with OpenRig agents on registered remote machines using SSH or HTTP connections. Select the intended host, inspect agent state, send messages, and interpret failures while checking whether remote actions actually took effect.
Plan and verify OpenRig startup, shutdown, and recovery. Compare reported status with actual running sessions, distinguish recovery outcomes, and define reboot tests that expose partial failures instead of hiding them behind a fresh launch.
Package an OpenRig agent arrangement and workflow for reuse by others. Guides bundle creation, inspection before installation, and checks in a clean environment to identify hidden dependencies on local paths, providers, or credentials.
Change a running OpenRig setup by adding or removing agent seats, connecting existing sessions, or attaching terminals. Guides checks for roles, startup context, permissions, and session identity so the setup reflects each change correctly.
Configure selected OpenRig command permissions in Claude Code or Codex at the agreed project or user scope. Preserve existing restrictions, verify that settings load and behave as intended, and record additions so they can be removed later.
Configure a new OpenRig agent seat, a managed place for an agent to run, using a prior Claude or Codex conversation. Covers fork settings, new session identities, and checks that distinguish forking from restoring.
Monitor other agent teams for abandoned work, process drift, off-task activity, and excessive token use. It guides evidence checks after alerts and chooses a proportionate response, from notifying the team’s coordinator to escalating to a human.
Guide OpenRig CLI and background service upgrades while protecting active sessions and local file changes. The skill provides staged checks, verified database backups, selective plugin refreshes, and migration helpers, with evidence checked after each change.
Opens groups of OpenRig agent terminals as live herdr tiles for interaction or observation. Explains view selection, read-only access, saved groups, and how to interpret agents that are offline or cannot be displayed.
Create an isolated development container configured for Claude Code and the project's languages. Generate container files, editor settings, dependency setup commands, and persistent storage for Python, Node/TypeScript, Rust, and Go projects.
Analyze agent runs that fail before any work begins. Check iteration counts, tool use, logs, and outputs to identify startup failures, then direct investigation toward environment setup, input formatting, permissions, or resource limits.
Diagnose connection problems with government websites by checking SSL certificates, which verify website identity, and proxy settings. Follow structured troubleshooting steps, record failed attempts, and explore alternative APIs or data sources when access remains blocked.
Troubleshoot access to government and institutional websites by checking connectivity, SSL certificates, and proxy settings. Follow a structured process to test request options, configure retries, and identify alternative data sources when access fails.
Diagnose failed connections to government websites and corporate portals by checking network access, SSL certificates, and proxy settings. If access remains unavailable, the workflow helps identify alternative data sources and document attempts and next steps.
Analyze agent runs that fail before any work begins. By checking execution counts, tool calls, outputs, and conversation logs, this skill classifies startup failures and directs investigation toward system setup, resources, or input processing.