AI Agent Workflow Collection

Execute the six-phase breaking-change recovery workflow. Invoked from workflow-resilience Tier-3 escalation or manually when a merged commit breaks the runtime, schema, or governance pipeline.

Detect and remediate documentation drift after code, config, workflow, or UX changes. Use after implementation, before merge, and before release.

Analyze any fleet's inventory/devices.json and recommend optimal Ollama models per device based on hardware constraints, inference tier, and current LLM landscape. Generates pull/delete commands and a safe transition plan.

Adapt the Megingjord harness to a new operator's fleet topology without hand-editing inventory files. Use when first activating the harness on a new host or onboarding a new fleet.

Enforce secure GitHub Actions posture with least-privilege tokens, pinned dependencies, runner risk controls, and workflow supply-chain checks.

Resolve GitHub feature availability and policy constraints by plan, repo visibility, account type, and enabled settings before recommending governance actions.

Define and apply expert GitHub policy profiles and control catalogs used by specialized execution skills across ticketing, review/merge, governance, and release flows.

Route GitHub workflow requests through a capability-first GitHub skill tree with explicit ownership boundaries and minimal overlap.

Apply Agile linkage controls in GitHub using issue types, sub-issues, dependencies, issue-branch/PR linkage, project fields, and built-in automations.

Govern release readiness and incident response flow in GitHub with rollback evidence, hotfix linkage, and follow-up controls.

Enforce review and merge administration gates with required checks, approvals, conversation resolution, rulesets, and merge queue readiness.

Design and audit repository and organization ruleset architecture, including layering, bypass controls, enforcement modes, and merge queue compatibility.

Naming conventions and phase protocol for GitHub ticket lifecycle. Baton workflow in manager-ticket-lifecycle.

Initialize a repository so global skills are always loaded first through repository instructions, local hooks, and governance presence checks.

Classify tasks into free, fleet, or premium lanes and persist an escalation rationale for the active session.

Operate and maintain the LLM Wiki knowledge system in the Megingjord source workspace.

Operate an LLM Wiki knowledge system in any workspace using the Karpathy…

The GitHub issue IS the baton. Manager creates tickets, pre-assigns roles, enforces status transitions through the Agile workflow.

Operate and tune Crostini Mem Watchdog for low-memory development sessions. Use for status triage, log interpretation, and safe threshold tuning.

Inventory of all network-accessible compute platforms, connection methods, credentials, and specs. Load this skill when a task could benefit from remote execution, offloading, or cross-platform deployment.

Keep OpenClaw gateway highly available and actively used through mandatory preflight checks, execution routing, and failover controls.

Make OpenClaw a reusable machine-global execution system for all VS Code Copilot agent chats, regardless of repository, by standardizing routing, observability, and decision checkpoints.

Configure and maintain optimal OpenRouter free model failover for OpenClaw. Prioritized cascade of free models ranked by coding capability, with automatic failover on rate limits, downtime, and errors. Load this skill when configuring models, troubleshooting model availability, or refreshing the free model inventory.

Establishes the operator identity, access authority, and execution mandate for all agent sessions. Always load at session start. The agent is the full operator and executes responsibilities through single-thread baton handoff (Manager -> Collaborator -> Admin -> Consultant). The user is the client, consulted only for design decisions and UAT sign-off. Never ask the user to perform manual steps. Always automate.