claude-code-plugins

Covers GitHub conventions for pull requests, issues, and comments including linking, language style, formatting, and callout syntax. Use when creating PRs, writing issues, or posting comments on Datum Cloud repositories.

Turn raw engineering notes, PR/issue links, commit messages, or a one-line feature description into a changelog entry for Datum Cloud's GitHub Discussions Changelog category: a benefit-led title plus a markdown body, drafted for users and ready to hand off for final capture and publish. Use when someone says "write a changelog entry", "announce this in the changelog", or "post this to the changelog discussions" — this is the community-facing changelog POST, not the Keep a Changelog release file (that lives in `gtm-templates`).

Provides templates for go-to-market communications including blog posts, changelogs, social media, and enablement briefs. Use when writing launch announcements or marketing content.

Create a new GitHub release. Verifies CI is green on the release commit and refreshes the third-party NOTICE file before tagging, determines the next version from the latest tag, summarizes merged PRs since the last release, drafts release notes in the established style, and publishes via gh release create. Works for any datum-cloud service repository.

Scan a project repository for strict AGPL-3.0 license compliance across Go, Rust, and JavaScript/React codebases. Use this skill whenever the user asks to check, audit, verify, or enforce AGPL license compliance on a project, repo, or codebase. Triggers on phrases like "check agpl compliance", "audit license headers", "is this project agpl compliant", "scan for license headers", "check my license files", "agpl audit", or any request involving ensuring a project is properly licensed under AGPL. Always use this skill — don't wing AGPL compliance checks from general knowledge.

Covers producing weekly operational reports for the Datum AI Edge. Use when asked for an ops review, traffic report, latency analysis, provisioning report, or edge performance summary. Guides metric queries, anomaly detection, and publishing to datum-cloud/engineering.

Generate a summary of recent cluster activity for handoffs, standups, or status updates. Use when the user asks for a status update, what happened recently, needs a summary for a handoff, or says "catch me up".

Audit a specific user's recent actions across all resources. Use when the user asks about what someone did, requests a user activity report, or needs to review actions for security or compliance purposes.

Create or edit an ActivityPolicy that translates audit logs or events into human-readable activity summaries. Use when the user mentions ActivityPolicy, wants to create translation rules, asks about CEL expressions for activity, or wants to define how changes appear in the activity timeline.

Investigate a cluster incident by systematically checking recent activity, failed operations, and resource changes. Use when the user reports something is broken, asks "what happened", mentions an outage, incident, or error, or wants to understand recent cluster changes.

Start an incident investigation with a description of the issue

Test an ActivityPolicy against sample data and iterate on its rules. Use when the user wants to test, debug, or validate an existing or in-progress ActivityPolicy, or when they say "preview this policy" or "test this policy".

Quick summary of recent cluster activity (last hour)

Covers creating C4 architecture diagrams using PlantUML. Use when documenting system architecture, component relationships, or container layouts for technical documentation.

Covers commit message conventions including format, structure, and content guidelines. Use when writing commits to ensure consistent, meaningful commit history across Datum Cloud repositories.

Covers patterns for building Kubernetes aggregated API servers including REST handlers, storage interfaces, scheme registration, and type definitions. Use when implementing API types, storage backends, or server configuration.

Provides automatic pattern extraction and knowledge accumulation from review findings. Use when running /evolve, /patterns, or /trends commands, or when understanding how patterns are promoted to runbooks.

Captures and learns from direct user corrections to Claude Code's outputs. Complements the code-reviewer-driven learning system with user-driven feedback for continuous improvement.

Covers pricing frameworks and commercial patterns including usage-based, subscription, and hybrid models. Use when designing pricing tiers, migration strategies, or assessing commercial viability of features.

Quick-start feature discovery. Creates a pipeline entry and invokes the product-discovery agent to begin the discovery process.

Covers activity timeline integration using the Activity system. Use when implementing ActivityPolicy resources, emitting Kubernetes events for activity tracking, or exposing activity timelines to users via CLI, UI, or API.

Decision framework for determining which platform capabilities a feature needs (Quota, Insights, Telemetry, Activity). Use when planning a new feature to assess which capabilities apply.

Covers proactive issue detection using the Insights system. Use when implementing InsightPolicy resources with CEL-based rules to automatically detect misconfigurations, health issues, or security concerns.

Covers resource quota integration using the Milo quota system. Use when implementing ResourceRegistration, ClaimCreationPolicy, or GrantCreationPolicy resources for quota enforcement and allocation.

Covers observability integration including metrics, traces, and logs following OpenTelemetry conventions. Use when instrumenting services for monitoring and debugging.

Covers patterns for building Kubernetes controllers using controller-runtime with Milo's multi-cluster runtime provider. Use when implementing controllers that need to operate across project control planes.

Covers CI/CD patterns using GitHub Actions with reusable workflows. Use when setting up pipelines, Taskfiles, or Dockerfiles for Datum Cloud services.

Trigger deployment workflow for a feature. Invokes the SRE agent to handle deployment configuration, staging rollout, and production promotion.

Covers the design token architecture for Datum Cloud UIs including colors, spacing, typography, and theme support. Use when implementing UI components to ensure visual consistency.

Analyze review findings and session learnings to extract patterns, update the pattern registry, and automatically promote high-confidence patterns to agent runbooks. Run periodically to keep runbooks current.

Covers GitOps deployment using FluxCD with OCIRepository and Flux Kustomization resources. Use when configuring deployments, dependency ordering, or inline patching in the infra repository.

Covers Go coding conventions including import grouping, error handling, naming, and comments. Use when writing or reviewing Go code to ensure consistency across services.

Covers Kustomize deployment patterns using base, components, and overlays structure. Use when organizing Kubernetes manifests for different environments.

Covers the Identity and Access Management system including ProtectedResource, Role, and PolicyBinding definitions. Use when implementing authorization for new resource types or defining service roles.

Display pattern statistics from the learning engine. Shows top patterns, their frequency, trends, and which agents are affected.

Covers pipeline orchestration for feature development including stages, handoffs, and artifact management. Use when coordinating work through the discovery to deployment pipeline.

Orchestrate the Datum Cloud feature development pipeline. Use to start new features, check status, advance to the next stage, or route work to the appropriate agent.

Provides high-level understanding of the Datum Cloud platform architecture. Use when onboarding to the codebase, understanding the system structure, or learning about multi-tenancy, resource hierarchy, and service architecture.

Invoke code review on the current branch or a specific feature. Runs the code-reviewer agent with appropriate context from the pipeline.

Explains the runbook system for accumulating learnings including patterns, anti-patterns, and service-specific guidance. Use when understanding how agents use runbooks or when manually adding entries.