CAIPE is an open-source AI platform for building, deploying, governing, and operating AI agents and agentic workflows for platform engineering and beyond.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Validate and repair the OSS first-install Docker Compose path. Use when editing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UI behavior for local all-in-one installs.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Run end-to-end integration tests with all 15 agents and supervisor in local Docker Compose dev environment. Validates agent discovery, multi-agent routing, checkpoint persistence, and cross-agent follow-up conversations.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Generate a combined release blog post for ai-platform-engineering. Produces a single docs/releases/YYYY-MM-DD-release-X-Y-Z.md file containing release notes and the upgrade guide (migration guide) inline. Use when cutting a release, when a user asks "what changed in 0.4.x", or when upgrading their values.yaml to a new…
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Run CAIPE integration tests — streaming comparison, metadata validation, and optionally full agent routing tests.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "skills" from caipe-io/ai-platform-engineering, covering user input, outline and notes.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "speckit.analyze" from caipe-io/ai-platform-engineering, covering user input, goal, operating constraints, execution steps and 1. initialize analysis context.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "speckit.checklist" from caipe-io/ai-platform-engineering, covering checklist purpose: "unit tests for english", user input, execution steps, example checklist types & sample items and anti-examples: what not to do.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "speckit.clarify" from caipe-io/ai-platform-engineering, covering user input and outline.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "speckit.constitution" from caipe-io/ai-platform-engineering, covering user input, outline, step 1: determine mode, step 2: create new constitution and step 3: amend existing constitution.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "speckit.implement" from caipe-io/ai-platform-engineering, covering user input, pre-execution checks and outline.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "speckit.plan" from caipe-io/ai-platform-engineering, covering user input, outline, phases, phase 0: outline & research and phase 1: design & contracts.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "speckit.specify" from caipe-io/ai-platform-engineering, covering user input, outline, quick guidelines, section requirements and for ai generation.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "speckit.sync-template" from caipe-io/ai-platform-engineering, covering user input, outline, step 1 — read current state, step 2 — discover latest release and step 3 — read the manifest.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "speckit.tasks" from caipe-io/ai-platform-engineering, covering user input, pre-execution checks, outline, task generation rules and checklist format (required).
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Skill "speckit.taskstoissues" from caipe-io/ai-platform-engineering, covering user input and outline.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Compare A2A streaming behaviour across supervisor versions. Captures SSE events, analyzes metadata flags (isnarration, isfinalanswer), and produces side-by-side comparison reports.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Run and document CAIPE UI/BFF performance benchmarks with Locust against the Docker Compose UI, including audit-service, OpenFGA, MongoDB, Keycloak, RAG, and dynamic-agents health context. Use when asked to run UI performance, BFF latency, Locust load tests, benchmark user-count sweeps, or update UI benchmark result…
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Audit and update all documentation moving parts for ai-platform-engineering. Checks release blog posts, features page, agent docs, homepage version strings, Docusaurus version config, and sidebar completeness. Fixes what is stale and reports what needs manual attention. Use after cutting a release, adding a new agent…
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Analyze AWS costs by service, account, and time period. Identifies top spenders, cost anomalies, and optimization opportunities. Use when reviewing cloud spend, preparing cost reports, or investigating unexpected charges.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Check the health and sync status of all ArgoCD applications across clusters. Identifies out-of-sync, degraded, or unhealthy deployments and provides actionable remediation steps. Use when monitoring deployments, troubleshooting sync failures, or verifying environment health after a release.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Check Kubernetes cluster health including pod status, node conditions, resource utilization, and pending alerts across EKS clusters. Use when monitoring infrastructure health, investigating capacity issues, or performing cluster audits.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Correlate PagerDuty incidents with Jira tickets and recent ArgoCD deployments to accelerate root cause analysis. Orchestrates multiple agents to build a timeline of events. Use when investigating active incidents, performing post-mortems, or correlating alerts with changes.
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Produce a thorough incident post-mortem report after an outage or customer-impacting event. Covers executive summary, impact, detailed timeline, root cause, contributing factors, corrective and preventive actions, and lessons learned. Use when the user asks to write, draft, or complete a post-mortem, blameless review…
caipe-io/ai-platform-engineering
Skill Claude CodeCodex
Generate a comprehensive on-call handoff document by aggregating open incidents, ongoing issues, recent deployments, and systems to watch. Orchestrates PagerDuty, Jira, and ArgoCD agents. Use during on-call rotation changes or shift handoffs.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: