devantler-tech

Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK,…

Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, set issue fields (dates, priority, custom fields), set…

Use when implementing any feature or bugfix, before writing implementation code

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for…

Codifies devantler-tech engineering practices: agent-first development workflow, TDD, CI/CD pipelines, GitHub Flow, code quality gates, and Kubernetes workflows with ksail. Use when filing issues, planning work, setting up projects, configuring CI/CD, writing…

Use the ksail CLI to spin up and manage Kubernetes clusters (Kind/K3d/Talos/vCluster/KWOK — local via Docker; EKS — cloud via AWS) and GitOps workloads declaratively. Triggers on requests involving Kubernetes clusters, Flux/ArgoCD GitOps bootstrapping,…

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Repository maintenance for devantler-tech/ksail — triage, bug fixes, CI/workflow health & CI-failure/flaky investigation, docs upkeep, driving trusted-author PRs to merge, weekly E2E coverage + live reliability testing, and the monthly KSail Strategy roadmap.…

The run procedure for the Agentic Engineer (the products' primary engineer) — pre-flight, survey the whole devantler-tech portfolio, select the highest-value work (operate first, then advance), act via per-run worktrees and draft PRs (driving every actionable…

The ADVANCE playbook for the Agentic Engineer (the products' primary engineer) — how to move a devantler-tech product forward once it's healthy: product strategy & roadmaps, issue triage & decomposition, planning & implementing issues, test coverage,…

Maintenance + advance task menu for the shared AGENT-EXTENSION libraries — devantler-tech/agent-skills (generic, cross-tool agent skills) and devantler-tech/agent-plugins (a tool-neutral marketplace bundling those skills for VS Code / Copilot CLI / Claude…

Maintenance task menu for devantler-tech/ksail (a Go CLI for local Kubernetes GitOps). Triage, bug fixes, CI/workflow health + CI-failure & flaky-test investigation, docs, driving actionable trusted-author PRs to merge including dependency-bot PRs that cannot…

Maintenance task menu for devantler-tech/monorepo itself — the devantler.tech Astro Starlight docs and blog product (docs/), CI/CD, submodule-README→docs sync, evidence-led content/marketing, and issue/PR triage. GitHub Issues are ENABLED here. Use when the…

Maintenance + advance task menu for the 🌊 Project Board (org project 5) — the maintainer's single cross-portfolio navigation surface. Covers coverage, hierarchy, status hygiene, views, and the roadmap axis. Use when the daily maintainer selects the project…

Devantler-tech compatibility overlay for the Agentic Engineer's self-improvement procedure. Routes portable changes to their canonical plugin or provenance-recorded skills upstream and deployment facts to the consumer contract.

The Agentic Engineer's cost-pass procedure — measure where the money actually goes (OpenCost attribution, real usage, provider surface), attribute it to workloads and drivers, diagnose waste vs rate vs rightsizing vs non-want, check every proposal against the…

The run loop for an autonomous AI engineer acting as a portfolio's primary engineer — pre-flight, resume in-flight work or survey every product's live state, select the highest-value work (operate before advance), act through isolated per-run working copies…

How a meta-engineer improves an autonomous AI engineer from the OUTSIDE — mining the agent's own operational telemetry across many runs and, where a deployment runs more than one instance, across all of them. Scores the agent on reliability, safety,…

The ADVANCE playbook for an autonomous AI engineer — how to move a product forward once it is healthy: product strategy and roadmap stewardship, issue triage and decomposition, oldest-actionable-first implementation, test coverage, benchmarking and…

How an autonomous AI engineer improves its OWN definition (its engineering contract, agent definitions, and skills) over time — capturing operational learnings from every run and distilling them into evidence-based, guard-railed draft PRs self-promoted on…

Debug and troubleshoot Flux CD on live Kubernetes clusters (not local repo files) via the Flux MCP server — inspects Flux resource status, reads controller logs, traces dependency chains, and performs installation health checks. Use when users report failing,…

Flux CD and Flux Operator expert — answers questions and generates schema-validated YAML for all Flux CRDs (not repo auditing or live cluster debugging). Use when users ask about Flux concepts, want manifests for HelmRelease, Kustomization, GitRepository,…

Audit and validate Flux CD GitOps repositories by scanning local repo files (not live clusters) — runs Kubernetes schema validation, detects deprecated Flux APIs, reviews RBAC/multi-tenancy/secrets management, and produces a prioritized GitOps report. Use…

Before agreeing to build anything for a non-technical user, check the need against the consuming deployment's "## Stack map" section: in-stack needs proceed; out-of-stack or unmatched needs get a friendly, jargon-free decline plus an offer to file a…

The run loop for an autonomous AI engineer acting as a portfolio's primary engineer — pre-flight, resume in-flight work or survey every product's live state, select the highest-value work (operate before advance), act through isolated per-run working copies…

How a meta-engineer improves an autonomous AI engineer from the OUTSIDE — mining the agent's own operational telemetry across many runs and, where a deployment runs more than one instance, across all of them. Scores the agent on reliability, safety,…

The ADVANCE playbook for an autonomous AI engineer — how to move a product forward once it is healthy: product strategy and roadmap stewardship, issue triage and decomposition, oldest-actionable-first implementation, test coverage, benchmarking and…

How an autonomous AI engineer improves its OWN definition (its engineering contract, agent definitions, and skills) over time — capturing operational learnings from every run and distilling them into evidence-based, guard-railed draft PRs self-promoted on…

Before agreeing to build anything for a non-technical user, check the need against the consuming deployment's "## Stack map" section: in-stack needs proceed; out-of-stack or unmatched needs get a friendly, jargon-free decline plus an offer to file a…

The conversational register for assisting a non-technical person who is building a product by conversation alone: plain language with no technical vocabulary by default, technical terms only on request and always explained in common words, and progress…

Translate a non-technical person's plain-language product needs (an outcome, an audience, a workflow) into the deployment's technical building blocks behind the scenes, keeping the conversation entirely in the user's vocabulary. Reads the consuming…

Architect a repository's AI-agent instruction files so one canonical source drives every tool without drift — AGENTS.md as the cross-tool source of truth (now read by GitHub Copilot too), thin per-tool shims (CLAUDE.md, GEMINI.md) that include it, and…

Debug and troubleshoot Flux CD on live Kubernetes clusters (not local repo files) via the Flux MCP server — inspects Flux resource status, reads controller logs, traces dependency chains, and performs installation health checks. Use when users report failing,…

Flux CD and Flux Operator expert — answers questions and generates schema-validated YAML for all Flux CRDs (not repo auditing or live cluster debugging). Use when users ask about Flux concepts, want manifests for HelmRelease, Kustomization, GitRepository,…

Audit and validate Flux CD GitOps repositories by scanning local repo files (not live clusters) — runs Kubernetes schema validation, detects deprecated Flux APIs, reviews RBAC/multi-tenancy/secrets management, and produces a prioritized GitOps report. Use…

Codifies devantler-tech engineering practices: agent-first development workflow, TDD, CI/CD pipelines, GitHub Flow, code quality gates, and Kubernetes workflows with ksail. Use when filing issues, planning work, setting up projects, configuring CI/CD, writing…

Repository maintenance for devantler-tech/platform — issue triage, manifest/Helm/Flux investigation & fixes, Helm chart + Actions version bumps, Kustomize cleanup, stale-PR nudges. Static validation only — never runs a cluster. Use when performing autonomous…

Deploy and operate Kubernetes clusters using Talos Linux and Omni. Use when generating/applying Talos machine configuration, managing cluster lifecycle in Omni, and troubleshooting common Talos/Omni workflows.

Repository maintenance for devantler-tech/reusable-workflows — triage, action/workflow version hygiene, backward-compatible workflow health, and consistency across the shared CI/CD building blocks. Use when performing autonomous or on-request maintenance of…

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for…

Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch…

Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, set issue fields (dates, priority, custom fields), set…

How an autonomous AI engineer improves its OWN definition (its engineering contract, agent definitions, and skills) over time — capturing operational learnings from every run and distilling them into evidence-based, guard-railed draft PRs that a human…

Repository maintenance for devantler-tech/actions — triage, action/workflow version hygiene, backward-compatible workflow health, and consistency across the shared CI/CD building blocks. Use when performing autonomous or on-request maintenance of this repo.

Repository maintenance for a devantler-tech platform-tenant app — triage, dependency/security hygiene, CI health, small confident fixes. Conservative, with discretion. Use when performing autonomous or on-request maintenance of this repo.

Repository maintenance for the devantler-tech platform template — triage, dependency/security hygiene, CI health, manifest/Helm/Flux investigation, small confident fixes. Static validation only; never runs a cluster. Use when performing autonomous or…

Repository maintenance for the devantler-tech Homebrew tap — Cask hygiene and CI health. Never chase version/sha bumps (release automation owns those). Use when performing autonomous or on-request maintenance of this repo.

Maintain the data-product-controller control plane, portable descriptor contract, registry, chart, and deployment readiness.

Repository maintenance for devantler-tech/go-template — triage, dependency/toolchain hygiene, CI health, and keeping the scaffold a clean current buildable template. Use when performing autonomous or on-request maintenance of this repo.