DevOps & Infra

tonyandrewmeyer Bundle

Operate a Juju controller — deploy, configure, integrate, scale, debug, and manage charms on Kubernetes and machine models. Use when asked to "deploy a charm", "add a model", "check status", "debug a unit", "integrate applications", "scale up/down", "manage secrets", "configure an app", "run an action", "destroy a model", or any Juju CLI operation. Keywords include juju, deploy, integrate, relate, model, controller, status, debug-log, config, action, expose, storage, secrets, ssh, scale.

tonyandrewmeyer Bundle

Expert assistant for Juju charm development using jhack utilities. Use when debugging charms, inspecting relations, syncing code, replaying events, testing scenarios, or performing rapid development iterations. Keywords include jhack, Juju debugging, charm testing, relation inspection, event replay, sync, tail, fire, show-relation, show-stored.

tonyandrewmeyer Bundle

Expert assistant for provisioning charm development and testing environments using concierge. Use when setting up development machines, bootstrapping Juju controllers, installing craft tools (charmcraft, snapcraft, rockcraft), or preparing test environments. Keywords include concierge, provision, development environment, Juju bootstrap, LXD, MicroK8s, K8s, craft tools, prepare, restore.

tonyandrewmeyer Bundle

Expert assistant for developing Juju charms using charmcraft. Use when initializing charm projects, building charms, managing charm libraries, publishing to Charmhub, running tests, or working with charmcraft.yaml configuration. Keywords include charmcraft, Juju, charm development, Charmhub publishing, charm libraries, pack, build, upload, release, init, extensions.

tonyandrewmeyer Bundle

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.

tonyandrewmeyer Bundle

Find bugs in Juju charm operator repositories. Use when asked to "find bugs", "audit code", "review for bugs", "check for issues", "security review", or review Python code in any Juju charm. Specialized for charm-specific bug patterns including Pebble container management, relation data handling, TLS certificate lifecycle, status management, config handling, ingress/networking, Grafana dashboard wiring, and Juju interaction. Built from analysis of 6,116 historical bug fixes across 134 charm repositories spanning 10 teams (Data, Observability, MLOps, IS, Identity, Telco, Commercial Systems, K8s, BootStack, Charm-Tech).

sunnypatneedi Skill

Build robust CI/CD pipelines with GitHub Actions, Docker containers, infrastructure as code, deployment strategies (blue-green, canary), and monitoring. Automate everything from commit to production.

jsamuelsen11 Skill

This skill should be used when designing Docker Compose services, configuring networking, managing volumes, or setting up multi-container applications.

jsamuelsen11 Skill

This skill should be used when designing Helm charts, writing values.yaml, creating templates, managing chart dependencies, or testing Helm releases.

jsamuelsen11 Skill

This skill should be used when working with Docker, writing Dockerfiles, configuring Docker Compose, building container images, or reviewing Docker configuration.

jsamuelsen11 Skill

This skill should be used when optimizing Docker image size, improving build performance, implementing caching strategies, or hardening container security.

lawless-m Bundle

Use when a task needs local LLM inference via the on-box Ollama server (Qwen 2.5) instead of a cloud API.

artokun Skill

Full production pipeline covering story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips, ffmpeg concatenation

artokun Bundle

Core ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usage

artokun Skill

Upscale and restore video in ComfyUI. Both the quick local path (per-frame ESRGAN like 4x_foolhardy_Remacri via ImageUpscaleWithModel + 4x→2x supersample, with its temporal-flicker tradeoff) and temporal-aware super-resolution (SeedVR2, the newer FlashVSR) with the downscale-first restore pipeline; RIFE/FILM frame interpolation via the BUILT-IN ComfyUI 0.26 FrameInterpolate (rife_v4.26 in models/frame_interpolation/) or the ComfyUI-Frame-Interpolation pack; 2x/4x scaling, VRAM tiers, VHS encode. Captures the classic downscale→SeedVR2→RIFE recipe and the current 2026 recommendation.

jsamuelsen11 Skill

This skill should be used when working with Kubernetes manifests, designing deployments, configuring services, or reviewing cluster configuration.

jsamuelsen11 Skill

This skill should be used when writing MongoDB aggregation pipelines, using $lookup, $group, $merge, or optimizing pipeline performance. It provides pipeline stage ordering rules, $lookup vs app-side join guidance, $facet patterns, $merge for materialized views, pipeline optimization techniques, and $out vs $merge comparisons.

jsamuelsen11 Skill

This skill should be used when implementing deployment strategies, configuring autoscaling, setting up probes, managing disruption budgets, or designing zero-downtime deployments.

jsamuelsen11 Skill

This skill should be used when working with GitHub Actions, writing CI/CD workflows, configuring workflow triggers, or reviewing GitHub Actions configuration.

proxiblue Skill

The sanctioned pre-push verification gate. Runs tests, type-check, shows diff stat against the target branch, and EXPLICITLY asks for user confirmation before any push. Required by CLAUDE.md's Deployment & Git Safety cardinal rules — the push-guard.sh hook blocks direct pushes to live/uat without this skill (or an explicit CLAUDE_PUSH_ALLOWED=1 session env var).

artokun Skill

On-demand procedures for the ComfyUI sidebar panel agent that are too long to sit in the system prompt. Read it when a task lands in one of these areas. subgraph boundary rails and blueprint reuse, merging or composing workflows across tabs, pinning your edits to one workflow, opening staged or downloaded workflow files, untangling Get/Set-bus and rgthree toggle-heavy graphs, authoring rgthree Fast Groups nodes, the LoRA Manager autocomplete-node limitation, the CivitAI browser flow, downloading model weights, reading hardware and runtime stats, Prompt Director audits, custom-node crash recovery, run-to-node render debugging, and multi-stage pipeline chaining. Each section is a lookup, not background reading. Reach for the one you need instead of guessing, and follow the tool's own description for parameter detail.

artokun Skill

Swap an OUTFIT or transfer CLOTHING onto a person LOCALLY, keeping their face, pose and background. Use for "put this jacket on her", "change his shirt", "clothes swap", "try on", "outfit transfer", "virtual try-on", "dress her in", "wear this outfit". Prefer this over API/cloud edit nodes and over generic img2img/inpainting. NOT for identity-preserving edits that are not about clothing (background swaps, relighting, age/expression changes, object removal). Use a general image-edit workflow for those.

artokun Skill

Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train_* tools (GPU Docker + ostris ai-toolkit). Use when the user wants to train a LoRA of a person/character from their photos on the local GPU. Covers dataset prep, launch, monitoring, and using the result in ComfyUI. For WAN/Z-Image training via the ai-toolkit UI see ai-toolkit-trainer.

proxiblue Skill

Reproduce-push-verify cycle for shipping a fix to UAT — confirms the bug still reproduces on UAT (reusing the local test that proves the fix, pointed at the UAT host), merges + pushes the feature branch to `uat` (structurally authorized to clear push-guard.sh's uat block for that one push), confirms via the buddy-mcp Buddy.works MCP server that the deploy pipeline actually completed, then reruns the same test against UAT to confirm the bug is gone. Invoke explicitly (e.g. "/uat-deploy-verify") — never auto-triggered, since it performs an authorized push.

proxiblue Skill

PER-TICKET BUILD workflow for shipping a Magento feature through plan + implement + review + verify + quality-gate stages — but STOPS at 'ready to deploy'. Does NOT push or deploy. The user runs /deploy-check separately when they're ready. Flow: prereq check (wires.json registry-driven, scales to N per-domain playbooks) → branch creation → /hcf:plan-create (devils-advocate consults wired playbooks: gitnexus, graphiti, …) → /manual-test-plan posts GitHub ticket comment → /hcf:plan-orchestrate (HCF native — gitnexus-reviewer runs as a pipeline.md post-implementation agent rather than per-task wrapper gate, after pb-gitnexus wrapper was retired in favour of pb-hcf wires) → handoff to /verify-feature (in a fresh thread per skill convention) → CHAINS /proxiblue-skills:workflow-security-audit as a quality gate → completion summary listing all gates passed/failed. Maintains visible TodoWrite list throughout. Pauses at every user-decision boundary. Assumes /proxiblue-skills:workflow-onboard-project has already run. C

proxiblue Skill

Maintenance workflow to re-index the per-project GitNexus knowledge graph after a major refactor, dependency update, or when impact/find_symbol queries stop matching reality. Use when: a recent merge added new modules, you ran composer update with significant version bumps, the gitnexus-reviewer is reporting symbols that don't match the actual code, or it's been a long time since the last reindex (index is a snapshot — drift accumulates). Workflow: detects the project, derives the correct mount alias from the .ddev/docker-compose.gitnexus.yaml, clears the existing lbug, runs build-mount.sh on the host (with crash auto-recovery if a tree-sitter Napi error fires), restarts the per-project gitnexus container, verifies the new index via mcp__gitnexus-mageos__list_repos. Crosses host/container boundary: host steps are explicitly handed off with copy-paste commands when invoked from inside the DDEV web container.

anthony-chaudhary Bundle

Cut a versioned release of the DOS kernel — bump the version, draft release notes, commit, tag, push to master, and create a GitHub release. The tag push triggers the gated PyPI publish pipeline (publish.yml); the skill surfaces the run and its approval gate.

olehsvyrydov Skill

SRE / Observability Engineer (/sre) — reliability engineering: SLOs/SLIs & error budgets, monitoring & alerting (Prometheus, Grafana, OpenTelemetry), incident response & runbooks, on-call, capacity & load, chaos/resilience, and post-incident reviews. Use when defining reliability targets, instrumenting observability, setting up alerting, writing runbooks, doing incident response, or reviewing a change for production readiness. Invoke alongside /arch for reliability NFRs and devops-engineer for the underlying infra/CI-CD. NOT for provisioning infra or pipelines (that's devops-engineer) — /sre owns reliability, not the cluster.

olehsvyrydov Bundle

Solution Architect (/arch, alias: Jorge, /jorge) - Principal Solution Architect with 15+ years designing scalable distributed systems. Use when making technology choices, designing system architecture, selecting patterns (Saga, CQRS, Event Sourcing), creating ADRs, planning integrations, database sharding/replication, microservices/microfrontends, security architecture, data platforms, AI/ML systems, or cloud cost optimization. Provides architectural guardrails, not prescriptions — developers decide HOW within boundaries.

anthony-chaudhary Skill

Route subagent claims through independent read-back before another agent relies on them. Use at parallel, pipeline, or synthesis barriers where shipped phases, files, rows, messages, or other effects must be witnessed.

olehsvyrydov Bundle

DevOps Engineer (/devops) - Senior DevOps Engineer with 12+ years cloud infrastructure experience. Use when setting up cloud infrastructure, writing Terraform configurations (loads references/terraform.md), creating Kubernetes manifests, building CI/CD pipelines with GitHub Actions, configuring Docker, or managing secrets.

olehsvyrydov Bundle

Soren - Principal Security Engineer with 15+ years application, infrastructure, and cloud security experience. Security review is a safety-override gate, required on security-relevant changes (auth, secrets, PII, external input, etc.) and always in the regulated preset. Use when conducting security reviews, threat modeling (STRIDE/PASTA/LINDDUN), implementing authentication (OAuth 2.1/Passkeys/WebAuthn), supply chain security (SBOM/SLSA), container/K8s hardening, Zero Trust architecture, AI/LLM security, privacy engineering, security scanning pipelines, compliance (GDPR/PCI-DSS/SOC2/ISO27001), or incident response. Primary command: /secops. Alias: /soren.

u9401066-rootcause-mcp Bundle

Pipeline persistence — save, load, and reuse structured search plans. Triggers: pipeline, 管道, search plan, 搜尋計畫, 重複搜尋, saved search, 排程, schedule, workflow, DAG

u9401066-rootcause-mcp Skill

Cline harness for PubMed Search MCP. Triggers: pubmed search, literature search, unified_search, pipeline, fulltext, release checklist, Cline.

darthmolen Bundle

Use when running ad-hoc read-only T-SQL against Azure SQL — exploring Query Store, sampling tables, inspecting DMVs, joining sys.* views, or producing JSON/CSV for an alerting pipeline. Read-only by construction (AST-validated, rolled-back transaction, no INSERT/UPDATE/DELETE/EXEC/OPENROWSET). Returns TOON by default for token-efficient consumption by Claude; --format=json|table|csv for other consumers.

darthmolen Bundle

Use when running ad-hoc read-only SQL against Azure Database for PostgreSQL — exploring tables, sampling rows, checking key uniqueness/overlap across tables, inspecting pg_stat_* / pg_catalog, or producing JSON/CSV for a pipeline. Read-only by construction (server-enforced read-only transaction + client-side guard, always rolled back; no INSERT/UPDATE/DELETE/DDL/COPY/dblink). Returns TOON by default for token-efficient consumption by Claude; --format=json|table|csv for other consumers. This is the PostgreSQL counterpart to sql-query (which targets Azure SQL only).