magnus919/agent-skills

Write, review, and maintain architecture decision records with clear context, alternatives, consequences, and lifecycle governance. Use when a consequential technical decision must remain understandable.

Design, document, review, and evolve consumer-facing APIs and event interfaces. Use when choosing REST, GraphQL, RPC, events, or webhooks; writing OpenAPI/AsyncAPI contracts; defining schemas, mutations, errors, idempotency, or planning API versioning, deprecation, and migration.

CLI tool for managing Radarr (movies) and Sonarr (TV series) media libraries. Use for listing, adding, searching, checking queues, quality profiles, and more.

Spawn a panel of expert agents to debate any question using a structured protocol with convergence diagnostics. Use for high-stakes decisions requiring multi-perspective analysis.

Design, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use when defining agent evals, datasets, graders, trajectory review, regression analysis, release gates, production traces, or privacy-aware telemetry.

Provides a runtime control plane for safely deploying evaluated AI agents into production, managing versioning, staged rollouts, fallback, cost and latency budgets, tool health, human escalation, and disablement.

Provides a standardized format and workflow for creating, reviewing, and implementing agent skills for AI agents, including directory structure, metadata, evals, and best practices.

Converts office documents, PDFs, ebooks, and spreadsheets to clean GitHub-Flavored Markdown locally. Use when you need the contents of a document you can't read directly.

Organize durable agent research outputs as summaries, analysis, and evidence dossiers. Use when producing multi-layer research artifacts or coordinating research handoffs.

Expert guidance for building conversational multi-agent AI systems using Microsoft AutoGen, covering agent orchestration, code execution, nested chats, and tool integration. Use when designing conversation-driven workflows or comparing multi-agent frameworks.

Design and implement backend services and APIs with patterns for REST, gRPC, GraphQL. Covers service logic, database access, integration, error handling, and testing.

Analyze unknown binary files (PE, ELF, Mach-O) using a deterministic CLI that wraps Ghidra. Perform triage, decompile functions, trace call paths, and produce structured evidence reports.

Creates comprehensive brand identity documentation covering strategy, visual identity (logo, color, typography), voice and tone, and application guidelines. Use when you need a durable brand reference for vault storage, agency handoff, or press kits.

Synthesizes workflow bundles from accumulated state, generating structured output directories with umbrella skills, sub-skills, manifests, and decision maps for agent skill scanners.

Create C4 software-architecture diagrams using Mermaid or Structurizr. Use when teams need clear system context, container, component, or code-level views.

Design or refactor CLI tools for AI agent consumption with patterns for non-interactive execution, machine-readable output, idempotent operations, and progressive help discovery.

Prepares accountable executive decisions, information triage, briefing, calendar choices, organizational sensing, and institutional memory without assuming authority. Use for chief of staff tasks like gatekeeping, decision memos, executive briefing, and strategic time allocation.

A structured, nine-stage lifecycle for embedded technical engagements—from discovery to adoption and measurement—ensuring continuity and stakeholder outcomes with templates for charters, workflow maps, and decision ledgers.

Provides scripts for backing up, restoring, and migrating Headscale installations, including SQLite database, configs, and TLS certificates. Use before upgrades or for disaster recovery.

Configures and manages DERP relay servers for Tailscale/Headscale, covering embedded and standalone setups, TLS, and connectivity testing. Use when setting up relay for NAT traversal failures.

Deploy, configure, and maintain a self-hosted Headscale control server for WireGuard mesh networking. Use this when you need full control over your tailnet without relying on Tailscale's SaaS infrastructure.

Manages the full lifecycle of nodes in a Headscale tailnet, including creation, registration, tagging, listing, and decommissioning via CLI or REST API. Useful for automating tailnet node provisioning and maintenance.

Configures subnet routers and exit nodes in Headscale tailnets to extend connectivity to non-Tailscale devices and route internet traffic through exit nodes. Use for managing routes, auto-approvers, and SNAT settings.

Conducts a structured, adaptive interview to discover a user's workflow, mapping phases, tools, branching, and pain points to generate a workflow bundle.

A disciplined operating model that guides AI agents through non-trivial software changes—from discovery and design to verified delivery—by enforcing evidence gates and escalation rules.

A passive observation sub-skill that scans session history to infer workflow patterns when triggered. It detects entry patterns, phases, branching, tools, pain points, and exit behavior, producing a structured workflow model for bundle generation.

Routes a product through nine lifecycle phases from discovery to review by composing specialist product skills with evidence handoff and phase-entry criteria. Use when managing a product across multiple stages.

Assembles production evidence from readiness, migration, recovery, capacity/cost, and incident learning into a structured gate decision (go, no-go, defer, exception, escalation) with accountable owners and a post-launch learning path.

Chain web research, atomic extraction, and durable knowledge capture into a repeatable workflow when the same research-to-notes sequence is needed.

A skill for authoring, testing, and deploying Tailscale-compatible huJSON policy files for Headscale and Tailscale. Use it to manage ACLs, grants, tags, auto-approvers, and SSH rules.

Deploy and manage a self-hosted Tailscale mesh VPN with Headscale. Covers server setup, node registration, access control, routing, relay servers, and backup tasks.

Install, configure, and troubleshoot the official Tailscale client for self-hosted Headscale control servers. Covers authentication, diagnostics, and connectivity optimization.

Discovers how you actually work through guided questions or session observation, then generates a bundle of loadable skills with triggers, phases, and transitions. Use it when you want an agent to adapt to your workflow automatically.