aeo-skill-marketplace

Migrate a Claude Cowork session from one Windows machine to another with full history, working file links, and no truncated-transcript rendering bug. Use this whenever the user mentions moving, importing, copying, or migrating a Cowork session/conversation/project between machines, or troubleshoots symptoms of a broken import like "session shows blank", "only the latest messages show", "scratchpad files don't open", "can't scroll past the last compaction", or "Loaded N messages (truncated via tail/compaction)" in the Cowork log. Covers orphan sessions on Windows to Windows under the same Cowork account. Handles the undocumented two-layer compact_boundary truncation filter in app.asar that silently clips imported transcripts. Does not handle Cowork Spaces/Projects, Linux/macOS, or cross-account migration.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Onboard a macOS host (Tahoe / macOS 26 and later) as a Tailscale client of a self-hosted headscale control plane. Covers Tailscale.app installation via Homebrew Cask, the NetworkExtension permission grants required for the daemon to start, the conflict that arises if the brew formula `tailscale` is also installed alongside the cask, how to use `tailscale up --login-server` with a headscale preauth key, the deep-link fallback flow when the CLI cannot reach the daemon, the headscale-specific gotcha that `headscale preauthkeys create --user <N>` expects a numeric user ID rather than a username on recent builds, and bidirectional reach verification once joined. Use when adding a macOS host to a headscale-controlled mesh, troubleshooting symptoms like "failed to connect to local tailscale service", Tailscale.app stuck on "Starting...", `tailscale up` hanging on "joining <coordinator>", a blank menu-bar icon after a fresh install, deciding between the Homebrew cask and formula distributions, or recovering from a st

Comprehensive reference for the GL-iNet Slate 7 travel router (model GL-BE3600, Wi-Fi 7). Covers hardware specs, 2.5G ports, touchscreen interface, full admin panel menu structure, VPN client setup (WireGuard/OpenVPN; NordVPN, Mullvad, Surfshark, and 30+ providers), WireGuard/OpenVPN server setup, AdGuard Home, Tor, Tailscale, DDNS, network modes (Router/AP/Extender/WDS/Drop-in Gateway), SSH/CLI access with command reference, factory reset, firmware update, and U-Boot bricked-device recovery. Also covers the JSON-RPC admin API at /rpc (challenge/response auth, module/method discovery, reusable bash helper), programmatic WireGuard server provisioning via the wg-server module (add_peer, generate_peer, settings, leak verification, local-only Endpoint pattern), and Linux client-side WG with overlay-VPN stacking — including the two leak modes that appear when running Tailscale on top of a full-tunnel WG client (fwmark 0x80000 bypass and wg-quick catch-all shadowing the tailnet routes) plus the wg-quick PostUp/PreD

This skill should be used when the user asks about "MLX serving", "mlx_lm.server", "oMLX", "Apple Silicon LLM serving", or "local LLM on Mac" — and when troubleshooting symptoms like model fails to load, OOM during load or inference, server hangs or crashes at batch>1, tool calls returning as plaintext content, throughput regression, or choosing between mlx-lm and oMLX. Also applies to oMLX feature-flag tuning ("turboquant_kv", "dflash", "MTP", "specprefill", "thinking_budget", "max-concurrent-requests", "force_sampling"), OptiQ proxy for models exceeding RAM, Llama-4 ChunkedKVCache batch handling, Llama-3 tool-call JSON format ("name"/"parameters"), and bench-driven validation of serving configs. For Apple Silicon (M-series) only — not for cloud LLM hosting (Bedrock, OpenAI API, Anthropic API), not for non-MLX backends (llama.cpp, Ollama, vLLM), not for model training.

This skill should be used when the user asks about "Lima", "limactl", "lima.yaml", "lima start", "lima shell", "creating a Linux VM on Mac", "running Linux on Apple Silicon", "macOS Linux VM", "Apple Silicon VM", or wants to "install Lima", "configure a Lima VM", "edit lima config", "spin up an Ubuntu VM on my Mac", or "use Lima to run Docker on macOS". Also applies for "lima vmType vz", "lima vz vs qemu", "host.lima.internal", "socket_vmnet", "lima networking", "lima shared network", "lima bridged network", "virtiofs mount", "9p mount", "lima port forward", "lima mount writable", "limactl edit", "limactl validate", "limactl template", "lima Rosetta", "running x86 in lima", "lima debug startup", or any task involving spinning up, configuring, troubleshooting, or shelling into a Lima VM on an Apple Silicon Mac. Use this skill whenever Lima is mentioned even if the user doesn't explicitly ask for "help" — the right configuration choices (vz vs qemu, mount type, network mode) are non-obvious and easy to get wron

Produce architecture documentation for technical audiences using established frameworks — the C4 model for system structure (Context / Container / Component / Code), Architectural Decision Records (ADRs) for capturing the why behind significant design choices, OpenAPI for HTTP API specifications, and system / component design documents for engineers who need to build against or reason about the architecture. Use when someone asks to document system architecture, write an ADR, capture an architectural decision, generate C4 diagrams (context / container / component), produce an OpenAPI spec, draft a component design doc, or document how services integrate. Trigger phrases include "create a C4 diagram", "write an ADR for X", "document the architecture", "specify the API", "OpenAPI spec for", "system design doc", "decision record", "architecture overview". Not for: end-user-facing docs (use the `aeo-docs:diataxis` skill instead — tutorials, how-tos, references, explanations live there), README content, or code-le

Author user-facing technical documentation following the Diataxis framework — tutorials, how-to guides, reference material, and conceptual explanations. Picks the right of the four documentation modes for the request, applies that mode's structural template, and avoids cross-mode bleed (no comprehensive API listings inside a tutorial, no learning exercises inside reference docs, no step-by-step procedures inside an explanation). Use whenever someone asks to document something for users, write a getting-started guide, generate an API or config or CLI reference, write a deployment / migration / troubleshooting guide, explain a design decision, or produce any docs that will live in `docs/`. Trigger phrases include "write a tutorial", "create a how-to", "document the API", "explain why we chose", "generate config docs", "build a reference", "write user docs for X", and any open-ended request to produce user-facing documentation. Not for: README content, code comments, architecture / C4 / ADR / OpenAPI work (use `

Author D2 diagrams (the Terrastruct text-to-diagram language at https://d2lang.com). Use whenever the user wants to produce, edit, or render any kind of diagram with D2 — architecture, flowchart, sequence, ER/SQL schema, UML class, network topology, mind map, deployment, org chart, state machine, grid layout, mermaid-style flow, or anything similar — even when they don't say "D2" explicitly. Trigger on requests for `.d2` files, mentions of `d2`/`d2lang`, or open-ended diagramming tasks ("draw me a system diagram", "make a flowchart of X", "diagram the request flow", "give me an ER diagram for these tables"). Covers the full DSL — shapes, connections, containers, classes, vars, globs/filters, imports, layers/scenarios/steps, styling, themes, sketch mode, icons, markdown/LaTeX/code blocks, layout engines (dagre/elk/tala), CLI flags, and the specialized diagram shapes (sequence_diagram, sql_table, class, grid, hierarchy, c4-person, image, text/code).

Craft Mermaid diagrams within Markdown for flowcharts, ERDs, sequence diagrams, state machines, Gantt charts, and mindmaps. Includes validated syntax templates, layout optimization, and cross-platform rendering for GitHub, GitLab, VS Code, and Obsidian. Use when: creating diagrams in markdown files, debugging "diagram not rendering" errors, selecting diagram types for docs, visualizing database schemas or API flows, or fixing Mermaid syntax issues.

Automated ultrareview validation loop that cycles between review and fix phases until no actionable findings remain. Use when you want continuous validation with automatic fix iterations on plans or code changes.

Coordinator-delegated planning mode that breaks complex tasks into subtasks and delegates all implementation to Opus subagents. Use when tackling multi-step projects, large refactors, or any work requiring parallel delegation with task tracking.

Team-coordinated planning mode that creates an agent team for parallel implementation. Use for complex multi-component projects requiring coordinated parallel workstreams. Extends ultraplan with Claude Code's teams feature for bidirectional agent communication.

Use this skill when the user is writing, reviewing, debugging, or rewriting any instructions that Claude itself will read — including CLAUDE.md files, skill files (SKILL.md, frontmatter descriptions), slash command templates (.claude/commands/*.md), and agent definitions (.claude/agents/*.md). Trigger on symptoms like: an agent firing too often or on the wrong things, a prompt that's too long or full of MUST/NEVER/ALWAYS, Claude ignoring sections of a command, agents looping on tools instead of stopping, skills not activating when they should, descriptions that don't trigger correctly, or asking how to structure a system prompt so Claude behaves a certain way. Also trigger when converting docs/runbooks into skills, drafting agent frontmatter from scratch, or asking what's "pulling weight" in a prompt. Do not trigger for general code review, MCP server design, hook scripts, or API/SDK questions unless the artifact under discussion is a prompt Claude reads.

Systematically address all findings from a preceding ultrareview validation. Works through errors, alignment issues, gaps, and improvements by priority. Use after running ultrareview to fix identified issues in plans or code.

Deep validation protocol that examines preceding context for errors, unvalidated assumptions, alignment issues, gaps, and improvement opportunities. Produces a machine-parseable summary. Use when validating plans, code changes, configurations, or any work product before proceeding.

Author custom Claude Code slash commands as reusable Markdown prompt templates. Covers frontmatter configuration, argument handling, variable substitution, and workflow automation patterns. Invoke when designing new commands, debugging command syntax, or converting repetitive prompts into reusable shortcuts.

Contains verified extension development workflows, webview CSP pitfall resolutions, and profile-based install fixes that produce more correct results than reasoning from general training alone. Consult when building or debugging a VS Code extension, scaffolding with esbuild, fixing blank webview panels or silent CSP violations, troubleshooting extensions that won't load after install with profiles, adding dual TreeView+WebviewView toggle panels, or publishing to the marketplace. Do NOT use for VS Code user configuration (themes, keybindings, tasks.json), Chrome/browser extensions, Electron apps, JupyterLab plugins, or Monaco Editor embeds.

Contains verified WSL-specific extension development workflows, webview CSP pitfall resolutions, and profile-based install fixes that produce more correct results than reasoning from general training alone. Targets code-insiders on WSL/Linux — not stable VS Code on Windows/macOS. Consult when building or debugging a VS Code extension under WSL, scaffolding with esbuild, fixing blank webview panels or silent CSP violations, troubleshooting extensions that won't load after install with profiles, or publishing to the marketplace with code-insiders. Do NOT use for stable VS Code, VS Code user configuration (themes, keybindings, tasks.json), Chrome/browser extensions, Electron apps, JupyterLab plugins, or Monaco Editor embeds.

Generate Gemini 2.5 computer-use automation scripts and natural-language goal files for web application QA. Produces Playwright-based test harnesses for browser automation with scenario generation capabilities. Activate for UI test automation, visual regression testing, or AI-driven browser interaction workflows.

Guide the user through repository documentation governance using the aeo-repo-* command family. Use when the user asks about AGENTS.md scaffolding, roadmap alignment reviews, doc curation, repo bootstrap, or wants to know which governance command to run next. Covers lifecycle sequencing: bootstrap a scaffold, iterate with alignment reviews and curation passes, sanitize before publishing.

Build autonomous AI agents in Python using the Claude Agent SDK. Covers the GTVR execution pattern (gather, take action, verify, repeat), stateless query() and stateful ClaudeSDKClient APIs, streaming versus batch modes, custom tool creation with @tool decorator, MCP server integration, hook-based execution control, permission boundaries, API key and OAuth token management, multi-agent coordination, and production deployment strategies. Suited for programmatic agents, tool chains, and multi-agent systems. Not designed for basic chat interfaces.

Construct rich terminal interfaces using Textual for multi-pane dashboards with CSS styling and Python Prompt Toolkit for interactive line editing with completions. Covers widget composition, key bindings, TUI testing strategies, and WSL2 layout quirks. Engage when building IDE-style interfaces, REPL shells, or dashboard applications.

Nous self-improving context system overview. Use when the user asks about "nous", "learnings", "knowledge extraction", "context injection", "how does memory work", "how are learnings captured", or wants to understand the self-improvement pipeline.

This skill should be used when the user asks about "Azure CLI commands", "writing Azure CLI scripts", "managing Azure resources", "az login", "az account", "service principal", "managed identity", "credential chain", or working with specific Azure services via CLI (VMs, Storage, VNets, NSGs, Key Vault, App Service, AKS, RBAC). Also applies when the user needs help with "JMESPath query", "--query syntax", "az graph query", "CLI pagination", "az wait", "output formatting", "multi-subscription", "resource locks", "safe destructive commands", "az rest API calls", "az bicep", "CLI extensions", "cost management", "cost analysis", "spending", or "az resource" for services without dedicated CLI commands.

This skill should be used when the user asks about "AWS CLI commands", "writing AWS CLI scripts", "querying AWS resources", "managing AWS credentials", "aws login", "aws configure sso", "assume role", "credential chain", or working with specific services via CLI (S3, EC2, IAM, Lambda, VPC, RDS, DynamoDB, CloudWatch, SSM). Also applies when the user needs help with "JMESPath query", "--query and --filters syntax", "CLI pagination", "aws cli waiter", "output formatting", "cross-account access", "safe destructive commands", "S3 sync dry run", "aws cli pager blocking script", or "migrating from AWS CLI v1 to v2".

Caching strategies, database optimization, algorithmic complexity, and when NOT to optimize. Activate when: optimizing performance, implementing caching, fixing N+1 queries, improving database queries, reducing latency, choosing data structures, deciding whether to optimize.

Performance profiling methodologies, interpreting profiler output, and benchmarking techniques. Activate when: profiling application performance, reading flame graphs, benchmarking code, identifying bottlenecks, measuring CPU usage, analyzing memory allocation, I/O profiling.

Engineer production-grade Python CLI tools with UV for package management, Ruff for linting, Pyright for strict typing, Typer for commands, and Rich for polished output. Addresses fail-fast patterns, pydantic-settings configuration, modular code organization, and professional UX conventions. Apply when creating admin utilities, data processors, or developer tooling.

Build-vs-buy decision framework with TCO analysis, vendor evaluation, and migration planning. Activate when: evaluating build vs buy, comparing vendors, assessing make or buy decisions, analyzing total cost of ownership, planning vendor migrations, evaluating SaaS vs custom.

Stakeholder interview techniques, requirement types, prioritization frameworks, and acceptance criteria patterns. Activate when: eliciting requirements, writing user stories, interviewing stakeholders, prioritizing features, defining acceptance criteria, building a requirements document.

OWASP Top 10 vulnerabilities with detection patterns, code examples, and prevention checklists. Activate when: reviewing code for security, checking for OWASP vulnerabilities, performing security audits, fixing injection flaws, preventing XSS, securing authentication, checking access control.

Secure coding practices covering input validation, secrets management, and authentication patterns. Activate when: validating user input, managing secrets, implementing authentication, handling authorization, encoding output, applying secure defaults, reviewing code security.

TDD cycle mechanics, test-first patterns, and fixture strategies. Activate when: practicing TDD, writing tests first, doing red-green-refactor, learning test-driven development, choosing test types, writing unit tests.

Test pyramid, testing anti-patterns, parameterized tests, and coverage interpretation. Activate when: designing test strategy, choosing test types, fixing test anti-patterns, writing parameterized tests, interpreting code coverage, understanding mutation testing.

Common failure patterns organized by category with symptoms, causes, and fixes. Activate when: diagnosing dependency conflicts, environment issues, PATH problems, permission errors, CORS errors, DNS failures, timeout issues, async bugs, concurrency problems, race conditions, memory leaks, deadlocks.

Root cause analysis, hypothesis-driven debugging, and isolation techniques. Activate when: debugging an issue, reading stack traces, performing root cause analysis, troubleshooting errors, reproducing bugs, isolating failures, binary search debugging.

Architect modern React progressive web apps with offline-first capabilities and responsive interfaces. Integrates shadcn/ui component library, service worker patterns, and mobile-friendly layouts. Consult when building installable web applications or designing component-driven UIs.

Battle-tested architectural blueprints derived from production n8n deployments. Covers webhook handlers, REST API integrations, database pipelines, AI agent orchestration, and scheduled automation. Reference when designing new workflows or selecting the right pattern for your use case.

Author high-quality Claude Code skills with proper frontmatter, trigger-optimized descriptions, progressive disclosure structure, and MCP tool integration. Includes file organization patterns, testing approaches, and performance tuning. Consult when building new skills, debugging activation issues, or refactoring existing skill content.