AeyeOps

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 `

Contains verified AJE/RJE/PJE posting workflows (AuditAdjustment and MaterialityThresholds data structures), TrialBalanceRow extraction with debit/credit normal-balance logic, and TaxLineMapping tables for Form 1120 Page 1, Schedule L, M-1, M-2, and Schedule C DRD calculations. Covers trial balance pulls, comparative trial balance with significance flagging, audit adjustment posting to QBO, passed adjustment materiality evaluation, book-tax reconciliation, and QBO-to-1120 account mapping. Consult when extracting QBO data for audit workpapers, posting year-end adjustments, building Schedule M-1 reconciliation, mapping QBO accounts to Form 1120 lines, evaluating passed adjustments against materiality, generating adjustment summary logs, or pulling comparative trial balances for analytical procedures.

Contains verified GL-to-1120-line mapping tables (income Lines 1-11, deduction Lines 12-27), permanent/temporary book-tax difference catalog with IRC citations, and year-by-year rule variance tables (meals, entertainment, bonus depreciation 2007-2027+). Taxable income computation, Schedule M-1/M-3 reconciliation, DRD, charitable 10% limit, Section 163(j), Schedule L balance sheet ties, officer compensation segregation, workpaper format, and preparer/reviewer/partner sign-off protocol. Consult when preparing a Form 1120, mapping trial balance accounts to return lines, classifying a book-tax difference as permanent or temporary, debugging an M-1 that does not balance, computing the charitable deduction limitation or DRD ordering, checking bonus depreciation or meals deduction rates for a specific tax year, reconciling Schedule L to the balance sheet, or running the final verification checklist before filing a C-corp return.

Contains verified C-corp vendor-to-GL mapping table (13 vendor types with account numbers), Form 1120 tax-line expense sub-range assignments (5xxx-9xxx with line numbers), and CapEx/OpEx capitalization threshold decision tree. Deductible vs non-deductible classification (meals 50% IRC 274, entertainment 0% post-TCJA, penalties IRC 162(f)), operating/investing/financing for cash flow, bank feed rule engine logic, split transaction patterns, personal vs business separation. Consult when categorizing any transaction to a GL account, asking "what account does this go to," fixing a miscategorized charge, deciding whether to expense or capitalize a purchase, splitting a multi-category transaction, setting up bank feed auto-categorization rules, or separating deductible from non-deductible expenses.

Contains verified C-corp COA procedures, account numbering decision trees, and Form 1120 tax-line mappings that produce more precise answers than reasoning from general training alone. Account type taxonomy (1xxx-9xxx), hierarchical grouping, book-tax differences, equity accounts (APIC, retained earnings, treasury stock), and COA restructuring. Consult when choosing account numbers, classifying accounts, mapping GL to tax lines, or asking "what account for X."

Contains verified entity-type comparison tables (C-corp/S-corp/LLC tax differentials, formation procedures, S-election deadlines), IRS officer compensation multi-factor analysis with Schedule E audit triggers, and IRC 267/482 related-party rules with Form 5472 foreign-ownership reporting. Covers EIN, ownership structure, constructive ownership (IRC 267(c)), controlled groups, fiscal year, accounting method, accumulated earnings tax (Bardahl formula), QSBS (IRC 1202), and state filing obligations. Consult when determining entity type, evaluating S-election timing or late relief (Rev. Proc. 2013-30), setting or defending officer compensation, identifying related parties, assessing Form 5472 requirements, analyzing AET exposure, onboarding a new entity, or answering "who owns this company / what entity type are we."

Contains verified C-corp year-end close sequence with closing journal entries (revenue/expense to Income Summary to Retained Earnings), Form 1120 tax-line mapping tables (Schedule M-1 book-tax differences, Schedule L balance sheet, Schedule M-2 retained earnings rollforward), and ratio analysis formulas (current, quick, DSO, DPO, gross/operating/net margin, ROE, ROA, ROIC, D/E, interest coverage). Covers GAAP classified balance sheet presentation, multi-step P&L structure, indirect-method cash flow construction, stockholders' equity statement, trial balance validation, common-size analysis, variance analysis, comparative reporting, materiality thresholds, notes disclosures, and SSARS compilation/review basis. Consult when generating or reading financial statements, preparing year-end closing entries, computing financial ratios, performing common-size or variance analysis, investigating trial balance anomalies (Opening Balance Equity, Income Summary, suspense accounts), tracing interstatement linkages (net inc

Contains verified lead schedule reference map (A–EQ with supporting codes), SSARS engagement level decision tree (AR-C 70/80/90 independence gates), and AJE/RJE posting patterns with workpaper cross-references. PBC lists, tickmark conventions, workpaper packaging, management representation letters, compilation vs review. Consult when "building the PBC list for the year-end audit" or preparing lead schedules, posting auditor adjustments, choosing compilation vs review, or assembling workpaper packages.

Contains verified opening-balance JE construction logic, summary-vs-detailed entry strategy decision framework (2-year threshold), and bank statement transaction-type routing tables that produce more precise answers than reasoning from general training alone. Backlog assessment, catch-up period boundaries, monthly summary JEs, OBE cleanup, hybrid multi-year reconstruction, fiscal year alignment, tax-filing readiness gates. Consult when books are months or years behind, reconstructing GL from statements, or asking "should I use summary JEs or enter each transaction."

Alias for $plan --consensus

Full autonomous execution from idea to working code

Strategic planning with optional interview workflow

Self-referential loop until task completion with architect verification

N coordinated agents on shared task list using tmux-based orchestration

QA cycling workflow - test, verify, fix, repeat until goal met

Parallel execution engine for high-throughput task completion

Socratic deep interview with mathematical ambiguity gating before execution

Spawn a read-only conversational analyst over a code-diligence target's warehouse and repo clones for open-ended drill-down into a finding (e.g., "why is this repo a hotspot?", "who carries bus-factor risk for X?"). Use when the user invokes /code-diligence:ask. Distinct from investigating which tool fed which warehouse column — use interpreting-tool-output for that.

Initial setup for a new code-diligence target — clone repos, walk git history, run the tool wrappers, populate the warehouse, and generate curation YAMLs. Use when the user invokes /code-diligence:ingest, or sets up code-diligence on a target for the first time (no warehouse exists yet). For already-ingested targets that need new commits picked up, use refreshing-target.

Reference for mapping raw tool output (code-maat, hercules, git-of-theseus, git-fame, git-truck, repowise) to warehouse tables, tool-specific quirks, and cross-check rules. Use when debugging warehouse mismatches, investigating why two tools report different values for the same metric, deciding which canonical source to trust, or querying a specific warehouse table to compare per-tool entries — distinct from open-ended dashboard drill-down (asker) or writing narrative copy (axes).

Incrementally refresh an existing code-diligence target — pull new commits, rerun the tool wrappers, and update the warehouse without resetting analyst-confirmed curations. Use when the target was already ingested (its warehouse exists) and the user invokes /code-diligence:refresh, or asks to recompute, rerun, or update an existing target's data.

Reference for the People / Product / Process taxonomy, card-to-table mappings, confidence model, and narrative-writing contract (headline-first, cite warehouse numbers, hedge on low confidence). Use when interpreting what a dashboard card measures, writing or updating narrative rows, understanding confidence classifications, or avoiding hallucination in PE write-ups — not for querying the warehouse or executing tool commands.

Build the Observable Framework dashboard for a code-diligence target's warehouse, honoring the privacy gate on the working-pattern card. Use when the user invokes /code-diligence:dashboard, or auto-fired by the PostToolUse hook after a warehouse write.

Manages Google Workspace operations across 12 services (Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, Custom Search). Supports MCP tools or CLI via uvx workspace-mcp --cli. Provides tool routing, workflows, and parameter guidance for 114 tools. Triggers for "check my email", "find a file", "schedule a meeting", "update the spreadsheet", "share a doc", "create a presentation", "add a task", "look up a contact", or any mention of Google Workspace services.

Contains verified esbuild configurations, WSL/code-insiders workflow requirements, and package.json contributes patterns for VS Code extension development that produce more correct results than reasoning from general training alone. This environment requires code-insiders (not code) for all CLI operations — the skill enforces this constraint and provides tested scaffolding, build scripts, and publish workflows that work under WSL. Covers TreeDataProvider, WebviewPanel/WebviewViewProvider with state persistence, FileSystemWatcher, StatusBarItem, command registration, menu when-clauses, activation events, esbuild bundling with problem-matcher plugin, @vscode/test-cli test runner, and vsce publishing. Consult when building a VS Code extension, scaffolding an extension project, implementing extension APIs (TreeView, Webview, sidebar panels, context menus, status bar), configuring package.json contribution points, setting up extension tests, bundling with esbuild, or publishing to the marketplace. Do NOT use for c