atlas-connectwise

Atlas architect: boot the workspace. Verify claude-mem and context-mode, scan the project, recommend tooling (confirm first), wire hooks, seed the docs/ SSOT.

Measure atlas's own run health, audit context/asset waste, and mine session transcripts. Three lenses: RUN HEALTH reads the observability DB for metrics (wall-clock, dispatches, verifier coverage) and baseline->target goals; ASSET AUDIT scores each context-loaded skill/agent/plugin by token cost and relevance to flag disable/relocate; SESSION FORENSICS mines transcripts for unused tools and unverified claims into rules. No args reports trends.

Use to map a codebase into feature-grouped flowcharts, find architectural duplication across features, and propose the simplest unified architecture - discovery-first and zero-arg. Runs as a Workflow that fans out one explorer per feature, hunts duplication, and synthesizes a unification proposal with file:line evidence. Use before a refactor, to "find the ideal path," or to unify duplicated systems.

Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts. BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up data analysis for our warehouse", "Help me create a skill for our database", "Generate a data skill for [company]" -> Discovers schemas, asks key questions, generates initial skill with reference files ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [topic]", "Update the data skill with [metrics/tables/terminology]", "Improve the [domain] reference" -> Loads existing skill, asks targeted questions, appends/updates reference files Use when data analysts want Claude to understand their company's specific data warehouse, terminology, metrics definitions, and common query patterns.

QA an analysis before sharing with stakeholders - methodology checks, accuracy verification, and bias detection. Use when reviewing an analysis for errors, checking for survivorship bias, validating aggregation logic, or preparing documentation for reproducibility.

Build self-contained interactive HTML dashboards with Chart.js, dropdown filters, and professional styling. Use when creating dashboards, building interactive reports, or generating shareable HTML files with charts and filters that work without a server.

Audit designs and code for WCAG 2.1 AA compliance. Trigger with "is this accessible", "accessibility check", "WCAG audit", "can screen readers use this", "color contrast", or when the user asks about making designs or code accessible to all users.

Refactor and reorganize codebases using SOLID principles, clean architecture, strict naming conventions, and defensive programming. Trigger with "refactor this codebase", "reorganize the code", "clean up the project structure", "fix the naming", "audit the codebase", "code organization", or when someone needs help restructuring, renaming, deduplicating, or improving code quality across a project.

Create comprehensive developer handoff documentation from designs. Trigger with "handoff to engineering", "developer specs", "implementation notes", "design specs for developers", or when a design needs to be translated into detailed implementation guidance.

Manage design tokens, component libraries, and pattern documentation. Trigger with "design system", "component library", "design tokens", "style guide", or when the user asks about maintaining consistency across designs.

Generate comprehensive, production-ready README.md documentation from a full codebase analysis. Trigger with "generate readme", "create readme", "update readme", "document this project", "write documentation for this repo", or when someone needs a complete project README created or refreshed from the actual implementation.

Modernize frontend codebases into production-grade interfaces using shadcn/ui, Tailwind CSS, and Radix UI. Covers design tokens, component architecture, loading/progress feedback patterns, accessibility, dark mode, and responsive design. Trigger with "modernize the UI", "ui refactor", "migrate to shadcn", "fix the design system", "add loading states", "progress feedback", "make it look modern", or when someone needs help with frontend component architecture, design tokens, or async feedback patterns.

Run a fallow static analysis pass on a JavaScript or TypeScript repo and synthesize a prioritized, ranked code-quality report covering changed-code risk, complexity hotspots, and architecture boundary violations. Use when the user asks "run a code quality sweep", "analyze code quality with fallow", or "what is risky in this changed code". Read-only and advisory.

Review code for bugs, security vulnerabilities, performance issues, and maintainability. Trigger with "review this code", "check this PR", "look at this diff", "is this code safe?", or when the user shares code and asks for feedback.

Customize a Claude Code plugin for a specific organization's tools and workflows. Use when: customize plugin, set up plugin, configure plugin, tailor plugin, adjust plugin settings, customize plugin connectors, customize plugin skill, customize plugin command, tweak plugin, modify plugin configuration.

Guide users through creating a new plugin from scratch in a cowork session. Use when users want to create a plugin, build a plugin, make a new plugin, develop a plugin, scaffold a plugin, start a plugin from scratch, or design a plugin. This skill requires Cowork mode with access to the outputs directory for delivering the final .plugin file.

Use fallow's cleanup layer to find unused files, exports, types, and dependencies plus cold-path deletion confidence from runtime coverage, then produce a safe, confirmation-gated deletion plan for a JavaScript or TypeScript repo. Use when the user asks "find dead code", "clean up unused exports and dependencies", or "what is safe to delete". DESTRUCTIVE: deletions are gated behind explicit confirmation; advisory by default.

Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of technical writing - API docs, architecture docs, or operational runbooks.

Instrument services and triage errors. Trigger with "why is this slow", "what's erroring", "set up alerting", "add tracing", "define an SLO", "triage this Sentry issue", "we're getting paged for nothing", or when the user needs logs, metrics, traces, or error monitoring.

Explain the Sentry MCP discovery flow, search_issues vs search_events query syntax and filters, pagination, rate limits, and resource resolution. Read-only reference. Use when user asks "how do I query Sentry", "what is the difference between search_issues and search_events", or "how does Sentry pagination work".

Deep-dive one Sentry issue across latest events, stack trace, breadcrumbs, tags, affected releases and users to isolate the failing frame. Read-only. Use when user asks "investigate this Sentry issue", "what is causing this error", or "show me the stack trace for issue X".

Rank open and unresolved Sentry issues by severity, event volume, users affected, and regression or first-seen status, then produce a prioritized action list. Read-only. Use when user asks "triage Sentry", "what should I fix first", or "rank our open errors".

Report Sentry release health (adoption, crash-free sessions and users, new vs resolved issues, regressions) for a release and flag bad releases. Read-only. Use when user asks "how healthy is this release", "is the latest deploy crashing", or "check release health".

Run Sentry Seer AI analysis on a specific issue to get an AI root-cause and suggested fix, then summarize cause, blast radius, and recommended fix. Read-only. Use when user asks "run Seer on this issue", "what is the root cause", or "what fix does Sentry suggest".

Identify, categorize, and prioritize technical debt. Trigger with "tech debt", "technical debt audit", "what should we refactor", "code health", or when the user asks about code quality, refactoring priorities, or maintenance backlog.

Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.

Manage the month-end close process with task sequencing, dependencies, and status tracking. Use when planning the close calendar, tracking close progress, identifying blockers, or sequencing close activities by day.

Generate income statements, balance sheets, and cash flow statements with GAAP presentation and period-over-period comparison. Use when preparing financial statements, running flux analysis, or creating P&L reports with variance commentary.

Prepare journal entries with proper debits, credits, and supporting documentation for month-end close. Use when booking accruals, prepaid amortization, fixed asset depreciation, payroll entries, revenue recognition, or any manual journal entry.

Use this skill when working with PandaDoc MCP tools - available tools, API key authentication, the hosted MCP server connection, documentation search, code generation assistance, rate limiting, error handling, and best practices for the PandaDoc API.

Use this skill when working with PandaDoc documents - creating proposals, quotes, contracts, SOWs, and MSAs from templates, sending documents for signature, checking document status, downloading signed copies, and managing the full document lifecycle. Covers all document statuses, content tokens, pricing tables, and e-signature workflows.

Use this skill when working with MSP proposal workflows in PandaDoc - creating managed service agreements (MSAs), statements of work (SOWs), hardware quotes, project proposals, and tracking the MSP sales pipeline. Covers content variables, pricing tables, proposal templates, and end-to-end proposal lifecycle for managed service providers.

Use this skill when working with PandaDoc recipients and signatures - adding recipients to documents, setting signing order, tracking who has signed, managing multi-party agreements, and understanding recipient roles. Covers e-signature workflows, completion tracking, and multi-signer scenarios common in MSP contracts.

Use this skill when working with PandaDoc templates - browsing the template library, finding the right template for a document type, understanding template fields and tokens, and using templates to create new documents. Covers MSP-specific templates for MSAs, SOWs, proposals, quotes, and contracts.

Use this skill when working with the Pax8 MCP tools - available tools, parameters, pagination, sorting, filtering, rate limiting, error handling, and best practices. Covers the official hosted MCP server connection and all 15 Pax8 MCP tools.

Use this skill when working with Pax8 companies (MSP clients) - searching, retrieving, and managing client records in the Pax8 marketplace. Covers company fields, contact management, billing settings, and cross-referencing with subscriptions and orders.

Use this skill when working with Pax8 invoices and billing - retrieving invoices, analyzing billing data, reconciling costs with client charges, reviewing usage summaries, and understanding the MSP billing cycle. Covers invoice retrieval, usage-based billing, and billing reconciliation workflows.

Use this skill when working with Pax8 orders - viewing orders, tracking provisioning status, understanding order line items, and managing the order-to-subscription workflow. Covers order retrieval, status tracking, and provisioning timelines.

Use this skill when working with the Pax8 product catalog - searching for cloud software, browsing vendors, checking pricing, reviewing provisioning details, and finding the right SKU for a client need. Covers Microsoft 365, Azure, security tools, backup products, and the full Pax8 marketplace catalog.

Use this skill when working with Pax8 subscriptions - checking license status, reviewing seat counts, filtering by company or product, tracking subscription states, reviewing change history, and optimizing license usage across MSP clients. Covers the full subscription lifecycle including all subscription states and quantity management.