agentsclimarketplace

Context & AI engineering

25,815 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • HaloPSA MCP

    servosity/msp-skills/io.github.Servosity/halopsa-mcp MCP server

    no license24★ repo

    HaloPSA ticket triage, SLA-breach pre-emption, and cross-client analytics for any MCP agent.

  • Nerdio Manager MCP

    servosity/msp-skills/io.github.Servosity/nerdio-mcp MCP server

    no license24★ repo

    The first non-PowerShell client for the Nerdio Manager for MSP API - cross-account AVD fleet

  • Resource Guru MCP

    servosity/msp-skills/io.github.Servosity/resourceguru-mcp MCP server

    no license24★ repo

    Operate Resource Guru from your AI agent via MCP.

  • Rootly MCP

    servosity/msp-skills/io.github.Servosity/rootly-mcp MCP server

    no license24★ repo

    Every Rootly incident, alert, and on-call object as a typed command - plus a local SQLite mirror

  • QuickBooks Online MCP

    servosity/msp-skills/io.github.Servosity/quickbooks-mcp MCP server

    no license24★ repo

    Every QuickBooks Online Accounting entity, plus an offline SQLite mirror and AR/AP aging.

  • Rewst MCP

    servosity/msp-skills/io.github.Servosity/rewst-mcp MCP server

    no license24★ repo

    Operate and monitor Rewst RPA across every client org: automation health, failures, ROI, and drift.

  • SentinelOne MCP

    servosity/msp-skills/io.github.Servosity/sentinelone-mcp MCP server

    no license24★ repo

    Every SentinelOne v2.1 management endpoint, plus an offline SQLite store and cross-entity analytics

  • runZero MCP

    servosity/msp-skills/io.github.Servosity/runzero-mcp MCP server

    no license24★ repo

    Every runZero query, plus a local SQLite copy of your whole attack surface that diffs over time

  • RocketCyber MCP

    servosity/msp-skills/io.github.Servosity/rocketcyber-mcp MCP server

    no license24★ repo

    CLI and MCP server for RocketCyber Managed SOC: triage, MTTR, and posture analytics.

  • Salesbuildr MCP

    servosity/msp-skills/io.github.Servosity/salesbuildr-mcp MCP server

    no license24★ repo

    Every Salesbuildr resource as a scriptable command, plus offline margin and pipeline analytics.

  • Sherweb MCP

    servosity/msp-skills/io.github.Servosity/sherweb-mcp MCP server

    no license24★ repo

    Every Sherweb Partner API capability, plus a local SQLite store, offline analytics, and

  • Syncro MCP

    servosity/msp-skills/io.github.Servosity/syncro-mcp MCP server

    no license24★ repo

    Every Syncro PSA and RMM workflow in your terminal, plus a local database, offline search, and

  • SuperOps MCP

    servosity/msp-skills/io.github.Servosity/superops-mcp MCP server

    no license24★ repo

    Every SuperOps PSA+RMM entity in your terminal, plus a local SQLite mirror that answers

  • Veeam VSPC MCP

    servosity/msp-skills/io.github.Servosity/veeam-mcp MCP server

    no license24★ repo

    Sync Veeam Service Provider Console tenants to local SQLite; cross-company backup answers offline.

  • Servosity MCP

    servosity/msp-skills/io.github.Servosity/servosity-mcp MCP server

    no license24★ repo

    Fleet-wide backup triage, stale-backup detection, and cross-engine analytics for any MCP agent.

  • SkyKick MCP

    servosity/msp-skills/io.github.Servosity/skykick-mcp MCP server

    no license24★ repo

    Fleet backup posture, stale snapshots, and coverage gaps for SkyKick Cloud Backup.

  • Xero MCP

    servosity/msp-skills/io.github.Servosity/xero-mcp MCP server

    no license24★ repo

    Every Xero Accounting read plus a local SQLite ledger - aging, reconciliation, and GL tie-out

  • Tactical RMM MCP

    servosity/msp-skills/io.github.Servosity/tactical-rmm-mcp MCP server

    no license24★ repo

    Every Tactical RMM endpoint as a typed command, plus an offline SQLite mirror and cross-entity

  • Zammad MCP

    servosity/msp-skills/io.github.Servosity/zammad-mcp MCP server

    no license24★ repo

    Every Zammad ticket, article, and Knowledge Base operation as one CLI and MCP server - plus a

  • ThreatLocker MCP

    servosity/msp-skills/io.github.Servosity/threatlocker-mcp MCP server

    no license24★ repo

    Every ThreatLocker Portal API feature, plus the write operations the read-only tools lack and a

  • Copilot review

    appleboy/skills/plugins/copilot-review/skills/copilot-review Skill

    no license23★ repo

    Runs a single Copilot review check-fix cycle on a PR using gh CLI. Use this skill whenever the user wants to: check and fix Copilot review comments, request a Copilot code review on a PR, or iterate on PR feedback. Trigger on phrases like 'copilot review', 'fix PR comments', 'iterate on PR', 're-review', or when the user mentions 'gh pr' with 'copilot'. Combine with /loop for automated repeated cycles, e.g. '/loop 2m /copilot-review'.

    The same file is in 2 other repositories

  • Prompt audit

    appleboy/skills/plugins/prompt-audit/skills/prompt-audit Skill

    no license23★ repo

    Audit a prompt the user is about to send to Claude (or another coding AI) for completeness and effectiveness. Use this skill whenever the user shares a prompt and asks for feedback — phrases like "is this prompt good", "audit my prompt", "review this prompt", "will Claude understand this", "improve this prompt", "is this enough context". Also trigger proactively when you notice the user is about to dispatch a vague, under-specified, or over-constrained prompt for non-trivial work. Checks the 6 essential elements (goal, scope, existing patterns, constraints, verification, done definition), flags what's missing, explains why each gap matters, and produces an improved rewrite. Treat this skill as the litmus test for "Be Claude's PM" — if the prompt fails the audit, the work that follows will probably fail too.

    The same file is in 2 other repositories

  • Lyra

    joaquimscosta/arkhe-claude-plugins/plugins/ai/skills/lyra Skill

    23★ repo

    Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.

    The same file is in 3 other repositories

  • Workflow orchestration

    joaquimscosta/arkhe-claude-plugins/plugins/core/skills/workflow-orchestration Skill

    23★ repo

    Coordinate structured thinking and multi-agent parallel execution for complex tasks. Use when tackling multi-step projects, planning parallel work, breaking down complex problems, coordinating specialist tasks, facing architectural decisions, or when user mentions "workflow", "orchestration", "multi-step", "coordinate", "parallel execution", "structured thinking", "break this down", "plan this out", "how should I approach", or needs help planning complex implementations.

    The same file is in 2 other repositories

  • Creating worktree

    joaquimscosta/arkhe-claude-plugins/plugins/git/skills/creating-worktree Skill

    23★ repo

    Creates isolated git worktrees in .claude/worktrees/ with intelligent branch naming, auto-incrementing, and commit type detection (feat/fix/refactor). Supports manual descriptions and auto-generation from uncommitted git changes. Use when user requests to create worktree, start isolated work, parallel development, run /worktree command, or mentions "worktree".

  • Resolving pr issues

    joaquimscosta/arkhe-claude-plugins/plugins/git/skills/resolving-pr-issues Skill

    23★ repo

    Multi-agent review resolution with trust-but-verify methodology. Accepts a PR number/URL or a local code-review report file. Extracts review comments, verifies each with parallel agents using confidence scoring (0-100), filters false positives, presents a triage report for approval, then applies fixes and replies. Use when user runs /resolve-review, mentions "resolve PR comments", "address review feedback", "fix PR suggestions", "handle review comments", or "resolve review findings".

  • Generating stitch screens

    joaquimscosta/arkhe-claude-plugins/plugins/google-stitch/skills/generating-stitch-screens Skill

    23★ repo

    Generates Stitch screens from authored prompt files using MCP tools. Reads prompt sections, sends each to Stitch for generation, and fetches resulting images and code. Use when user mentions "generate in stitch", "create stitch screens", "run prompts in stitch", "send prompts to stitch", "generate screens from prompts", "fetch stitch images", or has prompt-v*.md files ready for generation. Requires Stitch MCP server.

  • Code review

    joaquimscosta/arkhe-claude-plugins/plugins/review/skills/code-review Skill

    23★ repo

    Multi-agent code review using the Pragmatic Quality framework. Orchestrates parallel review agents (CLAUDE.md compliance, bug scanning, git history, security) with independent confidence scoring to produce high-signal findings. Use when user runs /code-review, /review:code-review, requests a "code review", "review my changes", "PR review", or mentions "review diff", "review branch".

  • Ai citation tracker

    tinh2/skills-hub-registry/analysis/ai-citation-tracker Skill

    no license23★ repo

    Track brand mentions, URL citations, and share-of-voice across the 2026 AI search surface — ChatGPT (with browsing), Perplexity, Claude (with search), Google Gemini, Google AI Overviews, Bing Copilot, You.com, Phind, and Microsoft Copilot. Polls a configurable query set per engine on a schedule; logs whether your brand was mentioned, whether your URL was cited, who your competitors were, and how all of that moved week over week. Outputs share-of-voice dashboards, weekly delta reports, competitor matrices, and citation-gap analysis (queries where you SHOULD be cited but aren't). Closes the single biggest gap in legacy SEO platforms — Visibly AI / Semrush / Ahrefs / Moz / Conductor all under-cover this surface in 2026, even though AI Overviews now answer 30%+ of informational queries with zero clicks. TRIGGER on "AI citation tracking", "share of voice AI", "ChatGPT citations", "Perplexity citations", "AI Overview tracking", "brand mentions in AI", "LLM visibility", "GEO tracking", "AEO measurement", "AI search analytics", "track Claude citations".

  • Seo orchestrator

    tinh2/skills-hub-registry/analysis/seo-orchestrator Skill

    no license23★ repo

    The full open SEO suite for 2026 — a single orchestrator that composes 10+ specialized sub-skills into a daily, weekly, and on-demand workflow that owns the SEO + GEO surface for a site. Built as a direct, open, code-first answer to Visibly AI's "6 agents + €399/month" pitch. Composes (a) the 2026 audit (`/seo-audit-2026`), (b) GEO/AEO optimization (`/geo-optimize`), (c) content brief generation (`/seo-content-brief`), (d) AI citation tracking across ChatGPT/Perplexity/Claude/Gemini/AI Overviews (`/ai-citation-tracker`), (e) GSC pipeline (`/gsc-pull`), (f) internal link graph + semantic recommendations (`/internal-link-graph`), (g) cannibalization detection (`/content-cannibalization`), (h) backlink outreach (`/backlink-outreach`), and (i) WordPress publish + content writing if applicable. Produces ONE prioritized punch list each Monday morning ranked by impact × confidence × effort, plus daily AI-citation deltas and GSC top-mover alerts. Your data stays yours (SQLite/Postgres of your choice). Your code stays yours (everything is generated, nothing is gated behind a vendor login). TRIGGER on "SEO suite", "SEO orchestrator", "full SEO audit and ongoing", "SEO weekly report", "automate SEO", "SEO agents pipeline", "alternative to Visibly AI", "alternative to Semrush", "alternative to Ahrefs", "alternative to Conductor", "open-source SEO platform", "SEO command center".

  • Fable 5 codebase migration

    tinh2/skills-hub-registry/build/fable-5-codebase-migration Skill

    no license23★ repo

    Autonomous large codebase migration agent optimised for Claude Fable 5 (Mythos class). Scopes the migration, builds a dependency-ordered wave plan, executes incremental file changes, validates behaviour equivalence after each wave, and halts on first validation failure. Works on framework upgrades, API version bumps, language migrations, and architectural refactors spanning 10–500+ files.

  • Ship pipeline

    tinh2/skills-hub-registry/combo/ship-pipeline Skill

    no license23★ repo

    Full-stack app pipeline — build, test, review, and deploy across one or ALL repos. Scans CLAUDE.md, MEMORY.md, TODOs, open PRs, and issues for shippable work. Supports 'ship all' for multi-repo. Use when: 'build and ship', 'ship it', 'ship all', 'deploy everything', 'full pipeline', 'what needs shipping', 'end to end'.

  • Claude code artifacts

    tinh2/skills-hub-registry/docs/claude-code-artifacts Skill

    no license23★ repo

    Publishes structured, actionable artifacts from Claude Code sessions — PR walkthroughs, incident timelines, system explainers, release checklists, and security audits. Creates live web pages that auto-update as your session progresses, shareable with authenticated org members. Requires Claude Team or Enterprise (CLI 1.13576.0+, Artifacts enabled by admin).

  • Docs to context

    tinh2/skills-hub-registry/docs/docs-to-context Skill

    no license23★ repo

    Convert any pile of documents (PDF, Word, HTML pages, wiki exports, PowerPoint slides) into clean, LLM-ready markdown context: inventories the sources, picks the right extractor per file type (pdftotext or PyMuPDF for PDF, pandoc or mammoth for docx, readability extraction for HTML, python-pptx for slides), preserves structure (headings, real markdown tables, code blocks), strips boilerplate and navigation, chunks by heading hierarchy into 2-4k token files under context/<source>/ with an INDEX.md, and spot-checks three random chunks against the originals for fidelity. Use when the user says: convert these docs to markdown, prep these PDFs for Claude, turn this documentation into context, markitdown these files, extract text from these documents, make this wiki LLM-readable, ingest these docs, build a context folder.

  • Claude code 101

    tinh2/skills-hub-registry/education/claude-code-101 Skill

    no license23★ repo

    Interactive tutorial teaching Claude Code fundamentals -- file ops, git, testing, context management, and advanced patterns. Use when: 'teach me claude code', 'how do I use claude code', 'claude code tutorial', 'learn claude code', 'getting started with claude code', 'claude code basics', 'how does claude code work'.

  • Prompt engineering

    tinh2/skills-hub-registry/education/prompt-engineering Skill

    no license23★ repo

    Learn effective AI prompting through practice -- good vs bad prompts, context management, the STAR framework, and advanced techniques

  • Acp agent setup

    tinh2/skills-hub-registry/integration/acp-agent-setup Skill

    no license23★ repo

    Configure your development environment for Agent Client Protocol (ACP) Spec 1.0 — registers Claude Code, Codex, Devin Local, and OpenCode as ACP peers in Devin Desktop, Zed, or any ACP-compatible editor. Sets default skill loadouts per agent, enables Spaces context sharing, and validates the integration end-to-end.

  • Antigravity sdk

    tinh2/skills-hub-registry/integration/antigravity-sdk Skill

    no license23★ repo

    Scaffold, configure, and deploy custom AI agents with the Google Antigravity 2.0 SDK and agy CLI. Handles auth, AGENTS.md setup, skill installation, MCP server connections, parallel subagent workflows, and Managed Agents API calls. Use when the user wants to build or extend agents on the Antigravity 2.0 platform launched at Google I/O 2026.

  • Copilot model routing

    tinh2/skills-hub-registry/integration/copilot-model-routing Skill

    no license23★ repo

    Intelligent task-to-model routing for GitHub Copilot's multi-lab model picker (2026). Audits your workflow, assigns the right model (OpenAI / Anthropic / Google / Microsoft / Moonshot) to each task type, configures VS Code settings, and writes a routing matrix your team can commit. Covers Kimi K2.7 Code, Claude Sonnet 5, GPT-5.6 tiers, Gemini 2.5, and Phi-4. Includes cost-per-accepted-change pilot framework and admin policy checklist for Business/Enterprise plans.

  • Figma mcp

    tinh2/skills-hub-registry/integration/figma-mcp Skill

    no license23★ repo

    Connect the Figma Dev Mode MCP server to your AI coding agent and implement designs against your real component library. Covers MCP setup, Code Connect annotation, design-to-code implementation, and design token sync — all in one autonomous workflow.

  • Kiro custom agent

    tinh2/skills-hub-registry/integration/kiro-custom-agent Skill

    no license23★ repo

    Design, configure, and iterate on custom Kiro agents using the 1.0 Markdown agent format. Covers tool-access tags (read | write | shell | web), capability-based permissions.yaml, Natural Language Hooks, and inline MCP server declarations. Produces production-ready .kiro/agents/*.md files ready to commit.

  • Mcp apps builder

    tinh2/skills-hub-registry/integration/mcp-apps-builder Skill

    no license23★ repo

    Build MCP Apps — the interactive HTML UI primitive introduced in the 2026-07-28 MCP specification. Scaffolds UI templates, wires the JSON-RPC back-channel, declares tool manifests, and validates against the conformance suite. Use when adding visual interfaces (forms, data previews, approval flows) to an existing MCP server.

  • Mcp enterprise auth

    tinh2/skills-hub-registry/integration/mcp-enterprise-auth Skill

    no license23★ repo

    Audit and configure enterprise-managed MCP authorization (EMA) for organizations using Okta and Claude Team/Enterprise. Inventories current connector state, generates Okta provisioning configuration, validates scope assignments by IdP group, and produces a per-connector access report. Works across Claude Chat, Claude Code, and Cowork.

  • Mcp protocol migration

    tinh2/skills-hub-registry/integration/mcp-protocol-migration Skill

    no license23★ repo

    Migrates an MCP server from the original session-oriented protocol to the 2026 stateless spec (finalising July 28, 2026). Upgrades tool schemas to JSON Schema 2020-12, adds cloud-native routing headers, hardens OAuth 2.0/OIDC wiring, and wires W3C Trace Context for observability. Works on TypeScript and Python MCP SDK projects.

  • Opencode model router

    tinh2/skills-hub-registry/integration/opencode-model-router Skill

    no license23★ repo

    Sets up and optimises an OpenCode terminal-agent project: installs the CLI, configures multi-provider routing (Claude for hard tasks, Qwen/open-weight for fast tasks, Ollama for offline/air-gap), wires LSP servers for your stack, and enforces a spending-cap policy. Leaves you with a validated opencode.json and a three-tier /model switching workflow.

  • X mcp

    tinh2/skills-hub-registry/integration/x-mcp Skill

    no license23★ repo

    Connect the X (formerly Twitter) official XMCP server to your AI coding agent. Covers hosted and self-hosted setup, Bearer token and OAuth 2.0 authentication, connection verification, and four production-ready query workflows: mention monitoring, trend analysis, competitive intelligence, and bookmark ingestion.

  • Bootstrap

    tinh2/skills-hub-registry/meta/bootstrap Skill

    no license23★ repo

    Scaffolds a new project from a saved template with CLAUDE.md, initial memory, recommended pipeline, known pitfalls, and foundation validation.

  • Coding guardrails

    tinh2/skills-hub-registry/meta/coding-guardrails Skill

    no license23★ repo

    Installs behavioral guardrails against classic LLM coding failures and audits the current session against them. Encodes six enforceable rules: verify APIs exist in node_modules or docs before calling them, state assumptions before coding, prefer minimal diffs over rewrites, re-read the actual error text instead of pattern-matching a fix, never claim done without running the code, and express uncertainty numerically. Writes the rules into CLAUDE.md with an idempotent merge and demonstrates each with a before/after example from this repo. Use when you hear: install guardrails, coding guardrails, stop hallucinating APIs, the agent keeps rewriting everything, add LLM safety rules, make Claude more careful, audit this session, why did you claim it works, anti-slop rules, Karpathy-style guidelines, tighten your coding behavior.

  • Skill creator

    tinh2/skills-hub-registry/meta/skill-creator Skill

    no license23★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.

  • Skill scout

    tinh2/skills-hub-registry/meta/skill-scout Skill

    no license23★ repo

    Project-aware skill discovery and installation. Scans the current repo for stack signals and pain points, searches the skills-hub registry and local ~/.claude/skills, scores candidates on relevance, quality, and maintenance, dedupes against what is already installed, and presents a ranked shortlist with exact install commands. Use when you hear: find skills, what skills should I install, discover skills, recommend skills for this project, search skills-hub, is there a skill for X, set up my agent tooling, what agent skills exist for Flutter/Next.js/Python, install the right skills, skill recommendations, browse the skill registry, or when a recurring manual workflow in the session looks like it should be a pre-built skill.

  • Skill stack

    tinh2/skills-hub-registry/meta/skill-stack Skill

    no license23★ repo

    Curated skill bundle installer keyed to project archetype. Classifies the repo as one of six archetypes (Next.js SaaS, Flutter app, API backend, CLI tool, data pipeline, mobile game), maps it to a 5-8 skill stack covering the whole lifecycle (build, test, review, deploy, docs), checks what is already installed, installs the missing pieces with a user-visible manifest, and records the stack plus rationale in .claude/skill-stack.md. Use when you hear: set up skills for this project, skill stack, install a skill bundle, what skills does a Next.js app need, bootstrap my agent tooling, starter skills, equip this repo, recommended skill set, new project skill setup, or when onboarding a fresh repo that has no skills configured yet.

  • Claude agent billing audit

    tinh2/skills-hub-registry/ops/claude-agent-billing-audit Skill

    no license23★ repo

    Audits your codebase for Claude Agent SDK usage affected by Anthropic's June 15 2026 billing split. Scans for claude -p invocations, GitHub Actions steps, and SDK imports; estimates monthly token cost per pipeline; flags automations that will hard-stop when credits run out; and produces a prioritized migration checklist with model-routing recommendations to stretch your credit pool.

  • Mcp connection audit

    tinh2/skills-hub-registry/ops/mcp-connection-audit Skill

    no license23★ repo

    Audits all connected MCP servers: auth type (OAuth vs static token), token expiry, available tools, and connection health. Flags servers that can migrate to claude mcp login OAuth flow and detects silent auth failures before they break agentic runs.

  • Acp multi agent

    tinh2/skills-hub-registry/productivity/acp-multi-agent Skill

    no license23★ repo

    Sets up and orchestrates multi-agent workflows via the Agent Client Protocol (ACP) inside Devin Desktop or any ACP-compatible editor. Configures Claude Code, Codex, Devin Local, and custom agents with shared Spaces context, then validates the setup with an end-to-end smoke test.

  • Ai spend optimizer

    tinh2/skills-hub-registry/productivity/ai-spend-optimizer Skill

    no license23★ repo

    Audits your AI coding tool costs across GitHub Copilot, Claude Code, Cursor, Windsurf, and other subscriptions. Analyzes usage patterns, calculates real monthly costs under token-based billing, flags budget risk, and generates a concrete optimization plan — including when switching tools makes financial sense.

  • Background agent pr driver

    tinh2/skills-hub-registry/productivity/background-agent-pr-driver Skill

    no license23★ repo

    Configures Claude Code's July 2026 async workflow: background agents that auto-commit, push, and open draft PRs when worktree tasks finish. Sets up Notification hooks for agent_needs_input and agent_completed events, enforces Manual permission mode, and wires dynamic workflow sizing. Lets you dispatch multiple agents in the morning and receive reviewable PRs without watching the terminal.

  • Claude code hooks setup

    tinh2/skills-hub-registry/productivity/claude-code-hooks-setup Skill

    no license23★ repo

    Autonomous Claude Code hooks configurator. Audits your project's existing .claude/settings.json hook setup, then installs a production-grade suite: PreToolUse safety enforcement (blocks rm -rf, sudo writes, secret leaks), PostToolUse auto-formatting and lint gates, SessionStart dynamic context injection, and FileChanged secret detection. Generates hook scripts and wires them into settings.json at project scope.

  • Claude model router

    tinh2/skills-hub-registry/productivity/claude-model-router Skill

    no license23★ repo

    Auto-select the optimal Claude model tier (Haiku 4.5, Sonnet 4.6, or Opus 4.8) for each task based on complexity signals, latency requirements, and budget constraints — minimizes cost without sacrificing output quality.

  • Copilot credits audit

    tinh2/skills-hub-registry/productivity/copilot-credits-audit Skill

    no license23★ repo

    Audits GitHub Copilot AI Credit usage patterns before the June 2026 flex-billing transition. Pulls usage data from the GitHub API, identifies high-credit-cost workflows (agentic sessions, cloud review, heavy chat), recommends the right plan tier (Pro / Pro+ / Max), and generates per-user budget configs for team admins. Run before June 1, 2026 — or any time you want to understand and reduce Copilot spend.

  • Cursor cloud agent workflow

    tinh2/skills-hub-registry/productivity/cursor-cloud-agent-workflow Skill

    no license23★ repo

    Sets up and orchestrates Cursor 3 cloud agent workflows using /in-cloud for isolated VM subagents, /babysit for overnight PR preparation, Bugbot for automated pre-merge review, and reusable environment snapshots. Use after upgrading to Cursor 3.7+ or when agentic work needs to persist past your local machine.