composio-community

Automatically analyze and tag untagged [Gorgias](https://composio.dev/toolkits/gorgias) tickets based on content.

Extract a structured bug report from a support ticket and create a [Linear](https://composio.dev/toolkits/linear) issue.

Summarize customer support/sales calls from [Dialpad](https://composio.dev/toolkits/dialpad) or [Leexi](https://composio.dev/toolkits/leexi) call logs

Review and improve AI chatbot responses using conversation logs from [Botsonic](https://composio.dev/toolkits/botsonic), [Docsbot](https://composio.dev/toolkits/docsbot-ai), or [Landbot](https://composio.dev/toolkits/landbot)

Sync customer data between [Gorgias](https://composio.dev/toolkits/gorgias) and [HubSpot](https://composio.dev/toolkits/hubspot) - find mismatches and missing contacts

Send CSAT follow-up emails to customers after ticket resolution via [Gmail](https://composio.dev/toolkits/gmail)

Full customer lookup across [Gorgias](https://composio.dev/toolkits/gorgias) tickets and [HubSpot](https://composio.dev/toolkits/hubspot) CRM.

Identify churned or at-risk customers and draft personalized winback emails

Workflow for building scalable messaging systems on Microsoft Azure using queues, event-driven architecture, pub/sub systems, service buses, and cloud-native communication patterns.

Workflow for implementing observability systems on Microsoft Azure using logging, monitoring, tracing, telemetry, metrics, dashboards, and production-grade cloud diagnostics.

Workflow for creating procedural systems in Blender using Geometry Nodes, procedural materials, node-based modeling, and non-destructive generation techniques.

Workflow for creating precise hard surface models in Blender using clean topology, subdivision workflows, bevel systems, and production-ready modeling techniques.

Workflow for using Claude to generate Blender Python scripts, automate 3D workflows, and create procedural scenes, animations, and assets directly inside Blender.

End-to-end workflow for setting up Blender, rigging a character, and creating a simple animation with a clear output (rendered animation).

Workflow for performing SEO research, content optimization, keyword strategy, technical SEO analysis, and search-focused content generation using Claude.

Workflow for running background reasoning, reflective analysis, hidden planning layers, and iterative self-improvement systems to improve Claude’s execution quality across complex tasks.

Generate a targeted lead list with Apollo — filter by title, company size, industry, tech stack — and export to CSV/HubSpot/Sheets. Use when the user says "build me a prospect list", "find 100 VPs of X", or "source leads for the campaign".

Build a competitive battlecard — when to land-grab vs. when to walk away, key wedges, objection handling, landmines to set. Use on "build a battlecard against <competitor>", "how do we beat <X>", or "compete review".

Check Google Calendar availability and book meetings — find slots across time zones, send invites, hold prep time. Use on "find time with X", "book a demo", "check my availability next week".

Write high-response cold emails — short, specific, prospect-centric. Use when the user asks to "write a cold email", "rewrite my outbound", or "this email is getting no replies". Produces 3 variants with rationale.

Run a cold email outreach campaign via Gmail. Use when the user wants to send personalized cold emails to a list of prospects, draft outbound sequences, or launch a small outreach batch from a CSV/sheet of leads. Proactively invoke when the user mentions "send cold emails", "outreach campaign", or "blast my leads".

Prep for a discovery call — research the account, the attendee, set hypothesis for their pains, write the question stack, define success. Use on "prep for my discovery call", "research this account before tomorrow", or "what should I ask <prospect>?".

Send follow-up emails on threads that haven't replied — 3, 7, 14 day cadence with fresh angles. Reads sent folder, identifies no-reply threads, drafts context-aware follow-ups. Trigger on "send follow-ups", "bump my cold emails", or "who hasn't replied?".

Build a go-to-market launch plan for a new product, feature, or segment — audience, channels, narrative, sequencing, metrics. Use on "launch plan for <product>", "GTM for the new feature", or "how do we take this to market?".

Scrape App Store (iOS) and Google Play reviews for any app and extract pain points, praise, feature requests, churn signals, and competitor mentions. Returns a rating distribution, themed quote clusters, and a ranked feature request list grounded in real user language.

Company discovery and deep research skill. Researches a company's product and ICP, discovers target companies to sell to using Browserbase Search API, deeply researches each using a Plan→Research→Synthesize pattern, and scores ICP fit — compiled into a scored research report and CSV. Supports depth modes (quick/deep/deeper) for balancing scale vs intelligence. Use when the user wants to: (1) find companies to sell to, (2) research potential customers, (3) discover companies matching an ICP, (4) build a target company list, (5) do market research on prospects. Triggers: "find companies to sell to", "company research", "find prospects", "ICP research", "target companies", "who should we sell to", "market research", "lead research", "prospect list".

Auto-register or RSVP to events on Lu.ma, Eventbrite, Meetup, Hopin, and custom event sites — given an event URL and an attendee profile, the skill drives a real cloud browser to fill the registration form, answer screener questions from a saved profile, and stop before final submit for human confirmation. Tracks RSVPs to a local pipeline. Useful for hackathons, meetups, conferences, and product launches.

Monitor GitHub repositories — stars, forks, issues, PRs, contributors, releases, and commit cadence — and produce a project-health snapshot with trend signals (active / declining / stale). Useful for OSS competitive intel, dependency due-diligence, and researching a company's engineering output.

Scrape Glassdoor for company reviews, salary data, interview experiences, and culture signals. Returns ratings breakdown, top pro / con quotes, salary ranges by role and level, and an interview-process summary — useful for job research, sales personalization, and competitive talent analysis.

Surface top Hacker News threads on a topic and extract the high-signal comments. Finds Show HN, Ask HN, and news discussions, sorts by score, pulls top comments, and clusters them by sentiment (positive / skeptical / critical) with linked alternatives mentioned in the thread.

Auto-fill job applications across Greenhouse, Lever, Ashby, Workday, and custom company forms — given a candidate profile JSON (name, contact, resume URL, work history, links) and a job posting URL, the skill drives a real cloud browser to fill every visible field, attach the resume, and pause for human confirmation before final submit. Companion to `job-tracker` (which finds the roles).

Scrape job listings from company careers pages, ATS APIs (Greenhouse, Lever, Ashby), and LinkedIn Jobs; normalize roles into a structured pipeline with salary ranges, required skills, and hiring signals. Use to monitor a company's hiring, track personal applications, or surface what teams competitors are growing.

Lists all inference providers offered during NemoClaw onboarding. Use when explaining which providers are available, what the onboard wizard presents, or how inference routing works. Trigger keywords - nemoclaw inference options, nemoclaw onboarding providers, nemoclaw inference routing, switch nemoclaw inference model, change inference runtime, nemoclaw local inference, ollama nemoclaw, vllm nemoclaw, local model server, openai compatible endpoint.

Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when deploying NemoClaw to a remote VM, onboarding a Brev instance, or migrating away from the legacy `nemoclaw deploy` wrapper. Trigger keywords - deploy nemoclaw remote gpu, nemoclaw brev cloud deployment, nemoclaw sandbox hardening, container security, docker capabilities, process limits, nemoclaw telegram, telegram bot openclaw agent, openshell channel messaging.

Describes the NemoClaw plugin and blueprint architecture and how they orchestrate the OpenClaw sandbox. Use when looking up architecture, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw plugin blueprint structure, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.

Reviews and approves blocked agent network requests in the TUI. Use when approving or denying sandbox egress requests, managing blocked network calls, or using the approval TUI. Trigger keywords - nemoclaw approve network requests, sandbox egress approval tui, customize nemoclaw network policy, sandbox egress policy configuration.

Lists the hardware, software, and container runtime requirements for running NemoClaw. Use when verifying prerequisites before installation. Trigger keywords - nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw quickstart, install nemoclaw openclaw sandbox, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.

Backs up and restores OpenClaw workspace files before destructive operations such as sandbox rebuilds. Use when downloading workspace files from a sandbox, uploading restored files into a new sandbox, or preserving sandbox state across rebuilds. Trigger keywords - nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.

Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task. Use when discovering NemoClaw capabilities, choosing the right skill, or orienting in the project. Trigger keywords - skills, capabilities, what can I do, help, guide, index, overview, start here.

Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant integration, or the .agents/skills/ directory. Trigger keywords - nemoclaw agent skills, ai coding assistant, cursor, claude code, copilot.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.