Business process evaluation and smart automation specialist. Turns Claude into a Make.com expert: conversational automation building, scenario auditing, AI agent creation, compliance assessment, and Telegram alerting.
Build an AI-powered agent inside Make.com. Guides model selection, tool inventory, memory strategy, and pattern choice — then designs and builds the scenario with full approval gates.
Audit Make.com scenarios for errors, missing error handlers, inefficiencies, compliance risks, and cost issues. Proposes ranked fixes and executes after approval.
Review a Make.com blueprint JSON for issues before pushing to the API.
Dispatch the `failure-diagnostician` agent to diagnose a Make.com scenario failure.
Generate a Mermaid flowchart for a Make.com scenario. Read-only — never modifies anything.
Designs and builds AI agents inside Make.com scenarios. Guides model selection, tool inventory, memory strategy, and looping pattern — then produces a validated blueprint and builds the scenario with full approval gates. Triggered by /agent command.
Generates detailed AutomationPlans from a business requirement. Produces step breakdowns, cost estimates, risk assessments, Mermaid diagrams, and Make.com module docs links. Never executes — planning only. Use /plan.
Primary Make.com automation specialist. Discovers business needs through conversation, generates automation plans with cost estimates, waits for approval, then executes via Make.com MCP. Explains everything in plain language. Responds to /make and /build.
Autonomous multi-hop research specialist for Make.com integrations. Investigates service APIs, webhook patterns, rate limits, and app module behaviors before building. Use when planning an integration with an unfamiliar service — not for quick lookups.
Diagnoses Make.com scenario failures using taxonomy-first protocol. Loads the failure taxonomy, classifies the error by pattern code, states expected vs actual behavior, and prescribes the exact fix. Dispatched by /diagnose command or when a Make error is described.
Diverge-then-converge for Make.com automation planning. Fires when the user has a business problem but no clear automation direction. Takes messy impulses like 'I'm wasting time on X' or 'I need to be more efficient' and produces ONE pointed direction sentence — the input that discovery-to-blueprint or kickstart-intake needs. Always routes to the next skill in the factory chain. Never produces standalone output.
Surface-level compliance risk assessment for Make.com scenarios. Checks GDPR, Quebec Law 25, PCI-DSS, and HIPAA. NOT legal advice — flags risks for human review.
Sets up and validates Make.com connections. Three modes — manage (check existing), setup-guide (step-by-step OAuth/API key instructions), credential-request (team-shared connections). Called during bootstrap gap analysis and pre-sprint checks.
Core identity, behavioral rules, and action classification for the Make.com Automation Specialist. Defines the deterministic/non-deterministic framework, system design protocol, approval gates, plain-language communication, cost awareness, compliance surface, and Telegram alert escalation.
Estimates Make.com operation counts and monthly costs for automation plans. Tracks actual usage against plan limits and warns when approaching thresholds.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin that turns any project into an intelligent Make.com automation workspace. You describe a business problem in plain English, Claude plans the automation, you approve it, and Claude builds it in Make.com.
.make/diagrams/..make/ folder with timestamps.Run this command once to install the plugin for all your projects:
claude plugin install make-automation-specialist@make-automation-specialist --scope user
Or install it only for one specific project (run from inside that project):
claude plugin install make-automation-specialist@make-automation-specialist --scope project
To verify it installed:
claude plugin list
You should see make-automation-specialist in the list.
Note: The first time you install, Claude Code needs to know where to find this plugin's marketplace. Add this to your
~/.claude/settings.jsonunderextraKnownMarketplaces:"make-automation-specialist": { "source": { "source": "github", "repo": "cardinalconseils/make-automation-specialist" } }
Copy the example env file and fill in your API keys:
cp .env.example .env
Open .env and set:
MAKE_API_KEY=your_make_api_key_here
MAKE_TEAM_ID=your_make_team_id_here
Where to find these:
/team/Open your Claude Code MCP config file. On Mac it's at:
~/.claude/claude_desktop_config.json
Add this inside the "mcpServers" block:
"make": {
"command": "npx",
"args": ["-y", "@anthropic-ai/mcp-server-make"],
"env": {
"MAKE_API_KEY": "your_make_api_key_here",
"MAKE_TEAM_ID": "your_make_team_id_here"
}
}
This lets Claude ping you on Telegram when something breaks and can't be auto-fixed.
@BotFather/newbot and follow the steps to create a bot — save the API token it gives youhttps://api.telegram.org/bot<YOUR_TOKEN>/getUpdates
to find your chat ID (it's the number next to "id":).env:
TELNYX_API_KEY=your_telnyx_api_key
TELEGRAM_CHAT_ID=your_telegram_chat_id
That's it. The on-project-open hook runs automatically and:
.make/ folder structure| Command | What it does |
|---|---|
/make [description] | Start an automation conversation. Discovers your workspace, designs the scenario, gets your approval, then builds it. |
/build [description] | Alias for /make. |
/plan [description] | Generate a detailed plan with cost estimate, risk level, and Mermaid diagram — without building anything. |
/factory [idea] | Full automation factory: Kickstart → Bootstrap → System Design → Sprint. Design your entire automation portfolio in one session, then build them all. |
/kickstart [idea] | Discovery only — guided interview + context artifacts. Does not build. |
/agent [description] | Design and build an AI-powered agent inside a Make.com scenario. Guides model selection, tool inventory, and memory strategy. |
npx claudepluginhub cardinalconseils/make-automation-specialist --plugin make-automation-specialist5-phase feature lifecycle toolkit — discover, design, sprint, review, release. Includes Stitch MCP design integration, 11-element discovery, iteration loops, quality gates, and environment promotion. From idea to production.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.