メニュー
SkillsMP は cardinalconseils/make-automation-specialist から 38 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
収集済み skill 38 件中 38 件を表示しています。
Designs AI agent architecture for Make.com scenarios. Determines model selection, tool inventory, memory strategy, looping pattern, and output contract. Called by scenario-orchestrator during System Design phase when ai_required is true, or directly by…
原文の言語: 英語
Pre-push blueprint JSON review for Make.com scenarios. Checks structural integrity, connection IDs, mapper references, filter logic, and error handler coverage before any scenario_update call.
原文の言語: 英語
Fetches exact Make.com module documentation before any blueprint is designed. Returns precise field names, required vs optional parameters, data types, and enumerated values. Eliminates improvisation and ensures first-shot accuracy.
原文の言語: 英語
Decides whether an automation should be built as a deterministic Make.com scenario, as an AI Agent, or as a hybrid (scenario shell with an AI Agent at the one indeterministic step). Produces a Routing Verdict recorded in the plan. Called before any blueprint…
原文の言語: 英語
Taxonomy-first failure diagnosis for Make.com. Loads the failure taxonomy, classifies errors by pattern code, states expected vs actual, and prescribes the exact fix. Always consult this before guessing.
原文の言語: 英語
Live retrieval of Make.com product documentation from help.make.com, with a local cache. Answers conceptual questions — routers, iterators, error-handler directives, operations and billing, AI Agent semantics, plan limits — that the MCP module docs do not…
原文の言語: 英語
Automation portfolio discovery interview. Guides the user to articulate every automation they need before any design begins. Produces a prioritized portfolio list. Called by scenario-orchestrator during the Kickstart phase.
原文の言語: 英語
Writes the kickstart plan document from the collected portfolio. Called by kickstart-planner agent at end of Phase 2. Produces the plan file that the user reviews and approves before any artifacts are generated.
原文の言語: 英語
Constructs a structured AutomationPlan from a business requirement. Maps requirements to Make.com modules, designs error handling, and runs the guardrail checklist. Called by automation-planner and automation-specialist agents.
原文の言語: 英語
Library of proven Make.com AI agent patterns. Returns the matching pattern blueprint — Mermaid diagram, module sequence, and wiring notes — based on the task type identified by ai-agent-designer. Called during System Design phase before plan-builder.
原文の言語: 英語
Fetches exact Make.com AI module specifications before any AI agent blueprint is built. Extends docs-researcher specifically for LLM/AI modules (Anthropic, OpenAI, Google AI, Hugging Face, Make.com AI Agent). Returns precise field names, model enums, token…
原文の言語: 英語
Sends Telegram alerts via Telnyx MCP when automations fail. Called by post-execute and on-error hooks. Handles rate limiting, fallback logging, and message formatting.
原文の言語: 英語
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…
原文の言語: 英語
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.
原文の言語: 英語
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.
原文の言語: 英語
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,…
原文の言語: 英語
Estimates Make.com operation counts and monthly costs for automation plans. Tracks actual usage against plan limits and warns when approaching thresholds.
原文の言語: 英語
Five adversarial voices that challenge an automation blueprint before significant resources are committed. Reads the discovery-to-blueprint output (process map + pre-mortem), each voice gives one honest paragraph, top concerns are extracted, user responds to…
原文の言語: 英語
Builds Make.com data structures (JSON schemas) and data stores. Called during bootstrap gap analysis when automations require persistent storage, and on-demand during sprint. All writes are gated Level 1.
原文の言語: 英語
Generates Mermaid flowcharts from parsed scenario data (scenario-reader output). Called by scenario-reporter and automation-planner. Saves diagrams to .make/diagrams/.
原文の言語: 英語
Conversational automation discovery that runs BEFORE any scenario design. Walks through a business process one question at a time, builds a structured automation blueprint: process map, data shapes, tech fit, Gary Klein pre-mortem risk gate, and next-step…
原文の言語: 英語
Error handling patterns, directives, and audit checklists for Make.com scenarios
原文の言語: 英語
Writes timestamped execution logs and changelog entries after every automation action. Called by post-execute hook. Append-only — never overwrites the audit trail.
原文の言語: 英語
Cross-cutting Make.com failure patterns — schema drift, eventual consistency, webhook replay, timezone drift, missing pagination, fire-and-forget async, and incomplete execution queue leaks. Load when designing scenarios to prevent these patterns proactively.
原文の言語: 英語
Make.com built-in functions, expression syntax, and module field expression patterns
原文の言語: 英語
Complete reference for all Make.com tools available via MCP and CLI. Classifies every operation as deterministic (read-only, safe) or non-deterministic (write, side effects, requires approval). Defines tool selection rules and system design protocol.
原文の言語: 英語
Scaffolds new MCP servers for APIs without native Make.com modules, and manages existing MCP connections in Claude Code. Two modes — scaffold (generate server code) and manage (check/configure existing MCPs). No Make.com MCP calls — file writes and Bash only.
原文の言語: 英語
Persistent project memory for Make.com automation projects. Reads and writes facts, decisions, gotchas, and session snapshots to .make/memory/. Called by on-project-open (read) and on-session-end (write).
原文の言語: 英語
Runs on first project open when .make/workspace.json does not exist. Detects available MCPs, connects to Make.com, lists all scenarios, and writes workspace.json. Shows setup instructions if Make MCP is missing.
原文の言語: 英語
Parses Make.com scenario blueprints into structured, analyzable form. Detects issues (missing error handlers, hardcoded credentials, inefficient triggers) and flags data sensitivity for compliance scanning.
原文の言語: 英語
Sequential scenario build executor. Iterates through an approved automation portfolio, builds each scenario in Make.com one at a time with narration and per-scenario confirmation, writes logs, and produces a factory report. Called by scenario-orchestrator…
原文の言語: 英語
Telnyx platform expertise — SMS, voice, SIP, AI assistants, WebRTC, phone number management
原文の言語: 英語
Fetches the current live blueprint from Make API and saves it as the authoritative local file before any editing begins. Entry point for the local-edit workflow.
原文の言語: 英語
Executes the full validated push cycle for a local blueprint: review → plan check → API push → validate isinvalid:false → log. The only sanctioned path for writing blueprint changes to Make.
原文の言語: 英語
Add new failure patterns to the Make Failure Taxonomy. Ensures correct categorization, consistent format, and changelog entry. Use after diagnosing a failure not currently in the taxonomy.
原文の言語: 英語
Behavioral constraints for Make.com autonomous agents — what may and may not be done without explicit human confirmation during /factory and /make sessions
原文の言語: 英語
Catalog of Make.com automation anti-patterns — detect and reject before building or approving. Covers triggers, data flow, error handling, and scenario structure.
原文の言語: 英語
Reverse-engineers existing Make.com scenarios into project context artifacts. Called by /kickstart when user selects "existing project" mode.
原文の言語: 英語