skills/mkn-constructor/SKILL.md
Construct and scaffold Machina agent-templates and connectors with correct YAML structure, then install them via MCP. Use when users ask to "create a template", "scaffold an agent", "init template", "build a new connector", "install template", "validate template", "analyze template", "trace agent", or "configure secrets".
npx skillsauth add machina-sports/machina-templates mkn-constructorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
End-to-end skill for building, validating, and deploying Machina agent-templates and connectors.
Procedural guides for each lifecycle stage:
| Reference | Description | |-----------|-------------| | init.md | Scaffold new template project from scratch | | create.md | Generate individual YAML components | | validate.md | Check YAML files against correct patterns | | install.md | Import templates via MCP (local or Git) | | analyze.md | Analyze template structure and dependencies | | trace.md | Trace agent execution chain with variable propagation | | secrets.md | Configure vault secrets for connectors | | api.md | MCP operations for all entities (CRUD, execute, search) | | yaml-reference.md | Complete YAML syntax and patterns | | connectors.md | All available connectors with docs | | frontend-api.md | Next.js frontend API integration |
Authoritative field definitions for every Machina entity:
| Schema | Entity |
|--------|--------|
| agent.md | Agent definition |
| connector.md | Connector (PyScript + REST API) |
| document.md | Document task type |
| mapping.md | Data transformation mapping |
| prompt.md | Prompt definition + JSON Schema |
| setup.md | _install.yml + _index.yml |
| skill.md | SDK skill registration |
| workflow.md | Workflow + task types |
When the user triggers this skill, load the appropriate reference:
| User Says | Reference | |-----------|-----------| | "init template", "scaffold template", "new template project" | init.md | | "create agent", "create workflow", "scaffold YAML" | create.md | | "validate", "check YAML", "verify template" | validate.md | | "install", "import", "deploy template" | install.md | | "analyze", "what's in this template", "overview" | analyze.md | | "trace", "execution chain", "variable flow", "debug agent" | trace.md | | "secrets", "credentials", "configure API key" | secrets.md | | "API", "MCP operations", "search agents", "execute workflow" | api.md | | "YAML syntax", "task types", "expression syntax", "foreach" | yaml-reference.md | | "connectors", "list connectors", "connector docs" | connectors.md | | "frontend", "Next.js", "API integration", "document search" | frontend-api.md | | "report bug", "found issue", "feedback", "suggest improvement" | Show Feedback & Contributing section below |
For YAML field specifics, read the relevant schema from schemas/.
Name: mkn-constructor-check-setup
Validates that the doc-structure document exists and returns its content.
| Input | Default | Description |
|-------|---------|-------------|
| document_name | doc-structure | Document to check |
| Output | Description |
|--------|-------------|
| doc-structure | Document content |
| check-status | Workflow execution status |
Found a bug, unexpected behavior, or have an improvement idea while using this skill?
skill:mkn-constructormainWhen the user encounters an error, unexpected scaffold output, or expresses frustration with a skill behavior, proactively mention this section and suggest opening an issue.
$.get('field') — never ${field} or $fieldprompts: array (not prompt:) with instruction: (not messages:)filetype: (not type:) and filename: (not script:)devops
# Project Manifest Generator Generates a draft `project.manifest.yml` for a Machina template by statically scanning a list of workflows and aggregating the credentials, connectors, datasets and agents they reference. Built to scale **Sprint 1A** of the Pipeline Platform Cleanup (the hand-written botandwin manifest at `entain-templates`) to every template in `machina-templates` without writing each one by hand. ## What it does 1. **Deterministic extraction (always)** — a pyscript connector wa
data-ai
# Press Conference Extractor Skill This skill processes a raw transcript from a press conference and extracts structured insights. ## Use Case Use this skill when you have a long text of a press conference and need to quickly identify the key topics discussed, who said what, and which quotes are the most impactful for news reporting or analysis. ## Inputs - `transcript`: A single long string containing the full text of the press conference. ## Example Output The skill returns a JSON objec
testing
# Post-Match Tweet Thread Skill Receives a raw match object and returns a structured 5-tweet thread in Brazilian Portuguese ready to be scheduled on the team's social account. ## Workflow: `generate-tweet-thread` Takes a single input `match_data` (a JSON object with the match facts) and returns a thread of exactly 5 perspective-tagged tweets. Each tweet is character-counted server-side so the publisher doesn't have to. ### Tweet positions | # | role | content angle
testing
# News Monitor: Storylines Skill This skill monitors news articles for a given entity and clusters them into distinct storylines. ## Use Cases - Tracking media coverage for a specific player, team, or league. - Identifying emerging narratives and trending topics. - Summarizing key events over a specific time period. ## How to Use Invoke the skill through its entry-point workflow, `news-monitor-workflow`, providing the following inputs: - `entity` (string): The name of the entity to search