Skip to main content
Glama
Flisk App Builder

Flisk App Builder

Official

project_init

Create or refresh a Flisk project's configuration and generated files in an existing directory, or clone a starter template into a new directory for setup.

Instructions

Create a Flisk project with flisk project --yes: in projectPath (an existing directory; default the server's directory) write .flisk/project.json and generate its files, or, with template, clone a starter project into a new directory there (then call project_init again with projectPath set to the clone to configure it). Inside an existing project it refreshes that project's generated files instead and never overwrites its project.json. Returns the command's text output.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "project_init"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoTemplate only: directory to clone into, relative to projectPath or absolute (default: the starter name, or its repository name)
templateNoClone this starter project instead of creating a blank one
agentSkillsNoBlank project only: write the Flisk agent skills and AGENTS.md (default true)
projectPathNoAbsolute path to an existing directory to create the project in (or to clone the template from)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.4.69
    • changedInput schema / properties / path / description
      Previous value: -"Template only: directory to clone into, relative to projectPath or absolute (default: the template's repository name)"New value: +"Template only: directory to clone into, relative to projectPath or absolute (default: the starter name, or its repository name)"
  2. Changed1 schema field changedv1.4.59
    • changedInput schema / properties / template / enum
      Previous value: -[
      -  "demo",
      -  "restaurant",
      -  "saas",
      -  "erp",
      -  "user-management",
      -  "ecommerce",
      -  "example",
      -  "agent-stack",
      -  "swarm",
      -  "security",
      -  "super-agent",
      -  "langgraph",
      -  "tool-loop",
      -  "launch",
      -  "portal",
      -  "fullstack"
      -]New value: +[
      +  "demo",
      +  "restaurant",
      +  "saas",
      +  "erp",
      +  "user-management",
      +  "ecommerce",
      +  "example",
      +  "agent-stack",
      +  "swarm",
      +  "security",
      +  "super-agent",
      +  "langgraph",
      +  "tool-loop",
      +  "next-postgres",
      +  "launch",
      +  "portal",
      +  "fullstack"
      +]
  3. Changed1 schema field changedv1.4.33
    • changedInput schema / properties / template / enum
      Previous value: -[
      -  "demo",
      -  "restaurant",
      -  "saas",
      -  "erp",
      -  "user-management",
      -  "ecommerce",
      -  "example",
      -  "agent-stack",
      -  "launch",
      -  "portal",
      -  "fullstack"
      -]New value: +[
      +  "demo",
      +  "restaurant",
      +  "saas",
      +  "erp",
      +  "user-management",
      +  "ecommerce",
      +  "example",
      +  "agent-stack",
      +  "swarm",
      +  "security",
      +  "super-agent",
      +  "langgraph",
      +  "tool-loop",
      +  "launch",
      +  "portal",
      +  "fullstack"
      +]
  4. Changed1 schema field changedv1.4.25
    • changedInput schema / properties / template / enum
      Previous value: -[
      -  "demo",
      -  "restaurant",
      -  "saas",
      -  "erp",
      -  "user-management",
      -  "ecommerce",
      -  "example",
      -  "agent-stack"
      -]New value: +[
      +  "demo",
      +  "restaurant",
      +  "saas",
      +  "erp",
      +  "user-management",
      +  "ecommerce",
      +  "example",
      +  "agent-stack",
      +  "launch",
      +  "portal",
      +  "fullstack"
      +]
  5. First observedv1.4.17

TDQS

A4.1/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description discloses the concrete side effects: writing .flisk/project.json and generating files, cloning a starter, refreshing generated files inside an existing project, and never overwriting project.json. It also states the return value ('the command's text output'), which is useful given there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loads the main action and keeps all clauses relevant. The long first sentence is somewhat run-on, but no sentence is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a project-creation tool with four parameters, no output schema, and useful annotations, the description covers the main modes, defaults, side effects, and return format. Minor omissions like error behavior or network needs for template cloning are acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already explains path, template, agentSkills, and projectPath in detail. The description adds only marginal meaning, notably the default for projectPath and the template two-step usage; most parameter semantics are already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Create a Flisk project') and covers its main modes: blank creation, template cloning, and refreshing an existing project. It does not explicitly differentiate from siblings such as project_import or project_templates, so it falls short of the highest clarity tier.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context for when and how to use the tool, including the two-step pattern for templates ('then call project_init again with projectPath set to the clone'). It does not name alternatives or say when not to use it, but the operational guidance is strong.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.