Laviya Agent Skills

io.github.kartegagithubPublished by GitHub account kartegagithubv0.1.32Updated Nov 7, 2026

Laviya AI Orchestration MCP runtime for IDE and agent integrations.

VerifiedSTDIODesktop onlyProductivity & WorkflowKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Laviya MCP runtime that lets an assistant manage Laviya projects, tasks, sprints, test cases and wikis, and run agent delivery workflows.

What you can do
  • List projects, tasks and sprints, and fetch a single task
  • Create tasks, sprints, test cases and wiki pages, and update task descriptions or wiki content
  • Assign tasks, link and unlink tasks, add comments, and attach files to tasks
  • Start, complete and cancel local work and delivery or execution runs, and report token usage
  • Check personal work status and run diagnostics
When to use it
Useful when a team runs its planning and delivery in Laviya and wants an IDE or agent assistant to create and track tasks, sprints, test cases and wiki pages, or to drive Laviya delivery and execution runs from the editor.
Requirements
Runs as a local stdio process from the npm package laviya-mcp-server, so Node.js is needed. Requires the secret LAVIYA_API_KEY. Optional overrides: LAVIYA_AGENT_UID, LAVIYA_BASE_URL, LAVIYA_GLOBAL_CONFIG_PATH and LAVIYA_LOG_LEVEL. Projects are configured per repository via .laviya/project.json or .laviya.json. Network access to the Laviya API is required.
Before you install
The API key LAVIYA_API_KEY is required and authenticates the runtime against Laviya. Many tools write to shared project data: creating and assigning tasks, sprints, test cases and wikis, adding comments and links, uploading files, and starting or completing delivery and execution runs. Work items may carry an ExecutionPolicy that restricts agents to read-only analysis or review and requires truthful completion evidence. Task and wiki content is sent to the Laviya API.

Installation

In SourceWeft

  1. Open Laviya Agent Skills in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Laviya Agent Skills

Laviya Agent Skills is a repository of reusable orchestration assets for IDE and agent integrations. It provides a production-oriented MCP runtime, shared orchestration prompt assets, and client-specific artifacts for tools such as Cursor and Claude.

Packages

  • laviya-agent-skills: reusable prompt, rule, and skill asset bundle for Node-based tooling
  • laviya-mcp-server: stdio MCP runtime published from mcp/

What Is Included

  • core/: shared orchestration prompt assets
  • mcp/: TypeScript MCP runtime scaffold (laviya-mcp-server)
  • cursor/: Cursor rule artifacts
  • claude/: Claude skill artifacts (SKILL.md for orchestration, laviya-delivery-cycle/SKILL.md for the user-driven delivery cycle, laviya-prd-intake/SKILL.md for turning a PRD into Laviya work)
  • docs/: setup, npm publishing, and end-user onboarding guides (docs/examples/: an example PRD)

Repository Structure

text
laviya-agent-skills/  core/  mcp/    src/    examples/    README.md  cursor/  claude/  docs/    Setup.md    MCPServerPublish.md    InstallationAndUsage.md

Quick Start

bash
cd mcpnpm installnpm run typechecknpm run buildnpm run dev

Required environment variable:

  • LAVIYA_API_KEY

Install the Claude Code skills

Claude Code loads a skill only from a skills folder, one folder per skill named after the skill, with the file named SKILL.md:

SkillSource file in this repositoryInstall to (personal, all projects)Or (one project only)
laviya-orchestrator (orchestration runs)mcp/examples/claude/SKILL.md~/.claude/skills/laviya-orchestrator/SKILL.md<project>/.claude/skills/laviya-orchestrator/SKILL.md
laviya-delivery-cycle (verify a work list, create tasks, report Ready for deploy)claude/laviya-delivery-cycle/SKILL.md~/.claude/skills/laviya-delivery-cycle/SKILL.md<project>/.claude/skills/laviya-delivery-cycle/SKILL.md
laviya-prd-intake (turn a PRD into epics, stories, tasks, sprints and test cases; example PRD: docs/examples/prd-order-export.md)claude/laviya-prd-intake/SKILL.md~/.claude/skills/laviya-prd-intake/SKILL.md<project>/.claude/skills/laviya-prd-intake/SKILL.md

The paths in the second column are where the files live in this repository, not where Claude Code looks for them. A file in ~/.claude/laviya-delivery-cycle/ (without skills) or directly in ~/.claude/ is ignored.

Windows (PowerShell, from the repository root):

powershell
New-Item -ItemType Directory -Force "$HOME\.claude\skills\laviya-orchestrator", "$HOME\.claude\skills\laviya-delivery-cycle", "$HOME\.claude\skills\laviya-prd-intake" | Out-NullCopy-Item mcp\examples\claude\SKILL.md "$HOME\.claude\skills\laviya-orchestrator\SKILL.md"Copy-Item claude\laviya-delivery-cycle\SKILL.md "$HOME\.claude\skills\laviya-delivery-cycle\SKILL.md"Copy-Item claude\laviya-prd-intake\SKILL.md "$HOME\.claude\skills\laviya-prd-intake\SKILL.md"

macOS / Linux (from the repository root):

bash
mkdir -p ~/.claude/skills/laviya-orchestrator ~/.claude/skills/laviya-delivery-cycle ~/.claude/skills/laviya-prd-intakecp mcp/examples/claude/SKILL.md ~/.claude/skills/laviya-orchestrator/SKILL.mdcp claude/laviya-delivery-cycle/SKILL.md ~/.claude/skills/laviya-delivery-cycle/SKILL.mdcp claude/laviya-prd-intake/SKILL.md ~/.claude/skills/laviya-prd-intake/SKILL.md

Check: start a new Claude Code session and run /skills; laviya-orchestrator, laviya-delivery-cycle and laviya-prd-intake must be listed. Copy the files again after updating this repository. The Laviya MCP tools also work without the skills; the skills add the step-by-step rules.

Installable Asset Package

Install the reusable asset bundle:

bash
npm install laviya-agent-skills

Example usage:

js
import { assets, resolveAssetPath } from "laviya-agent-skills";import { readFileSync } from "node:fs";
const cursorRule = readFileSync(assets.cursorRule, "utf8");const orchestratorPrompt = readFileSync(resolveAssetPath("orchestratorSystemPrompt"), "utf8");

Documentation Index

  • Runtime architecture and implementation: mcp/README.md
  • Developer setup guide: docs/Setup.md
  • NPM publishing guide: docs/MCPServerPublish.md
  • End-user installation and usage: docs/InstallationAndUsage.md
  • Client-specific MCP setup (Codex, VS Code, Antigravity, Claude): docs/InstallationAndUsage.md

Runtime Overview

The MCP runtime follows a global-runtime plus project-local-config model:

  • machine-level runtime installation
  • repository-level project configuration (.laviya/project.json or .laviya.json)
  • runtime-enforced lifecycle mechanics (validation, retries, idempotency, and structured logging)

Current MCP tool set includes both orchestration and local-direct task feed flows:

  • laviya_help
  • laviya_feed_task
  • laviya_get_local_work_status
  • laviya_cancel_local_work
  • laviya_add_task_comment
  • laviya_list_projects
  • laviya_list_tasks
  • laviya_create_tasks
  • laviya_start_delivery_run
  • laviya_get_task
  • laviya_upload_task_file
  • laviya_update_task_description
  • laviya_assign_task
  • laviya_list_sprints
  • laviya_create_sprint
  • laviya_assign_tasks_to_sprint
  • laviya_list_task_links
  • laviya_add_task_link
  • laviya_remove_task_link
  • laviya_list_test_cases
  • laviya_create_test_cases
  • laviya_report_test_result
  • laviya_list_wikis
  • laviya_get_wiki
  • laviya_create_wiki
  • laviya_update_wiki
  • laviya_start_task_work
  • laviya_complete_task_work
  • laviya_get_my_work
  • laviya_start_execution
  • laviya_complete_execution
  • laviya_report_token_usage
  • laviya_diagnostics

All tools return API envelope JSON text in the shape: { HasFailed, Messages, Data }.

Work items may include a backend-defined ExecutionPolicy. Analysis and review policies are read-only: agents must not implement changes, and enforced policies require a truthful completion executionEvidence.

For full architecture details and file-level scaffolding, refer to mcp/README.md.

Source: README.md at commit f2808c6

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

7
  1. v0.1.32LatestNov 7, 2026
  2. v0.1.30Oct 26, 2026
  3. v0.1.29Oct 26, 2026
  4. v0.1.27Oct 23, 2026
  5. v0.1.26Oct 23, 2026
  6. v0.1.25Oct 22, 2026
  7. v0.1.24Sep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.