lfg_skill

This skill orchestrates a full autonomous engineering workflow, planning, deepening plans when needed, and executing end-to-end implementation across
  • TypeScript

10.5k

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

3 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill everyinc/compound-engineering-plugin --skill lfg

  • SKILL.md1.9 KB

Overview

This skill orchestrates a full autonomous engineering workflow for compound engineering tasks. It codifies planning, implementation, review, testing, and release steps so teams can produce reliable changes with clear gates. The skill is designed for TypeScript codebases and integrates planning and deepening steps for high-risk areas.

How this skill works

The skill runs a strict, gate-driven sequence: generate a written plan, optionally deepen the plan for risky or uncertain work, perform implementation edits, and then run review and automated resolution steps. It verifies that each gate produces tangible outputs (plan files, code changes, tests, and a feature video) before advancing. Outputs include plan artifacts, modified source files, test results, reviews, and a PR video.

When to use it

  • Large or cross-cutting engineering changes that need careful sequencing and verification
  • Work that touches auth, security, payments, migrations, or external APIs
  • When an auditable plan and traceable implementation artifacts are required
  • Automating repeatable engineering workflows for feature rollouts
  • When you need an end-to-end engineering runbook enforced by automation

Best practices

  • Always produce and verify a written plan before any coding begins
  • Use the deepen-plan step for any Standard/Deep plans or when risk/confidence gaps exist
  • Ensure plan files are saved to docs/plans/ so gating checks can succeed
  • Confirm that implementation step produces concrete file changes before proceeding to review
  • Attach a short feature video demonstrating the change when creating the PR

Example use cases

  • Implementing a migration that affects database schema and runtime behavior
  • Adding an external API integration with OAuth and payment flows
  • Rolling out an auth or permission model change across services
  • Refactoring a core library shared across multiple services with coordinated release steps
  • Creating a small team-driven feature where traceability and review history are required

FAQ

The workflow stops. Re-run the planning step until a plan file appears in docs/plans/; do not proceed to implementation without it.

When should deepen-plan be invoked?

Invoke deepen-plan for Standard or Deep plans that touch high-risk areas or when the plan lacks confidence, sequencing, or verification details.

How does the skill ensure work was performed?

The work gate requires concrete file creations or modifications beyond the plan artifact; the workflow checks the repository for those changes before moving on.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
lfg skill by everyinc/compound-engineering-plugin | VeilStrat