playbooks

home / skills / everyinc / compound-engineering-plugin / lfg

lfg skill

/plugins/compound-engineering/skills/lfg

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

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

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
1.9 KB
---
name: lfg
description: Full autonomous engineering workflow
argument-hint: "[feature description]"
disable-model-invocation: true
---

CRITICAL: You MUST execute every step below IN ORDER. Do NOT skip any required step. Do NOT jump ahead to coding or implementation. The plan phase (step 2, and step 3 when warranted) MUST be completed and verified BEFORE any work begins. Violating this order produces bad output.

1. **Optional:** If the `ralph-wiggum` skill is available, run `/ralph-wiggum:ralph-loop "finish all slash commands" --completion-promise "DONE"`. If not available or it fails, skip and continue to step 2 immediately.

2. `/ce:plan $ARGUMENTS`

   GATE: STOP. Verify that the `ce:plan` workflow produced a plan file in `docs/plans/`. If no plan file was created, run `/ce:plan $ARGUMENTS` again. Do NOT proceed to step 3 until a written plan exists.

3. **Conditionally** run `/compound-engineering:deepen-plan`

   Run the `deepen-plan` workflow only if the plan is `Standard` or `Deep`, touches a high-risk area (auth, security, payments, migrations, external APIs, significant rollout concerns), or still has obvious confidence gaps in decisions, sequencing, system-wide impact, risks, or verification.

   GATE: STOP. If you ran the `deepen-plan` workflow, confirm the plan was deepened or explicitly judged sufficiently grounded. If you skipped it, briefly note why and proceed to step 4.

4. `/ce:work`

   GATE: STOP. Verify that implementation work was performed - files were created or modified beyond the plan. Do NOT proceed to step 5 if no code changes were made.

5. `/ce:review`

6. `/compound-engineering:resolve_todo_parallel`

7. `/compound-engineering:test-browser`

8. `/compound-engineering:feature-video`

9. Output `<promise>DONE</promise>` when video is in PR

Start with step 2 now (or step 1 if ralph-wiggum is available). Remember: plan FIRST, then work. Never skip the plan.

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

What happens if the plan step fails to create a plan file?

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.