Executes a multi-stage engineering workflow: planning, implementation, review, and testing.

Install

mkdir -p .claude/skills/lfg-nabilban && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15275" && unzip -o skill.zip -d .claude/skills/lfg-nabilban && rm skill.zip

Installs to .claude/skills/lfg-nabilban

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Full autonomous engineering workflow
36 charsno explicit “when” trigger
Advanced

Key capabilities

  • Execute a multi-step autonomous engineering workflow
  • Generate a plan file using `/ce-plan`
  • Perform implementation work using `/ce-work`
  • Verify requirements completeness with `/ce-review`
  • Resolve compound engineering todos

How it works

The skill executes a sequential engineering workflow, starting with plan generation, followed by implementation, review, and testing. It enforces strict adherence to the order of operations.

Inputs & outputs

You give it
Feature description as arguments to `/ce-plan`
You get back
Completed software implementation, verified against a plan

When to use lfg

  • Implement new software features
  • Run autonomous engineering pipeline
  • Verify implementation against plans

About this skill

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) MUST be completed and verified BEFORE any work begins. Violating this order produces bad output.

  1. Optional: If the ralph-loop skill is available, run /ralph-loop-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. If ce-plan reported the task is non-software and cannot be processed in pipeline mode, stop the pipeline and inform the user that LFG requires software tasks. Otherwise, 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. Record the plan file path — it will be passed to ce-review in step 4.

  3. /ce-work

    GATE: STOP. Verify that implementation work was performed - files were created or modified beyond the plan. Do NOT proceed to step 4 if no code changes were made.

  4. /ce-review mode:autofix plan:<plan-path-from-step-2>

    Pass the plan file path from step 2 so ce-review can verify requirements completeness.

  5. /compound-engineering-todo-resolve

  6. /compound-engineering-test-browser

  7. Output <promise>DONE</promise> when complete

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

When not to use it

  • When the task is non-software related
  • When a plan file is not required before implementation
  • When the steps cannot be executed in the specified order

Limitations

  • Requires software tasks to operate
  • Cannot skip any required step in the workflow
  • Implementation work must result in code changes

How it compares

This skill automates and strictly sequences the entire software development process from planning to testing, ensuring each step is completed and verified before proceeding, unlike a manual or less structured approach.

Compared to similar skills

lfg side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
lfg (this skill)03moNo flagsAdvanced
github-script13moNo flagsIntermediate
spec-to-done01moNo flagsAdvanced
executing-plans02moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

github-script

githubnext

Best practices for writing JavaScript code for GitHub Actions using github-script

12

spec-to-done

monkey1sai

Use when a brainstormed spec already exists under docs/superpowers/specs/ and the user asks to autonomously drive it to a merged PR (e.g. 「跑 spec-to-done」「用 spec-to-done 跑 <spec 路徑>」), or when resuming a previously held spec-to-done run.

00

executing-plans

liujiarui0918

Use to execute a written plan. Run tasks in batches with human checkpoints.

00

turborepo

vercel

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

61191

command-development

anthropics

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

16133

bazel-build-optimization

wshobson

Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.

14116

Search skills

Search the agent skills registry