A comprehensive autonomous engineering cycle from planning to shipping.
Install
mkdir -p .claude/skills/lfg-packrat-ai && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10068" && unzip -o skill.zip -d .claude/skills/lfg-packrat-ai && rm skill.zipInstalls to .claude/skills/lfg-packrat-ai
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 workflowKey capabilities
- →Plan engineering tasks
- →Deepen plans
- →Execute work
- →Review code
- →Record feature videos
How it works
It orchestrates a sequential workflow of planning, implementation, review, and verification.
Inputs & outputs
When to use lfg
- →Building new features autonomously
- →Executing full engineering plans
- →Managing complex development workflows
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, and step 3 when warranted) MUST be completed and verified BEFORE any work begins. Violating this order produces bad output.
-
Optional: If the
ralph-loopskill 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. -
/ce:plan $ARGUMENTSGATE: STOP. Verify that the
ce:planworkflow produced a plan file indocs/plans/. If no plan file was created, run/ce:plan $ARGUMENTSagain. Do NOT proceed to step 3 until a written plan exists. -
Conditionally run
/compound-engineering:deepen-planRun the
deepen-planworkflow only if the plan isStandardorDeep, 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-planworkflow, confirm the plan was deepened or explicitly judged sufficiently grounded. If you skipped it, briefly note why and proceed to step 4. -
/ce:workGATE: 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.
-
/ce:review -
/compound-engineering:resolve-todo-parallel -
/compound-engineering:test-browser -
/compound-engineering:feature-video -
Output
<promise>DONE</promise>when video is in PR
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
- →Skipping planning phase
Limitations
- →Do not jump ahead to coding
How it compares
It mandates a written plan before any code is written, ensuring high-confidence execution.
Compared to similar skills
lfg side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| lfg (this skill) | 0 | 4mo | No flags | Advanced |
| agent-factory | 8 | 9mo | Review | Advanced |
| subagent-driven-development | 14 | 7mo | No flags | Advanced |
| continuous-learning-v2 | 10 | 2mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by PackRat-AI
View all by PackRat-AI →You might also like
agent-factory
alirezarezvani
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
subagent-driven-development
davila7
Use when executing implementation plans with independent tasks in the current session
continuous-learning-v2
affaan-m
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
agent-skill-creator
FrancyJGLisboa
This enhanced skill should be used when the user asks to create an agent, automate a repetitive workflow, create a custom skill, or needs advanced agent creation capabilities. Activates with phrases like every day, daily I have to, I need to repeat, create agent for, automate workflow, create skill for, need to automate, turn process into agent. Supports single agents, multi-agent suites, transcript processing, template-based creation, and interactive configuration. Claude will use the enhanced protocol to research APIs, define analyses, structure everything, implement functional code, and create complete skills autonomously with optional user guidance.
vibe-build
KhazP
Build your MVP following the AGENTS.md plan. Use when the user wants to start building, implement features, or says "build my MVP", "start coding", or "implement the project".
swarm-coordination
joelhooks
Multi-agent coordination patterns for OpenCode swarm workflows. Use when work benefits from parallelization or coordination.