Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From compound-engineering
Executes full autonomous software engineering workflow using swarm mode for parallel planning, coding, review, testing, autofix, todo resolution, and feature video in PR.
npx claudepluginhub everyinc/compound-engineering-plugin --plugin compound-engineeringHow this skill is triggered — by the user, by Claude, or both
Slash command
/compound-engineering:slfgThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Swarm-enabled LFG. Run these steps in order, parallelizing where indicated. Do not stop between steps — complete every step through to the end.
Executes full autonomous engineering workflow with swarm-mode parallelization: plans features, builds via agent swarms, parallel reviews/tests/de-slopping, autofixes, learns patterns, resolves todos, records PR video.
Executes autonomous engineering workflow: plan feature with /ce:plan, implement via /ce:work, autofix review, resolve todos, browser test, feature video, and PR. For full-cycle software tasks.
Provides patterns for autonomous Claude Code loops: sequential pipelines, agentic REPLs, PR cycles, de-sloppify cleanups, and RFC-driven multi-agent DAGs. For continuous dev workflows without intervention.
Share bugs, ideas, or general feedback.
Swarm-enabled LFG. Run these steps in order, parallelizing where indicated. Do not stop between steps — complete every step through to the end.
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./ce:plan $ARGUMENTS — If ce:plan reported the task is non-software and cannot be processed in pipeline mode, stop the pipeline and inform the user that SLFG requires software tasks. Otherwise, record the plan file path from docs/plans/ for steps 4 and 6./ce:work — Use swarm mode: Make a Task list and launch an army of agent swarm subagents to build the planAfter work completes, launch steps 4 and 5 as parallel swarm agents (both only need code to be written):
/ce:review mode:report-only plan:<plan-path-from-step-2> — spawn as background Task agent/compound-engineering:test-browser — spawn as background Task agentWait for both to complete before continuing.
/ce:review mode:autofix plan:<plan-path-from-step-2> — run sequentially after the parallel phase so it can safely mutate the checkout, apply safe_auto fixes, and emit residual todos for step 7/compound-engineering:todo-resolve — resolve findings, compound on learnings, clean up completed todos/compound-engineering:feature-video — record the final walkthrough and add to PR<promise>DONE</promise> when video is in PRStart with step 1 now.