Menu
Full autonomous engineering workflow using swarm mode for parallel execution
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Full autonomous engineering workflow
Session kickoff protocol - the opposite of "land the plane". Use this skill whenever the user says "takeoff", "take off", "/takeoff", "starting a new session", "what should I work on", "kickoff", "what's next", or wants a prioritized view of the backlog at the start of work. Surfaces the top-priority backlog tasks as a table with status, dependencies, and blockers pulled from Backlog.md (CLI + MCP). Use this at the start of a coding session to orient on what to work on.
Full autonomous engineering workflow
Produce two independent agent reviews on the current PR (an existing Copilot review when present, otherwise two distinct subagent reviewers), adjudicate findings with a third independent subagent, post inline PR comments for verified issues, run a tight inline fix-and-reply-and-resolve loop, then deliver a verdict — APPROVE if clean, APPROVE-WITH-CHANGES if findings were verified (and fixed or noted), CLOSE if the PR is fundamentally unsound, or WITHHELD if CI is red post-fix and the regression cannot be resolved. The skill is read-only with respect to GitHub reviewer assignment — it never adds reviewers. Use whenever the user invokes /ghcp-review-resolve, asks to "run copilot review and resolve", asks to "review and fix my PR with copilot", asks for a "dual review and fix pass", or wants automated review triage, remediation, and verdict on a pull request they just opened. Submits APPROVE or CLOSE; never submits REQUEST_CHANGES and never merges.
Session completion protocol - the opposite of "takeoff". Use this skill whenever the user says "land", "/land", "land the plane", "land it", "let's land", "land this", "bring it in", "wrap it up", "land the plan", "land plane", "time to land", "ok land", "go ahead and land", or any variation that signals they want to finish, close out, ship, or wrap up the current session's work. Executes the full commit → push → PR → handoff checklist without asking. If the user's message contains "land" in the context of finishing work, invoke this skill — it is a keyword trigger, not an exact match.
Full autonomous engineering workflow using swarm mode for parallel execution
| name | slfg |
| description | Full autonomous engineering workflow using swarm mode for parallel execution |
| argument-hint | [feature description] |
| disable-model-invocation | true |
Swarm-enabled LFG. Run these steps in order, parallelizing where indicated. Do not stop between steps — complete every step through to the end.
This workflow is resumable. A tiny helper tracks which phases are done and where each phase's output lives, so re-invoking /slfg continues from the first unfinished phase instead of restarting.
node .github/hooks/scripts/lfg-state.js — commands init, bind-plan, done <phase> --run-id <id> [--artifact <repo-relative-path>], status --run-id <id>, run-id-from-plan --plan <path>. It writes .atv/runs/<run-id>/ (gitignored, local-only).RUN_ID from an existing docs/plans/ plan via run-id-from-plan, else init a provisional id. Run node .github/hooks/scripts/lfg-state.js status --run-id <RUN_ID> and skip phases already done.run:<RUN_ID> to every sub-skill so artifacts co-locate and downstream phases read paths, not full content.node .github/hooks/scripts/lfg-state.js done <phase> --run-id <RUN_ID> --artifact <path> after the parallel agents join. This avoids races on the state directory.ce-work MUST run with mode:orchestrated so resume reconciles existing work instead of duplicating commits/PRs. If .atv/runs/ is absent, infer progress from the plan, branch, and any open PR.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 run:<RUN_ID> — Record the plan file path from docs/plans/ for steps 4 and 6. Then (parent) node .github/hooks/scripts/lfg-state.js bind-plan --run-id <RUN_ID> --plan <plan-path> and node .github/hooks/scripts/lfg-state.js done ce-plan --run-id <RUN_ID> --artifact <plan-path>./ce-work mode:orchestrated plan:<plan-path-from-step-2> run:<RUN_ID> — Use swarm mode: Make a Task list and launch an army of agent swarm subagents to build the plan. Then (parent) node .github/hooks/scripts/lfg-state.js done ce-work --run-id <RUN_ID>.After work completes, launch steps 4 and 5 as parallel swarm agents (both only need code to be written). Subagents return artifact paths only — the parent records state after they join:
/ce-review mode:report-only plan:<plan-path-from-step-2> run:<RUN_ID> — spawn as background Task agent/compound-engineering-test-browser run:<RUN_ID> — spawn as background Task agentWait for both to complete before continuing. Then (parent) node .github/hooks/scripts/lfg-state.js done test-browser --run-id <RUN_ID> --artifact <report-path>.
/ce-review mode:autofix plan:<plan-path-from-step-2> run:<RUN_ID> — run sequentially after the parallel phase so it can safely mutate the checkout, apply safe_auto fixes, and emit residual todos for step 7. Then (parent) node .github/hooks/scripts/lfg-state.js done ce-review --run-id <RUN_ID> --artifact <review-artifact-path>./compound-engineering-todo-resolve — resolve findings, compound on learnings, clean up completed todos. Then node .github/hooks/scripts/lfg-state.js done todo-resolve --run-id <RUN_ID>./compound-engineering-feature-video — record the final walkthrough and add to PR. Then node .github/hooks/scripts/lfg-state.js done feature-video --run-id <RUN_ID>.<promise>DONE</promise> when video is in PRStart with step 1 now.