Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/11-James-Traina-compound-science/skills/slfg

Full autonomous research workflow using swarm mode for parallel execution

Swarm-enabled LFG. Run these steps in order, parallelizing where indicated. Do not stop between steps — complete every step through to the end.

Sequential Phase

  1. /workflows:brainstorm $ARGUMENTS Gate: must produce a file in docs/brainstorms/ before proceeding.

  2. /workflows:plan Gate: must produce a file in docs/plans/ before proceeding.

  3. /workflows:work — Use swarm mode: Break the plan into independent tasks and launch parallel subagents via Task tool to build them concurrently. Each subagent handles one task from the plan. See references/orchestration-patterns.md for parallel dispatch patterns. Gate: must produce at least one code change (committed or staged) before proceeding. If work fails with no changes, stop and report the failure.

Parallel Phase

After work completes, launch steps 4 and 5 as parallel swarm agents (both only need completed code to operate):

  1. /workflows:review — spawn as background Task agent
  2. /workflows:compound — spawn as background Task agent

Wait for both to complete before finishing.

Output

When all steps are done, output:

Research workflow complete.

Brainstorm: [brainstorm file path]
Plan: [plan file path]
Work: [summary of implementation]
Review: [summary of findings]
Documentation: [docs/solutions/ path if created]

Start with step 1 now.

add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall