Start a fresh conversation. Replace the highlighted placeholders.
Use slfg to research and implement [research task or methodological improvement], completing its documented workflow and returning the required brainstorm, plan, work, review, and documentation summary.
Required inputs
[research task or methodological improvement]
User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗
SKILL.md
name: slfgdescription: Full autonomous research workflow using swarm mode for parallel executionargument-hint: "[research task, estimation problem, or methodological improvement]"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.
Sequential Phase
/workflows:brainstorm $ARGUMENTSGate: must produce a file in docs/brainstorms/ before proceeding.
/workflows:planGate: must produce a file in docs/plans/ before proceeding.
/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):
/workflows:review — spawn as background Task agent
/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]