agentleFS
Sign inStart free
shyamsridhar123shyamsridhar123/kevin-copilot/.github/skills/slfg/SKILL.md

slfg

Skill7 starsChanged 3 months agoMITView on GitHub

Full autonomous engineering workflow using swarm mode for parallel execution

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Optional: If the ralph-loop skill is available, run /ralph-loop-ralph-loop "finish all slash commands" --completion-promise "DONE".

    line 12
  2. Distinctive:

    After work completes, launch steps 4, 5, and 6 as parallel swarm agents (all read-only, safe to run concurrently):

    line 18
  3. Distinctive:

    Wait for all three to complete before continuing.

    line 24
  4. Distinctive:

    Start with step 1 now.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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. Optional: If the 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.
  2. /ce-plan $ARGUMENTS — Record the plan file path from docs/plans/ for steps 4 and 6.
  3. /ce-work — Use swarm mode: Make a Task list and launch an army of agent swarm subagents to build the plan

Parallel Phase

After work completes, launch steps 4, 5, and 6 as parallel swarm agents (all read-only, safe to run concurrently):

  1. /ce-review mode:report-only plan:<plan-path-from-step-2> — spawn as background Task agent
  2. /compound-engineering-test-browser — spawn as background Task agent
  3. /unslop — spawn as background Task agent (read-only de-slop report)

Wait for all three to complete before continuing.

Autofix Phase

  1. /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 8
  2. /unslop fix — run sequentially after ce-review autofix to strip AI slop (commented-out code, filler comments, stale TODOs)

Learning Phase

  1. /observe on the areas of code that were changed — analyze patterns in the modified files to capture what was done and how.
  2. /learn — extract reusable patterns from this session into project instincts.

Finalize Phase

  1. /compound-engineering-todo-resolve — resolve findings, compound on learnings, clean up completed todos
  2. /compound-engineering-feature-video — record the final walkthrough and add to PR
  3. Output <promise>DONE</promise> when video is in PR

Start with step 1 now.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free