agentsclimarketplace

Slopmop

Skill ScienceIsNeato/slop-mop/skills/slopmop

Trigger when you would normally reach for pytest, gh, mypy, black, or other raw repo tooling. Redirect to `sm swab`, `sm scour`, `sm buff`, `sm sail`, `sm refit`, or `sm doctor` so remediation follows the established rails. Also trigger when asked to "install" or "set up" slop-mop in a repo, or when you find a repo with sm installed but no .sb_config.json — follow the install handoff (sm agent install → sm init → sm refit) before the loop. Also trigger when filing issues about slop-mop friction — use `sm barnacle file` / `/sm-barnacle`, never `gh issue create`. Also trigger when the maintenance loop is exhausted and only a human judgment call remains — use `sm wake-angry-drunk-captain` as a last resort.From its SKILL.md

Install
npx -y skills add ScienceIsNeato/slop-mop --skill slopmop

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 15 stars15 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

6.0 KB, as published. Nobody here has run it

Slop-mop skill

Filing slop-mop friction? Use /sm-barnacle or sm barnacle file — never gh issue create directly. The barnacle CLI auto-applies the correct labels and targets the right repo regardless of where you are.

Slop-mop (sm) has two primary modes: refit (one-time onboarding) and maintenance (steady-state development). Refit remediates all existing slop and installs permanent guards; the swab/scour/buff loop then keeps the repo clean as you work.

Setting up slop-mop in a repo (the install handoff)

When the user says "install slop-mop", "set up slop-mop in this repo", or similar, do not improvise ad-hoc setup. It is an ordered handoff — each step is a real CLI surface (sm -h lists them). Run them in order, skipping any that are already done:

  1. CLI present? If sm is "command not found", install the utility: pipx install slopmop[all].
  2. Repo-local agent instructions? Install them so every agent in this repo follows the rails: sm agent install (add --target copilot|cursor|claude as needed).
  3. Config? If there's no .sb_config.json, generate one tuned to the detected stack: sm init --non-interactive.
  4. Onboard the existing code: sm refit --start → sm refit --iterate → sm refit --finish, then enter the maintenance loop.

"Install slop-mop in the repo" means all of the above, not just step 1. If you are unsure which steps remain, sm sail reads the repo state and tells you the next move.

When to use

  • Initial setup (step -1): Run sm init --non-interactive when the repo has sm installed but no .sb_config.json. This generates a config tuned to the detected stack. Run it before refit or the maintenance loop.
  • Default action: Run sm sail when you're not sure what's next — it reads workflow state and does the right thing.
  • Refit (step 0): Run sm refit --start to generate a remediation plan, then sm refit --iterate until complete, then sm refit --finish to enter maintenance.
  • During implementation: Run sm swab after every meaningful code change. Keep running until clean.
  • Before PR: Run sm scour for a comprehensive sweep.
  • After CI/review: Run sm buff <PR_NUMBER> to convert feedback into next steps.
  • Loop exhausted (last resort): Run sm wake-angry-drunk-captain only when barnacles are filed, gates are green or truly unfixable, and the one move left is a human judgment call no verb can make. It demands structured proof, then ends your turn and hands you the captain's question to relay to the human. See below.

When the loop is exhausted: wake the captain

Every other verb assumes there is more agent work to do. sm wake-angry-drunk-captain is the one that doesn't — it escalates to the human, and only the human, when you have genuinely run out of moves.

The name is the guardrail. The captain is asleep, angry, and drunk; the standing order is "do not wake me unless there's an emergency." Picture his face before you reach for it.

Required proof (skip any and it reads the standing order back and refuses):

sm wake-angry-drunk-captain \
  --objective "what you were trying to get done" \
  --verbs-tried "sm swab — green" \
  --verbs-tried "sm buff 42 — CI green, no unresolved threads" \
  --why-stuck "no remaining verb advances; blocker is a product/design call" \
  --decision "the ONE call only a human can make" \
  --option "approach A" --option "approach B"

A valid summons doesn't resolve into more agent work. The verb writes .slopmop/last_captain_summons.md, then returns an envelope whose data.relay_to_human is the captain's question and whose data.agent_directive says, plainly: your turn is over. Show the user relay_to_human verbatim, then stop and wait — the human's next message is the captain's orders. You cannot complete this verb alone; that is the point. Carry out the orders when they come; do not keep looping. Full detail: /sm-wake-angry-drunk-captain.

The maintenance loop

Fastest path:  sm sail → fix what it finds → sm sail → repeat until PR lands
Manual path:   write code → sm swab → fix → repeat → sm scour → sm buff <PR#>

sm sail automates verb selection. Use individual verbs (sm swab -g <gate>, sm buff resolve, etc.) for surgical work.

Refit (before entering the loop)

Refit is not part of the maintenance loop. It is step 0 — how you earn the right to enter the loop.

sm refit --start → fix one gate → sm refit --iterate → ... → sm refit --finish

Prerequisite

The sm CLI must be installed in the user's environment. If invocation fails with "command not found", suggest:

pipx install slopmop[all]

Then re-run the command.

Safety

  • Never bypass or silence a failing check — that's how repo rot compounds.
  • If a gate seems wrong, tune it or file a bug. Don't disable it as a workaround.
  • Report friction (invalid guidance, broken state, blocked rails) via /sm-barnacle rather than working around it.

Reference

Full project docs: https://github.com/ScienceIsNeato/slop-mop Workflow state machine: https://github.com/ScienceIsNeato/slop-mop/blob/main/DOCS/WORKFLOW.md Gate reasoning: https://github.com/ScienceIsNeato/slop-mop/blob/main/DOCS/GATE_REASONING.md

Keep looking

Skills are one crate of 611,178. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.