agentsclimarketplace

Ca chore

Skill arbiterForge/codeArbiter/plugins/ca-pi/skills/ca-chore

When you can't trust yourself with your code base, trust Arbiter.

Install
npx -y skills add arbiterForge/codeArbiter --skill ca-chore

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

What its author says it does

Copied from the file, not written here

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

SKILL.md

3.0 KB, 719 tokens by cl100k_base, as published. Nobody here has run it

/ca-chore — non-behavioral change lane

The sanctioned path for work that has no behavioral surface to test-drive. Three types, each with the gates that fit it — and nothing it doesn't need. Everything still exits through commit-gate (classification docs / chore / revert) and lands via branch/PR.

Types

docs — README, comments, CHANGELOG, .codearbiter/ prose, typo fixes.

  • Gates: secrets scan over the diff; diff review (no behavioral code change smuggled in); anti-slop copy pass on any user-facing doc in the change; commit-gate.
  • Anti-slop copy pass — for any user-facing doc the change touches (repo-root community docs and docs/**; not codeArbiter's own framework bodies), load <plugin-root>/includes/anti-slop-design/INDEX.md, then core.md and the medium-documents leaf (§7.A.1), and run the §3.A em-dash ban and the §3.B copy self-audit over the authored prose before commit-gate. The H-13 PostToolUse reminder surfaces §3.A separator dashes as you write, so the pass is a confirmation, not a discovery.
  • No tdd — prose has no failing test to write.

deps — bump an existing dependency's version (manifest + lockfile together, never one without the other).

  • Gates: dispatch dependency-reviewer (same vetting as /ca-add-dep — license, provenance, supply chain, changelog of the bump); full test suite green after the bump; commit-gate.
  • A bump that requires code changes to adopt is not a chore — route the code change through /ca-feature or /ca-fix.

revert — back out a named commit.

  • Gates: git revert <SHA> (never hand-edited backout); full suite green after the revert; the commit message references the reverted SHA and the reason; commit-gate.
  • No new regression test demanded — the revert restores already-tested behavior. If the revert is fixing a defect the suite missed, open /ca-fix afterward to pin it.

Flow

  1. Classify $ARGUMENTS into one of the three types. Anything with a behavioral code change beyond a mechanical revert is NOT a chore — redirect to /ca-feature or /ca-fix and stop.
  2. Run the type's gates above.
  3. Exit through commit-gate with the matching classification, then finishing-a-development-branch as usual.

Hard gate

MUST reject a change containing behavioral code (beyond the revert itself) — that is /ca-feature or /ca-fix territory. MUST keep manifest and lockfile changes in the same commit for deps. MUST run the full suite for deps and revert. MUST run the anti-slop copy pass on any user-facing doc a docs change authors or edits. Never skips commit-gate.

When NOT to use

  • Any new or changed behavior → /ca-feature / /ca-fix.
  • Adding a NEW dependency → /ca-add-dep.
  • Restructuring code → /ca-refactor.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most docs writing skills give in 719 tokens

Counted across 1,637 of the 3,044 authors here whose files we hold, read 2026-08-07

  • Announce the skill at startin 54 of 1637, across 26 files
  • Convert legacy doc files before editingin 45 of 1637, across 7 files
  • Predict questions readers might askin 42 of 1637, across 4 files
  • Generate clarifying questions for initial contextin 42 of 1637, across 3 files
  • Create document scaffold with placeholder textin 42 of 1637, across 3 files
  • Brainstorm content options for each sectionin 42 of 1637, across 3 files
  • Test the document with a fresh context-less instancein 42 of 1637, across 3 files
  • Include exact file paths in every taskin 42 of 1637, across 15 files
  • Ask interview questions one at a timein 42 of 1637, across 27 files
  • Apply surgical edits during refinementin 41 of 1637, across 2 files
  • Offer structured workflow or freeformin 40 of 1637, across 1 file
  • Ask for document meta-contextin 40 of 1637, across 2 files

Said here and by no other author read

  • classify the change into docs, deps, or revert
  • redirect behavioral changes out of this lane
  • run the type-specific gates
  • update manifest and lockfile in the same commit
  • run the full test suite for deps and reverts
  • run an anti-slop copy pass on user-facing docs

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,970. 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.