Chapter VII · Tools

Skillet

The skills rack: installable agent skills for auditing, improving, and shipping repos. The flagship is line-check, a repo audit that ends in a leverage-sorted improvement backlog instead of a wall of findings.

Current as of skillet 0.4.0, 2026-06-27.

What this is

skillet is a public collection of agent skills extracted from the workflows in this cookbook. Where Brigade gives your agent kitchen its shape (memory, handoffs, guards), skillet gives the cooks their techniques: repeatable procedures any SKILL.md-capable harness can load on demand.

Twenty-nine skills ship in 0.4.0, organized by job. Any SKILL.md-capable harness loads them on demand:

FamilySkills
Design and buildmise (idea to approved spec), recipe (spec to plan), demi, taste (test-first), fire (execute a plan task by task), stations (fan out parallel work), worktree
Debug and verifyrefire (root-cause before any fix), check (prove it works before claiming it)
Review and shippass (the pre-PR gate), review, sendback, release-cut, expedite
Audit and directionline-check (the flagship repo audit), bug-hunt, security-sweep, special
Simplifyreduce
Writing and publishinggrill, plate, publish-readiness, reel-check, seo-fleet
Memorymemory-handoff, brigade-handoffs
Pressure and metapressure-test, skillify, using-skillet

line-check is still the flagship: it audits a repo across seven stations (docs, agent-readiness, tests/CI, hygiene, structure, release hygiene, TODO mining), scores each 0-5, and delivers a backlog sorted by impact relative to effort. It composes with bug-hunt and security-sweep (the audit trio) on a shared report contract.

Why this way

Three design calls worth stealing:

One report contract across the audit trio. line-check, bug-hunt, and security-sweep share a severity scale, finding schema, and backlog format. Run them weeks apart and the findings still compose into one prioritized list. The contract lives in docs/audit-report-format.md and each skill inlines the short version so it works standalone.

Backlogs, not findings. The deliverable of an audit is the ordered list of what to do next. A finding without a concrete fix, an effort estimate, and a checkable location does not make the report. Cheap high-impact items float to the top regardless of severity.

Verification before reporting. bug-hunt’s verifiers are prompted to refute, not confirm; findings that survive get a concrete trigger, findings that do not die silently. Plausible-but-wrong findings are the failure mode of agent auditing, and redundant generation does not fix it; adversarial review does.

How it pairs with Brigade

line-check’s agent-readiness station checks the things Brigade manages: are AGENTS.md/CLAUDE.md present and accurate, is the handoff wiring healthy (brigade handoff doctor), are memory cards fresh (brigade memory care scan). The memory-handoff skill writes handoffs that pass brigade handoff lint. None of the skills require Brigade; they detect it and use it when present.

Install

Claude Code:

/plugin marketplace add escoffier-labs/skillet
/plugin install skillet@skillet

OpenClaw or any SKILL.md-compatible harness:

git clone https://github.com/escoffier-labs/skillet
cp -r skillet/skillet/skills/line-check <your-skills-dir>/

Verification

Confirm the clone ships every skill as a discoverable SKILL.md:

git clone https://github.com/escoffier-labs/skillet
ls skillet/skillet/skills/*/SKILL.md | wc -l
# 29

ls skillet/skillet/skills
# brigade-handoffs  bug-hunt  check  demi  expedite  fire  grill
# line-check  memory-handoff  mise  pass  plate  pressure-test
# publish-readiness  recipe  reduce  reel-check  refire  release-cut
# review  security-sweep  sendback  seo-fleet  skillify  special
# stations  taste  using-skillet  worktree

In Claude Code, after the marketplace install, run /plugin and confirm skillet appears in the installed list; its skills then show up as skillet:line-check and friends.

Gotchas