Run sequential verification checks on the current codebase. Build, typecheck, lint, tests, debug log audit, and git status. Stops on critical failures. Supports modes: quick, full, pre-commit, pre-pr.
Runs sequential verification checks including build, types, lint, tests, and debug logs with configurable modes.
/plugin marketplace add howells/arc/plugin install arc@howellsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
<tool_restrictions>
EnterPlanMode — BANNED. This is a procedural skill. Execute it directly.ExitPlanMode — BANNED. You are never in plan mode.
</tool_restrictions>Run sequential verification checks. Stop on critical failures.
Before running checks, detect the project's tooling:
Package manager:
pnpm-lock.yaml → pnpmbun.lockb or bun.lock → bunyarn.lock → yarnpackage-lock.json → npmLinter:
biome.json or biome.jsonc → [pm] biome check ..eslintrc* or eslint.config.* → [pm] eslint .Test framework:
vitest.config.* → [pm] vitest runjest.config.* → [pm] jestType checker:
tsconfig.json → [pm] tsc --noEmitBuild:
package.json scripts for build → [pm] run build$ARGUMENTS determines the mode:
| Argument | Mode | Checks |
|---|---|---|
quick | Quick | Build + types only |
full or (none) | Full | All checks |
pre-commit | Pre-commit | Build + types + lint + debug logs (skip tests) |
pre-pr | Pre-PR | All checks + search for hardcoded secrets |
Execute each check sequentially. If a check fails critically, report it and stop.
[pm] run build
[pm] tsc --noEmit
file:line)[pm] biome check .
# or
[pm] eslint .
[pm] biome check --write .quick and pre-commit modes)[pm] vitest run
# or
[pm] jest
Search for leftover debug statements in source files (not test files):
Use Grep tool: Pattern console\.(log|debug|dir|table) in src/ or app/ directories, excluding *.test.* and *.spec.* files
console.warn and console.error are intentional — don't flag thosegit status --short
git diff --stat
Use Grep tool: Search for patterns that suggest hardcoded secrets:
sk_live_, sk_test_, pk_live_, pk_test_ (Stripe)AKIA (AWS access keys)ghp_, gho_, ghs_ (GitHub tokens)xoxb-, xoxp- (Slack tokens)*_KEY, *_SECRET, *_TOKEN that look like real values (not env var references)Exclude: .env*, *.example, *.md, node_modules/
VERIFICATION: [PASS / FAIL]
Build: [OK / FAIL]
Types: [OK / X errors]
Lint: [OK / X issues]
Tests: [X/Y passed / SKIPPED]
Debug logs: [OK / X found]
Git: [clean / X uncommitted]
Secrets: [OK / X found / SKIPPED]
Ready for PR: [YES / NO]
If any check failed, list the specific issues below the table with file:line references and brief fix suggestions.
turbo.json or root pnpm-workspace.yaml exists, run checks at the workspace level (turbo build, turbo typecheck)Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.