mcpField
F
finalize

finalize

github.com/steveclarkeTesting & quality3695 installsUpdated today
Repository

About finalize

Finalize is a harness-neutral skill for developers preparing code changes for completion. It runs a checklist covering lint, tests, code quality, documentation, UI, and project-specific requirements, and fixes issues it finds.

Key features

  1. 01Runs lint and format checks
  2. 02Runs the project test suite
  3. 03Scans code quality and security
  4. 04Checks documentation and UI changes
  5. 05Follows project-specific finalization steps

Use cases

  1. 01Verifying changes before completion
  2. 02Checking tests and lint after implementation
  3. 03Reviewing documentation and interface updates

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/steveclarke/dotfiles --skill finalize

After installing, type/finalizein Claude Code to confirm it loaded.

Details

From the project README

Finalize

How it works

This skill runs a universal checklist, then checks the project's agent instructions file (CLAUDE.md, or AGENTS.md in harnesses that use it) for any project-specific finalization requirements (look for a "Finalize Checklist" section or similar). The project knows what it needs — this skill just makes sure nothing gets skipped.

Harness-neutral. The checklist is tool-agnostic: run the project's real lint/test/build commands with whatever shell and tooling the harness has. Steps that name a specific tool (e.g. the Impeccable UI pass, or the Memory step) apply only where that tool exists — skip them, with a note, where it doesn't. Nothing here requires subagents.

Universal Checklist

Work through each section. Report what passes and what needs fixing. Fix issues directly rather than just listing them — the user wants the work done, not a report.

1. Lint & Format

Run whatever lint/format tools the project uses. Check CLAUDE.md/AGENTS.md or package.json/Gemfile for the commands.

2. Tests

Run the project's test suite. Check for:

  • All tests pass
  • No skipped tests that shouldn't be skipped
  • New code has test coverage (or note if it doesn't)
3. Code Quality Sweep

Scan changed files for common issues:

  • Raw/hardcoded values that should use project utilities or constants
  • Inconsistent patterns with existing code (naming, structure, style)
  • Dead code, redundant logic, TODO/FIXME comments left behind
  • Debug statements (console.log, binding.pry, debugger, puts)
  • Security: hardcoded secrets, unsafe patterns
4. Documentation

Check that new/changed code has corresponding documentation:

  • README or docs pages updated if user-facing behavior changed
  • Inline docs (JSDoc, YARD, docstrings) on public APIs
  • Any project-specific docs (check CLAUDE.md/AGENTS.md for the list)
5. UI & Design Quality

Skip this section if the changeset has no view/template/component files.

Run the Impeccable skill on changed view files:

  • $impeccable audit <target> — accessibility, performance, responsive behavior, theming
  • $impeccable polish <target> — final UI quality pass: spacing, interaction states, typography, transitions, component-library fit, design-system compliance, tokens

Report which Impeccable commands were run and what they found. Fix issues directly.

Consistency with existing pages (not covered by Impeccable):

  • New pages match the structure of similar existing pages
  • Headers, content wrappers, and action placement follow established patterns
  • If the page deviates from the dominant pattern, the deviation is intentional and justified

Visual verification:

  • Changes render correctly in dev server, Storybook, or Lookbook
  • Light mode and dark mode if applicable
  • Mobile/responsive if applicable
6. Git & Issue Hygiene
  • PR description reflects the actual scope of changes
  • Closes #N or equivalent issue linking in PR body
  • Parent issues/epics updated if this is part of a larger effort
  • Follow-on issues created for deferred or discovered work
  • Issues added to project board with correct status
7. Project-Specific Checks

Read the project's CLAUDE.md/AGENTS.md for a "Finalize Checklist" section (or similar). If it exists, work through those items too. These are project-specific requirements that the universal checklist can't know about.

8. Knowledge
  • Record lasting learnings, decisions, or patterns in the repo's docs, with a pointer from CLAUDE.md/AGENTS.md

Comments

Markdown supported