lancewillett/ai-plugins

Lance's AI skills, agents, commands, etc. By convention, works with Claude and Codex both.

2Stars on the repository
20Mods indexed here, across every type
16d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

ai-plugins

01

lancewillett/ai-plugins

Plugin Claude Code

Plugin marketplace listing 8 plugins: kb-to-spec, js-perf-audit, visual-screenshots, claude-cleanup, playwright-ui-check.

2 16d ago A tokens not measured original MIT

claude-cleanup

02

lancewillett/ai-plugins

Plugin Claude Code

Audit and clean up Claude Code configuration. Checks skills, hooks, plugins, configs, commands, and stale data for issues and fixes them.

2 16d ago A tokens not measured original MIT

five-steps

03

lancewillett/ai-plugins

Plugin Claude Code

Apply the 5-step optimization framework (question, delete, simplify, accelerate, automate—in that order) to a plan or an existing system, then edit the target in place.

2 16d ago A tokens not measured original MIT

flake-to-fact

04

lancewillett/ai-plugins

Plugin Claude Code

Replace vague flaky-test language with the narrowest evidence-supported classification for test, build, deployment, performance, security, and CI failures. Separates recurrence from cause, records confidence, and requests a specific diagnostic when evidence is insufficient.

2 16d ago A tokens not measured original MIT

js-perf-audit

05

lancewillett/ai-plugins

Plugin Claude Code

Audit any JS-heavy codebase for performance issues. Checks bundle weight, code splitting, selector memoization, rendering architecture, and performance infrastructure. Produces a findings report with severity ratings and recommendations.

2 16d ago A tokens not measured original MIT

playwright-ui-check

06

lancewillett/ai-plugins

Plugin Claude Code

Verify a login-gated UI loads and behaves correctly - to validate product changes fast - by logging in once in a visible browser, then attaching a headless browser over the Chrome DevTools Protocol for every check after. Includes the auth-once session model, a reference Playwright runner, and the collision and…

2 16d ago A tokens not measured original MIT

unit-tests

07

lancewillett/ai-plugins

Plugin Claude Code

Audit existing test suites for meaningful coverage, brittle checks, duplicated assertions, and genuine gaps. Improves test quality without blindly adding tests.

2 16d ago A tokens not measured original MIT

visual-screenshots

08

lancewillett/ai-plugins

Plugin Claude Code

Capture before/after screenshots for PRs with visual UI changes using Playwright. Reads the repo's dev-server setup, captures matched before/after shots at multiple viewports, and can upload them straight into the PR comment as inline images. Works on github.com and GitHub Enterprise.

2 16d ago A tokens not measured original MIT