Audits a codebase across nine categories and writes self-contained implementation plans that another agent or a cheaper model can carry out, each with exact files, steps that end in a check, scope limits and STOP conditions. It also writes a plan from a description or from another audit's report, hands a plan to an executor in a separate git worktree and reviews the result, and keeps the plans up to date as the code changes. It never changes source code itself
Plugin ai-improve from marketplace ai-agent-plugins in charlesjones-dev/ai-agent-plugins. Commands read from the repo's manifest — 2 days ago.
improve-auditAudit a codebase as an advisor and write implementation plans for another agent or a cheaper model to carry out. Maps the repo and its build, test and lint commands, audits up to nine categories (bugs, security, performance, tests, tech debt, dependencies, tooling, docs and direction), re-reads ever
improve-executeHand one implementation plan from plans/ to a cheaper executor model in a separate git worktree, then review its work the way a tech lead reviews a pull request: run every done criterion again, check that the diff stays in the plan's scope, read the diff and the new tests, and give a verdict of appr
improve-planWrite one self-contained implementation plan for another agent or a cheaper model to carry out, without a full audit. Takes a description of what to build or fix, or a findings report from another audit, or 'review' and an existing plan to check and tighten. Reads the repo for its conventions and it
improve-reconcileBring the implementation plans in plans/ up to date with the code. Checks that finished plans still hold and that approved branches were merged, investigates blocked plans and rewrites them around the obstacle, refreshes plans whose files changed since they were written, and retires findings that we
Keeps a team knowledge base in git as Claude Code rules, so each article loads when Claude works on matching files, every session, or on demand from a short index. Capture learnings as you work with auto-capture or on request, add docs, repos and URLs, query and prune it, and migrate a 1.x knowledge base
7 skills · hooks
Audits a site's code for search rankings (SEO), direct answers in featured snippets and voice assistants (AEO), and citations in AI answers from ChatGPT, Perplexity, Copilot and Google AI Overviews (GEO), crawls the live site to check what search engines get, and submits new pages to Google, Bing and Brave for indexing. Catches SEO patterns LLMs still generate, applies framework-specific fixes, generates and validates JSON-LD, builds FAQ sections and question maps, and writes llms.txt
8 skills
Audits a repository for security problems and saves Markdown and JSON reports that track findings across audits, plans a sandboxed audit on a stronger model that proves each finding with a failing test, scans a live site's dependencies, and sets up file-access deny rules for secrets and pnpm supply-chain hardening
5 skills · 1 agent
Audits a codebase's user-facing copy, layouts and metadata for AI-written tells and factual errors, such as a privacy policy that misses the trackers the code loads, reviews a web, iOS or Android screen for AI-generated design and fixes it in ordered passes once you approve a direction, rewrites a file or pasted text to remove AI writing patterns, prunes code comments that narrate the code or excuse a workaround, and rebuilds a feature an agent just wrote as a simpler second version, keeping the first until you choose
5 skills
Catches Xcode Cloud and TestFlight blockers before upload (XcodeGen pbxproj drift, static build numbers, missing ci_scripts, macOS App Store entitlements/Info.plist, headless-CI keychain test failures, ad-hoc signing entitlement rejections, flaky-UITest release gating), diagnoses ITMS rejection emails and red CI logs, scaffolds Xcode Cloud CI, runs a local verify gate, and reviews Swift 6 strict-concurrency and SwiftUI code
5 skills
Takes a branch to production through Claude Code, Codex and Cursor Bugbot review, merge and a watched deploy, or stops when the PR is ready to merge. Also runs review loops with models from several providers, finishes other people's PRs and refreshes stale ones
5 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Rewrite AI-sounding text so it reads like the writer without changing what it says.
1 skill
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.