Architecture skills: a multi-agent architecture review from the inside, an outside-in user panel review, a stranger's cold visit by a headless agent that knows nothing about the project, and a lightweight design review of one design before it's built, each adapting to any repository through a per-project profile.
Plugin architecture from marketplace mcbridedm-skills in mcbridedm/claude-skills. Commands read from the repo's manifest — 4 days ago.
architecture-reviewMulti-disciplinary architecture review of the current repository. Checks the project's review profile for drift, builds an architectural context document from the repo, has a panel of specialist architects (13 by default - enterprise, solution, application and domain, cloud, security, data, AI/ML, f
cold-visitorA stranger's test of a site. Launches one headless agent from an empty folder, with no repository, instructions, memory or notes, gives it one vague prompt ("go engage with example.com") and lets it find its own way; then reports what it tried, where it stuck or gave up, what confused it and what it
design-reviewLightweight review of one design before it's built. Takes a draft ADR, a design doc or a description (and writes the draft ADR first if there is none), picks the 3 to 5 most relevant personas from the project's architecture-review panel by what the design touches (data model, money, auth, abuse, UI,
user-panel-reviewOutside-in review of the current project by a panel of simulated users - a newcomer, a regular and a bad actor trying to abuse it, plus, when the product has an API, CLI, SDK or MCP server, people who run agents and AI agents using it on their own. Each persona sees only what a real user would see (
reviewerRead-only reviewer for this plugin's review skills (architecture-review panelists, design-review reviewers, user-panel-review screenshot walkers). Reads and searches the repository and does light web research; it has no shell and no editing tools, so it cannot change files or run commands. Use when
Code quality skills: a parallel, verified review of a range of commits already on a branch, resuming where the last review stopped; a whole-codebase audit of one commit against its own designs, decisions, rules and docs, with proven coverage; and a safe, standards-based review of pull requests from outside contributors, people or AI agents, with a written verdict.
4 skills · 1 agent
Documentation skills: a profile-driven docs sync that brings a project's docs, ledgers, generated files and project state back in line with the code, with parallel read-only audits, every finding validated before it's fixed, and a marker so the next sync resumes; and a writing audit that checks UI copy, docs and what a project's bots publish against its own writing standard, every product claim against the code.
2 skills · 2 agents
Infrastructure skills: a step-by-step first-apply guide for any infrastructure-as-code root, with region callouts, cross-environment checks, DNS and secret steps, and a scale-to-zero ('park') drill, if the project has one; and a local reproduction of a failing CI or workflow job, in a throwaway replica of its environment, before anyone changes code on a guess.
3 skills
Setup skills: sets up a project to use these skills (starter profiles, a section in CLAUDE.md or AGENTS.md, optional guardrails with a hook that refuses shell writes to protected paths), and keeps a Claude Code setup current by watching trusted sources for new practices, recommending them and codifying the ones adopted, and turns recurring tasks into headless jobs (a cheap guard, scoped tools, a spend cap and a schedule) instead of session crons.
3 skills
Mobile app skills: a verify step for iOS and Android changes that builds the app, drives the changed flow on throwaway simulators and emulators, captures and reads screenshots across phones, tablets, foldables, light and dark, the largest text size and landscape, and runs the platform accessibility audit and log checks.
1 skill
UI skills: an icon check that renders a project's favicons and app icons at the sizes people see them (16 and 32 px with pixel zooms, mocked light and dark browser tab bars at 1x and Retina, manifest, maskable and Apple touch icons) on one review sheet, and reports missing sizes, an SVG favicon that overrides hand-tuned PNGs, and maskable content outside the safe zone.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 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
Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.
1 skill · 7 commands
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
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
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.