angular-architect

An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: angular, performance, reactive, state-management, testing, web.

What it does

Generates Angular 17+ standalone components, configures advanced routing with lazy loading and guards, implements NgRx state management, applies RxJS patterns, and optimizes bundle performance. Use when building Angular 17+ applications with standalone components or signals, setting up NgRx stores, establishing RxJS reactive patterns, performance tuning, or writing Angular tests for enterprise apps.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add Jeffallan/claude-skills --skill angular-architect

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/angular-architect ~/.claude/skills/angular-architect

Safety box score

Grade A, minimal risk: 4 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a documentation-only Angular architecture guide: it generates standalone components, routing, NgRx, RxJS, and test code, but ships no executable scripts or installers. The main exposure is ordinary local code generation and the recommended use of project build/test tooling; there is no evidence of secrets access, privilege changes, or remote exfiltration.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It recommends local project commands like `ng build --configuration production` and writing tests, but ships only Markdown guidance and no native scripts or evaluators.
Network access	0 (none)	There is no instruction to download files or send data to remote hosts; the `HttpClient` and routing snippets are examples of Angular app code, not skill behavior.
Filesystem reach	0 (none)	The skill does not instruct writes outside the workspace or touch dotfiles/system paths; the shipped files are all under `skills/angular-architect` and are read-only documentation.
Secrets & credentials	0 (none)	It explicitly says `MUST NOT DO - Expose sensitive data in client-side code` and contains no steps to read keychains, `.env` files, or browser sessions.
Privilege & persistence	0 (none)	There is no sudo use, global install, service registration, or shell/OS configuration change anywhere in the skill files.
Instruction hijack surface	0 (none)	No prompt-injection or instruction-hiding content is present; the files do not tell the agent to ignore its rules, skip confirmations, or fetch remote instructions.
Irreversible actions	0 (none)	The skill does not push, deploy, publish, pay, book, or delete anything; its scope is implementation guidance and local verification only.
Transparency	0 (none)	All shipped content is plain, readable Markdown with code examples; there are no binaries, base64 blobs, or unpinned external installers.

Before installing

Read `SKILL.md` and the four reference files to confirm the guidance matches your Angular workspace conventions.
If you will let the agent run the suggested build/test steps, do so in a scratch branch or disposable checkout first.
Verify your project’s `package.json` scripts are trusted before following the `ng build`/testing workflow.

Rated 2026-10-20 by an automated review of 6 files from the skill's repository.

Source

Repository: Jeffallan/claude-skills (all skills from this repository)
Path: skills/angular-architect/SKILL.md
Branch: main
Updated: 2026-09-19

react-expert — Use when building React 18+ applications in .jsx or .tsx files, Next.js App Router projects, or create-react-app setups. Creates components.
vue-expert — Builds Vue 3 components with Composition API patterns, configures Nuxt 3 SSR/SSG projects, sets up Pinia stores, scaffolds Quasar/Capacitor mobile apps.
coverage-analysis — Measures and interprets what a fuzzing campaign actually reaches, using llvm-cov, lcov, or a fuzzer's own coverage output.
cro — When the user wants to optimize, improve, or increase conversions on any marketing page or form — including homepage, landing pages, pricing pages.
pentesting-with-aws-security-agent — Run an AWS Security Agent penetration test against a live web application — registers and verifies the target domain.
run-smoke-tests — Run Playwright smoke tests, debug failures, and verify fixes