amelnagdy/guard-skills
5 skills10.1k installs5.7k starsGitHub
Install
npx skills add https://github.com/amelnagdy/guard-skillsSkills in this repo
1Clean Code GuardYou are reviewing generated or changed code before it ships Apply the rules below as a guard pass after the first implementation pass If the user explicitly invokes this skill before writing code use the same rules while writing and still run the self check before delivery This is a portable instruction skill It requires no MCP server network access API key shell command local executable or bundled script It can be used in any runtime that supports SKILL md plus directly linked references references files agents openai yaml is lightweight display metadata This skill does not replace project linters formatters type checkers or test runners Use the project s own tools for mechanical verification use this skill for the judgement layer around code quality and review This skill has two modes pick based on the user s request Guard pass mode recommended after code has been generated edited refactored or fixed check the diff or target files against the Always applied imperatives below Fix violations before presenting committing or2.8kinstalls2Test GuardThe test-guard skill "Review generated or changed test code against universal testing rules before it ships. Best used reactively after an agent writes, edits, generates, or refactors tests, before presenting, committing, or merging them. Use for pytest test_ .py, _test.py , PHPUnit/Pest Test.php , Jest/Vitest .test.ts, .spec.js , Go _test.go , files under tests/, __tests__/, or spec/, and review requests like 'write tests for X', 'add tests', 'test this', 'review these tests', or PR diffs containing tests. Can also guide test writing when explicitly invoked before the work. This skill is the quality gate that prevents AI-generated test bloat." It covers a coding agent has just written new test functions or test files, in any language. Key workflows include you are editing existing tests. Developers invoke test-guard when the task matches the triggers and reference files in SKILL.md for grounded, stepwise execution.2.4kinstalls3Docs GuardThe docs-guard skill reviews generated or changed documentation before release including READMEs, API references, docstrings, changelogs, and tutorials. Core principle: documentation is checkable claims about code; every function, flag, endpoint, config key, and code sample must be verified against source, CLI help, routes, or schema by reading not recalling. Modes include guard-pass after generation, live verify-before-write, and review-mode findings reports with file line evidence. Rules reject unverifiable performance claims, paraphrased upstream docs, happy-path-only examples, and docstrings that restate signatures. Versioning requires explicit introduced versions and deprecation replacements. Code changes owe synchronized doc surface updates grepped for old symbols. Invoke when user says review the docs, is this documentation accurate, write README, document API, or add changelog entry. Every referenced symbol verified against actual source or CLI help. Every code sample must run with correct imports and signatures.2.3kinstalls4Wp Guardwp-guard is a guard-skills reference that equips AI agents to review WordPress plugin and theme code immediately after edits. Its internationalization reference covers wrapper selection—`__()`, `_e()`, `esc_html_e()`—text domain rules, placeholder and translator-comment conventions, plural forms, sentence assembly, JavaScript i18n, dates, numbers, RTL handling, and multilingual-plugin gotchas. The default prompt tells agents to run `$wp-guard` after WordPress code is written or changed to surface security, i18n, and performance problems. Developers reach for wp-guard when AI-generated PHP, block editor code, or theme templates need a WordPress-specific review pass that generic linters miss. The package ships as structured guardrail documentation from amelnagdy/guard-skills, not a standalone scanner binary.1.3kinstalls5Woo Guardwoo-guard is a guard-skills reference package that teaches AI coding agents how to review WooCommerce plugin and theme changes for production-critical pitfalls. The skill documents two non-overlapping checkout hook surfaces—Blocks checkout via the Store API versus legacy shortcode checkout with `woocommerce_checkout_*` hooks and `wp_ajax` fragments—so reviewers do not apply the wrong patterns to the wrong flow. Coverage spans server-side validation, cart and session context guards, money handling, and gateway or webhook callback safety. The default prompt instructs agents to invoke `$woo-guard` immediately after WooCommerce code is written or changed. Developers reach for woo-guard when AI agents generate WooCommerce extensions, payment integrations, or HPOS migrations and need a structured audit pass before merge. The reference is reference-only guardrail content from amelnagdy/guard-skills rather than an executable CLI.1.3kinstalls