AgentX - Digital Force for Software Delivery
This repository also configures its own agents. See what AgentX tells them →
Skill Claude CodeCodex
Write UI copy that survives review -- microcopy, empty states, error messages, onboarding, confirmations, and tone. Use when authoring or reviewing any user-facing string in a prototype or shipped app. Provides patterns by surface type, a 5-line voice rubric, and mechanical anti-patterns reviewers can grep for.
Skill Claude CodeCodex
Synthesize product context into a coherent UI direction with page archetypes, visual language, token guidance, anti-pattern filters, and stack-aware translation. Use when choosing a design style, defining a design brief, aligning UI choices to industry expectations, or reviewing whether a UI direction fits the product…
Skill Claude CodeCodex
Build frontend UIs with HTML5, CSS3, and Tailwind CSS following accessibility and performance best practices. Use when creating responsive layouts, styling with Tailwind CSS, implementing accessible forms, optimizing frontend performance, or building common UI patterns.
Skill Claude CodeCodex
Drive the Impeccable design language for a target app -- PRODUCT.md and DESIGN.md authoring, the 23-command intervention vocabulary, and the 59-rule deterministic detector wired as a three-state gate (PASS / BLOCKED / DEGRADED). Use when defining the design language for a target app, or when running design-language…
Skill Claude CodeCodex
Mechanically audit a UX prototype or front-end build through ten self-healing passes -- deterministic design-language conformance, accessibility, performance, content, responsive layout, routes, build hygiene, usability heuristics, visual regression, and anti-slop critique. Use before declaring any prototype…
Skill Claude CodeCodex
Craft visually polished, production-quality HTML/CSS prototypes with modern styling, typography, color theory, and micro-interactions. Use when building UX deliverables that need visual polish beyond wireframes, implementing color systems, typography scales, elevation shadows, or smooth transitions for interactive…
Skill Claude CodeCodex
Score a UX prototype or shipped UI against Nielsen-10 heuristics with a severity rubric. Use when reviewing a design, running prototype-auditor Pass 7, or producing a heuristic evaluation report. Mechanically maps each heuristic to inspection prompts, severity (0-4), and fix patterns so two reviewers reach the same…
Skill Claude Code
Design user experiences with wireframing, prototyping, user flows, accessibility, and production-ready HTML prototypes. Use when creating wireframes, building interactive prototypes, designing user flows, implementing accessibility standards, or producing HTML/CSS design deliverables.
Skill Claude CodeCodex
Catch unintended visual drift between prototype iterations with deterministic screenshot diffs. Use when iterating on a prototype, before review handoff, or before promoting an SPA prototype to a real build. Default engine is Playwright toHaveScreenshot with masking, threshold, and per-OS baselines. Includes Chromatic…
Skill Claude CodeCodex
Build a runnable, multi-page UX prototype as a real SPA when static HTML is insufficient. Use when the prototype must demonstrate routing, state persistence, dynamic data, or interactive flows that exceed what plain HTML/CSS can convey. Provides a Vite + React + Tailwind + Framer Motion + Lucide scaffold, data-driven…
Skill Claude CodeCodex
Drive a real browser from an Frontier FDE for prototype validation, web research, HTML output verification, and accessibility audits. Use when an agent needs to render JavaScript, click/type/screenshot a page, run an axe-core a11y audit, or read a JS-rendered page. Backed by Microsoft's Playwright MCP server…
Skill Claude CodeCodex
Read-only hygiene review that reports cosmetic lint/style findings as LOW advisories and requests explicit approval before cleanup. Genuine defects are assessed separately by impact.
Skill Claude CodeCodex
Rewrite working code into its minimal, elegant form -- lower cyclomatic complexity, fewer lines, no dead code, no needless abstractions -- using a Draft -> Optimize -> Verify loop. Use when asked to compress, minimize, simplify, or make code more elegant WITHOUT sacrificing correctness, boundary validation, or…
Skill Claude Code
Use when reviewing implementation changes for correctness, evidence and release risk with the repository exact-scope rubric and native verification commands.
Skill Claude CodeCodex needs its repo
Implement configuration management patterns including environment variables, secrets, feature flags, and validation strategies. Use when setting up app configuration, managing environment-specific settings, implementing feature flags, storing secrets securely, or validating configuration at startup.
Skill Claude Code
Create upload-ready Microsoft 365 Copilot Cowork plugin packages containing manifest.json, color and outline icons, and one or more agent skills, MCP connectors, or both. Use for Cowork plugin authoring, packaging, and validation requests.
Skill Claude Code
Create upload-ready Microsoft 365 Copilot Cowork skills as zip packages containing SKILL.md plus populated assets, references, and scripts folders. Use for Cowork, co-work, or coworker skill authoring and packaging requests.
Skill Claude CodeCodex needs its repo
Manage dependencies with version pinning, lock files, vulnerability scanning, and update strategies. Use when adding new packages, pinning dependency versions, scanning for vulnerabilities, updating outdated dependencies, or managing monorepo dependency graphs.
Skill Claude CodeCodex
Fan out independent work to multiple subagents with context isolation. Covers when to parallelize (independent reads, multi-file searches, parallel analysis), when not to (writes, dependent steps, shared mutable state), bounded concurrency limits, and the anti-patterns that turn parallel dispatch into corruption. Use…
Skill Claude CodeCodex needs its repo
Write effective documentation including inline docs, README structure, API documentation, and code comments. Use when writing README files, documenting APIs, creating architecture decision records, adding inline code documentation, or setting up documentation tooling.
Skill Claude CodeCodex needs its repo
Implement robust error handling with exceptions, retry logic, circuit breakers, and graceful degradation. Use when designing error handling strategies, implementing retry policies, adding circuit breakers, configuring timeouts, or building health check endpoints.
Skill Claude CodeCodex
Run a metric-driven autonomous experimentation loop on an isolated branch. Use when a task has a measurable target (latency, bundle size, test pass-rate, build time, memory, score, accuracy) and the agent should propose changes, measure each attempt against a baseline, keep wins and revert losses, and produce a…
Skill Claude CodeCodex needs its repo
Decide what to do with a feature branch once the work itself is complete. Covers the merge / open PR / keep open / discard decision, the pre-disposition checklist (loop complete, tests green, compound capture resolved), and cleanup commands for branches and worktrees. Use whenever an agent says "tests pass, now what?".
Skill Claude CodeCodex
Run parallel agent sessions on the same repo using git worktrees without corrupting the primary checkout. Use when an agent needs an isolated working directory for a prototype, a long-running experiment, a parallel branch, or a deploy artifact, especially when Frontier is being driven from a single primary clone.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: