devx-plugins

Stages the changes produced in this session, excludes junk and secrets, and generates a conventional commit. Triggered when the user runs /devx-git:ci or asks to commit.

Updates the current branch onto an origin branch via rebase, with a recoverable backup, safe conflict resolution, and recovery steps. Use when the user runs /rebase or asks to rebase/update their branch onto main (or another origin branch).

Audits an agent, tool loop, or inference request across six dimensions (prompt engineering, tools definition, context engineering, cache usage, evaluation, guardrails) and produces a scored gap analysis with severity ratings and concrete remediations. Framework-agnostic; recognizes patterns from Anthropic SDK, OpenAI SDK, Vercel AI SDK, and OpenAI Agents SDK. Triggers on: audit my agent, review tool loop, audit inference request, agentic engineering review, audit prompt, review agent code, check prompt caching, evaluate guardrails.

Rewrites a given prompt or agent definition by applying Anthropic prompt-engineering best practices — clarity and directness, context and motivation, XML structure, role assignment, long-context layout, output format control, communication-style calibration, and parallel-tool-call affordance. Produces a before/after with per-change rationale. Triggers on: optimize this prompt, improve my prompt, rewrite prompt, prompt optimization, refine system prompt, tune agent prompt, polish prompt for production.

Analyzes project architecture and generates ASCII state machine and sequence diagrams. Use for explaining a project, analyzing architecture, tracing an entrypoint, showing a state machine, or generating a sequence diagram.

Audits a project's agentic harness (CLAUDE.md, AGENTS.md, .claude/rules, .claude/settings.json) and refactors it into a layered, path-scoped configuration that loads only what is relevant. Rewrites CLAUDE.md and AGENTS.md as a thin critical-rules layer, segments domain rules with `paths:` frontmatter, and adds deny-first permission guardrails. Use for: fixing the harness, auditing claude.md, refactoring agentic configuration, improving agent rules, segmenting rules by path, reviewing settings.json, harness review, or when claude.md is too long.

Evaluate and improve a plugin's skills by applying Anthropic's skill authoring best practices. Use to fix, improve, or review skills for a specific plugin or agent team.

This skill should be used when the user asks to "security review this PR", "review this diff for vulnerabilities", "appsec review these changes", "audit this branch for auth, injection, or data exposure bugs", "check this code for exploitable security issues", or requests a focused application security review of pending changes.

Reviews pull requests and code changes for correctness, conventions, maintainability, performance, test coverage, and security. Use when the user asks for a code review, PR review, feedback on a diff, or to check code quality.

Generate advertising visuals — banners, social media ads, display ads, and promotional graphics with auto-prompt building and format-aware aspect ratios. Triggers on: ad, banner, advertisement, display ad, social ad, promo graphic, campaign visual, marketing image, sponsored post image, ad creative.

Generate illustrations in various styles — flat vector, watercolor, line art, 3D clay render, pixel art, and isometric. Auto-detects style from context. Triggers on: illustration, illustrate, flat design, watercolor, line art, pixel art, 3D illustration, isometric, sketch, cartoon, vector art, hand drawn.

Generate logo concepts and brand identity marks — abstract marks, lettermarks, mascot emblems, and geometric icons with minimal clean aesthetics. Triggers on: logo, brand mark, wordmark, lettermark, icon logo, brand identity, monogram, emblem, logo design, logo concept.

Generate product photography and object images — product shots, still life, packaging mockups, food photography, and item compositions with studio lighting. Triggers on: product photo, product shot, still life, object, packaging, food photo, mockup, e-commerce photo, item photography.

People & portrait photography via Google Gemini (Nano Banana Ultimate). Triggers on: portrait, headshot, lifestyle photo, people, person, editorial photo, team photo, professional photo, face, human.

Generate or edit images via Google Gemini (Nano Banana Ultimate). Text-to-image generation and multi-image editing with up to 14 input references. Triggers on: generate image, create image, edit image, make a picture, draw, render, visualize, banana, create visual.

Generate web design assets — hero backgrounds, landing page visuals, card images, section dividers, and motion design keyframes with dark/light mode support. Triggers on: web design, hero image, hero background, landing page background, website asset, section graphic, UI mockup, web banner, motion design asset, web illustration.

Generate bold, high-contrast YouTube thumbnail images with dramatic framing, exaggerated expressions, and click-optimized compositions via Gemini. Triggers on: youtube thumbnail, thumbnail, youtube, video thumbnail, yt thumbnail, video cover image, click-worthy thumbnail.

Audits React codebases for anti-patterns (useEffect misuse, missing cleanup, stale closures, derived-state-in-effects, memory leaks) and produces a scored gap analysis table with severity ratings. Applies prioritized fixes on request. Triggers on: audit react code, fix react anti-patterns, review react hooks, scan for react issues, check useEffect cleanup, fix memory leaks in react.

Creates a GitHub pull request using gh CLI. Triggered when the user asks to open, create, or submit a PR, or runs /pr.

Generates a complete Astro 5 landing page with Tailwind CSS v4 from copywriting content. Triggers when the user asks to build a landing page, create the HTML/CSS for a landing page, generate an Astro site from copy, or implement a landing page design. Expects structured copywriting input matching the writing-landing-page-copy output format.

Generates high-converting landing page copy through a structured interview and section-by-section writing process. Triggers when the user asks to write landing page copy, create a landing page, write marketing copy for a product, or generate conversion-optimized web copy.