.agents

Know how Pi model selection is configured and changed: default model, thinking level, one-off model switches, Ctrl+P scoped model cycling, and prompt-editor modes for this repo.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Interview the user relentlessly about a plan, decision, or idea by asking all independent questions in batches, round by round. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Review a diff, branch, PR, commit, or work-in-progress change along two separate axes: Standards (repo conventions, maintainability, safety) and Spec (does the change implement the originating issue/PRD/request?). Runs focused sub-agents in parallel and reports prioritized, actionable findings side by side. Use when the user wants to review a branch, PR, WIP changes, or asks to "review since X".

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this/find bugs", or reports something broken/throwing/failing/slow.

Read this skill before making git commits

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up code", "refactor for clarity", "improve readability", or review recently modified code for elegance. Focuses on project-specific best practices.

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.

Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

Audit a GitHub repository's configuration against open-source security best practices — settings, workflows, credentials, rulesets, publishing pipeline — and apply fixes on approval.

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

Use before writing or changing code.

Crawl and extract web content using the Crawl4AI CLI (crwl).

Use this skill whenever a task involves a document file (PDF, DOCX, PPTX, XLSX, or image) and you need to read it or pull text, tables, or specific values out of it — to answer a question about its contents, look up a figure, or extract data. Provides fast, local, model-free extraction via the `lit` CLI with disciplined, low-cost search patterns.

Atlassian CLI (acli) reference for Jira Cloud. Use when the user needs to interact with Jira work items via the command line — searching, creating, viewing, editing, assigning, transitioning, commenting, linking, or bulk-operating on tickets. Triggers on mentions of "acli", "jira cli", "jira ticket", "work item", or any task involving Jira automation from the terminal.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.

Become Fable: a superintelligent orchestrator that owns the goal, chooses the best execution strategy at each step (direct work, subagents, or workflows), and validates all delegated work with independent judgment — delegates are less intelligent and their output is never trusted at face value. Use when the user invokes /fable or asks for Fable-mode orchestration of a large or high-stakes task.

Rewrite prompts for legitimate Fable work so they are clearer, safer, authorized, and policy-aligned. Use when you want a Fable prompt rewritten, not to bypass safety systems or disguise harmful intent.

Manage Hetzner Cloud infrastructure using the hcloud CLI. Use when the user needs to create/manage servers, volumes, networks, firewalls, load balancers, floating IPs, primary IPs, SSH keys, images, certificates, placement groups, storage boxes, DNS zones, or any Hetzner Cloud resource. Also use for hcloud setup, context management, scripting hcloud commands, CI/CD automation with Hetzner, or generating hcloud command sequences. Triggers on mentions of "hcloud", "hetzner", "hetzner cloud", or any Hetzner infrastructure task.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer

Create slide presentations from Markdown using Marp. Use when: (1) Creating presentation slides or decks (2) Converting markdown to PDF/PPTX/HTML slides (3) User mentions "marp", "slides", "presentation", or "deck" (4) Requests for speaker notes, slide themes, or presentation exports (5) Vague requests like "make it look good" or "make slides professional" Supports themes, backgrounds, math, diagrams, and multiple export formats.

Fetch and analyze Sentry issues, events, transactions, and logs. Helps agents debug errors, find root causes, and understand what happened at specific times.

Fetch a URL or convert a local file (PDF/DOCX/HTML/etc.) into Markdown using `uvx markitdown`, optionally it can summarize

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Work on PrestaShop core, module, and theme projects. Use for PrestaShop architecture, CQRS/domain code, Symfony back office, legacy ObjectModel/controllers, modules, hooks, multistore, translations, upgrades, tests, or themes.