Fewer subscriptions.
More vibe-coding.

Self-hosted CRM with customizable records and interfaces for AI agents

Build and operate private clouds, edge infrastructure, and distributed deployments for VMs, Kubernetes, and GPU workloads.

name: actualize description: "Reconcile the project's FPF state with recent repository changes" --- # Actualize Knowledge Base This command is a core part of maintaining a living assurance case. It keeps your FPF knowledge base (`.fpf/`) in sync with the evolving reality of your project's codebase. The. The workflow is tied to actualize.

Self-hostable web analytics for visitor activity and custom events.

Manages a local skills-hub catalog by searching, inspecting, installing and removing agent skills through a desktop application.

Self-hosted billing and client management for online service businesses.

Automates headless browser tasks through Playwright CLI for page navigation, interaction and screenshot evidence.

name: accessibility-compliance-accessibility-audit description: "You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance." --- # Accessibility Audit and Testing You are an. The workflow is tied to accessibility-compliance-accessibility-audit and specifies practical inputs, decisions, or outputs rather than only providing general inspiration.

Explores a feature idea through a structured brainstorm and records the resulting decision context for implementation.

Keeps a PromptHub project’s README and version metadata synchronized during a release.

Coordinate software delivery across product, project, and QA workflows.

Self-host your music collection and access it through a web interface.

name: swift-concurrency description: Diagnose Swift Concurrency issues, refactor callback-based code to async/await, and guide Swift 6 migration when working with tasks, actors, @MainActor, Sendable, data races, thread safety, or concurrency-related compiler and linter warnings. --- # Swift Concurrency ##. The workflow is tied to swift-concurrency and specifies practical inputs, decisions, or outputs rather.

A specialized performance guide for React Native applications, including frame rate, startup time, memory use, rerenders, and animation costs.

name: adjudicate-review description: Turn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread damage correct work. Every finding is a CANDIDATE until checked against the actual source. Use. The workflow is.

Self-hosted ingress for routing private-network services through encrypted WireGuard tunnels.

A decision aid limits endless research by setting a decision deadline, information budget and stop rule.

Creates or retrieves marketing video and image assets by calling Arcads AI’s external API from a coding-agent workflow.

name: user-research-cookiy description: > End-to-end user research assistant — qualitative and quantitative. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, quantitative research, user surveys, survey design. The workflow is tied to user-research-cookiy and specifies practical inputs, decisions, or outputs rather than only.

A self-hosted collaborative wiki with Markdown pages and Git-backed history.

Generate, extend, or audit design tokens in DTCG format with the 3-tier architecture (primitive → semantic → component). Use when the user wants a color palette, type scale, spacing/shadow/radius/motion tokens, multi-brand theming, or wants to validate token files. Covers colors, typography, spacing. The workflow is tied to design-tokens and specifies practical inputs, decisions.

Takes an existing Azure Kubernetes Service cluster from prerequisite checks through AI Runway controller installation, GPU/provider assessment, and a first model deployment.

Stores cross-agent messages and task status in SQLite so Claude Code, Codex and other agents can coordinate locally.

Self-host a link landing page and community, then adapt the Laravel codebase to your workflow.

Track domain details, renewals, changes, and website health in one self-hostable portfolio.

A repository-specific review procedure for checking adk-bot pull requests against source code, task intent, formatting, and project architecture.

name: build-review-interface description: > Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels. --- # Build a Custom Annotation Interface ##. The workflow is tied to build-review-interface and specifies.

Plans safe Terraform releases, provisioners, environment isolation, host bootstrap, and drift or deployment troubleshooting.

Reviews a LinkedIn account’s published posts and analytics to identify which content performed, why, and what to change. It emphasizes the account’s own evidence as the reliable basis for conclusions and extracts repeatable patterns from actual results.

A self-hosted electronic lab notebook and resource database for research teams.

Creates or updates a test suite for changed code by reading project preferences and choosing cases for each changed file.

Designs a 360-degree feedback survey or turns gathered feedback into a structured report of themes, strengths, and development areas. It uses behaviorally anchored ratings and requests reviewer relationships and anonymity settings so the instrument or narrative matches the intended feedback process.

Analyzes a codebase to explain structure, technology stack, key modules and execution paths.

Self-host a videoconferencing server and build tools or clients around its group configuration.

A customizable PHP CMS and framework for building websites, blogs, and mobile APIs.

Serve and organize personal media for UPnP-compatible devices on your home network.

name: app-store-preflight-skills description: > Scan an iOS/macOS Xcode project for common App Store rejection patterns before submission. Use when preparing an app for App Store review, after receiving a rejection from Apple, or when auditing metadata, subscriptions, privacy manifests, entitlements, or. The workflow is tied to app-store-preflight-skills and specifies practical inputs, decisions, or.

Plans empirical evaluation for AI products by analyzing real failures, selecting human/code/LLM-as-judge methods, building gold sets, and incorporating repeatable checks into CI.

Analyze PDF layout, extract content, and convert documents through a web interface or REST API.

Analyzes KiCad projects and PDF schematics, PCB layouts, Gerbers, footprints, symbols, netlists, and design rules. It traces nets, cross-references schematic and board, extracts BOM data, checks DRC/ERC and manufacturability, and labels findings with confidence and evidence.