Top Agent Skills

Helps identify and evaluate communities to build a minimalist business around, based on the philosophy of The Minimalist Entrepreneur.

Render declarative UI widgets from JSON for React/Next.js applications, enabling agent-generated UIs, dynamic forms, and interactive cards.

Generate images with Google Gemini native image models via the inference.sh CLI, supporting text-to-image, image editing, multi-image input, and various output options.

Convert text to natural speech using multiple TTS models via the inference.sh CLI, with support for emotion steering, voice cloning, and multi-speaker dialogue.

Remove backgrounds from images using BiRefNet and edit them with Reve via the inference.sh CLI.

Generate multi-speaker dialogue audio with different voices in a single file using the inference.sh CLI.

Create consistent characters across AI-generated images using reference sheets, detailed descriptions, and LoRA techniques.

Choose a prioritization framework based on product stage, team context, and stakeholder needs.

Run a customer journey mapping workshop with adaptive questions to map stages, actions, emotions, pain points, and opportunities for a persona and scenario.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation, using combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded strategies.

Review, triage, validate, and discuss ClawHub GitHub issues and pull requests with structured evidence, best-fix analysis, and maintainer handoff.

Drive end-to-end Convex production migrations with explicit safety gates for destructive operations and cleanup.

Craft portfolio-ready case studies that tell the story of a design project, demonstrating process, thinking, and impact.

Establish design review gates with criteria, checklists, and approval workflows to maintain design quality.

Model complex UI behavior as finite state machines with states, events, and transitions to eliminate impossible states and make behavior predictable.

Identify, evaluate, and prioritize design opportunities using impact-effort frameworks and strategic criteria.

Transform user interview transcripts into structured, actionable insights with key themes, quotes, and action items.

Design rigorous A/B tests with clear hypotheses, controlled variants, appropriate metrics, and sample size calculations.

Analyze a screen's visual hierarchy by evaluating entry point, eye flow, weight distribution, and emphasis, then provide actionable fixes.

Generate interior design visualizations by redesigning existing rooms or creating new concepts with specific styles, colors, and furniture.

Generate artistic top-down photos of keyboard keycaps arranged to spell out custom text messages.

Designs and implements a Google Cloud solution for live, bidirectional multimodal streaming workloads with AI agents, covering requirements discovery, architecture design, and deployment planning.

Control cmux workspaces, panes, surfaces, and agent sessions safely from macOS terminal workflows.

Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2, covering microservices, WebSockets, and modern Python async patterns.

Generates and explains Makepad DSL code for the Rust `makepad-widgets` crate, covering syntax, inheritance, property overriding, and widget instantiation.

Build production-ready AI agents with type-safe tool use, structured outputs, dependency injection, and multi-model support using PydanticAI.

Executes a phased implementation plan by deploying subagents for implementation, verification, anti-pattern checks, code quality review, and committing.

Generate a serial, multi-chapter narrative digest of a project's claude-mem history, producing one digest per ISO week with coherent story flow across chapters.

Defines the caption model (drop/rail/embed) and overlay law for compositing captions on top of video, never reserving a bottom band.

Audits a project's agent configuration files, establishes a source-of-truth skills directory, normalizes naming, and generates bridge files to make the workspace consistent across Claude Code, Codex, Grok, and generic Agents.

Drive development with tests by writing a failing test before implementing code, and reproduce bugs with tests before fixing them.

Grounds every implementation decision in official documentation, ensuring authoritative, source-cited code free from outdated patterns.

Tests and debugs web applications in real browsers using Chrome DevTools MCP, enabling DOM inspection, console error capture, network analysis, performance profiling, and visual verification with live runtime data.

Protects stateful GKE workloads by configuring backup plans, restore workflows, and disaster recovery using Backup for GKE.

Plans, configures, and manages GKE networking including private clusters, VPC-native configurations, Gateway API, DNS, ingress/egress, Dataplane V2, and IP planning.

Configures GKE workload reliability with PodDisruptionBudgets, health probes, topology spread constraints, and graceful shutdown patterns.

Solve LP, MILP, and QP problems using the cuOpt C API with a consistent build pattern and core calls.

Provides patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

Converts narrative technical documents into structured mathematical problem specifications with variables, constraints, objectives, and uncertainty.

Upload local images to GitHub and get canonical user-attachments embed URLs for use in PRs, issues, comments, or README files.

Query, inspect, and manage Redis databases from the command line using redis-cli, covering connection, data operations, scanning, and server diagnostics.

Updates StyleSeed engine files in a project by detecting the current setup, comparing versions, and safely applying additive updates without overwriting user code.

Use Expo DOM components to run web code in a webview on native and as-is on web, enabling incremental migration of web code to native.

Helps write and edit EAS CI/CD workflow YAML files for Expo projects, including schema validation and resource fetching.

Migrate AEM replication code from legacy CQ Replicator and Sling Replication Agent APIs to the Sling Distribution API for AEM as a Cloud Service, covering agent selection, async handling, and service-user setup.

Migrates AEM Cloud Service code from legacy AssetManager APIs (createAssetForBinary, getAssetForBinary, removeAssetForBinary, client-facing createAsset) to Direct Binary Access or in-JVM resolver patterns, covering IMS authentication and service-user setup.

Diagnose and fix common AEM 6.5 LTS replication issues including blocked queues, connectivity failures, and content distribution problems.

Map every stakeholder before engaging anyone, using an equity-aware process that captures not just obvious sponsors but gatekeepers, impacted communities, and overlooked voices.

Plan tailored engagement for a specific stakeholder before critical conversations, milestones, or relationship repairs.

Enforces an opinionated UI baseline to prevent AI-generated interface slop, covering Tailwind CSS, accessible components, interaction patterns, animation constraints, typography, layout, and performance.

Routes general Convex requests to the appropriate project skill, installs official Convex AI guidance, and provides command preflight instructions for Convex CLI operations.

Moderate ClawHub platform resources including skills, users, org publishers, plugin packages, and staff email using the repo-local admin CLI tool.

Drafts structured goal-loop prompts for long-running agent work with verifiable stop conditions, validation commands, and documentation requirements.

Build production-ready LLM applications, advanced RAG systems, and intelligent agents with vector search, multimodal AI, and enterprise integrations.

Reviews code through the lens of 12 classic software engineering books, catching design smells, coupling issues, and architectural risks that linters miss.

Upscales and enhances image and video resolution using AI.

Treats rough ideas as competing organisms on an evolution island, scoring, selecting, crossing, and evolving them through structured rounds to surface the strongest concepts.

Reads every source file in a codebase to build a deep understanding of the project, using pagination for large files.

Merges multiple diagnosis snapshots from dbs-save into a single, timestamped Markdown report organized by topic.

Scans copy for AI-generated writing patterns and outputs a diagnostic report. Diagnosis only by default.