Top Agent Skills

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Structures immediate next steps into a dependency-ordered plan, gated by the current action_gate mode, with checkpoints and risk flags before execution.

Generates design systems and UI/UX recommendations for React Native projects, with domain-specific searches for styles, colors, typography, and best practices.

Configures a repository's issue tracker, triage labels, and domain documentation so engineering skills can operate correctly.

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting, then commit with git.

Autonomously repairs failed task verification by choosing retry, decompose, prune, or escalate strategies before surfacing to the user.

Enforces a verification gate before any completion claim, requiring fresh command output as evidence.

Migrate TypeScript test code from `as` assertions to type-safe `shoehorn` helpers like `fromPartial` and `fromAny`.

Executes a written implementation plan in a separate session, reviewing it critically, running tasks with verification, and stopping to ask for help when blocked.

Generates multiple radically different interface designs for a module, compares them, and synthesizes the best approach.

Implements Apple's Liquid Glass design system for iOS 26 apps, covering SwiftUI, UIKit, and WidgetKit integration with glass effects, morphing transitions, and customization.

Displays the complete GSD command reference for hierarchical project planning with Claude Code.

Detects the current state of an Open-workspace project and advances to the next logical workflow step, from discussion through planning, execution, verification, and completion.

Captures quick notes as timestamped markdown files, lists them, and promotes them into todos with zero friction.

Rolls back Open-workspace phase or plan commits using a phase manifest with dependency checks and a confirmation gate, preserving history via git revert.

Creates brand identities, logos, corporate identity programs, HTML presentations, banners, icons, and social media images using AI generation and HTML/CSS-to-screenshot workflows.

Triage and review open GitHub issues and PRs against project contribution templates, producing a compliance report and optionally labeling, commenting, or closing items.

Executes small ad-hoc tasks with GSD guarantees, spawning planner and executor agents, tracking tasks in .planning/quick/, and updating STATE.md. Supports composable flags for discussion, research, plan-checking, and verification.

Runs focused experiments to validate feasibility of an idea, saving artifacts to .planning/spikes/ and supporting both idea and frontier modes.

Validates the integrity of a project's .planning/ directory, reporting missing files, invalid configurations, and inconsistent state, with optional auto-repair of safe issues.

Imports external plan files into a GSD-structured project, detecting conflicts against existing roadmap, requirements, and locked decisions before writing a validated PLAN.md.

Runs independent AI CLI reviewers over phase plans and merges their feedback into a REVIEWS.md file.

Ingest, index, search, edit, and generate video and audio assets from files, URLs, RTSP feeds, or desktop capture, with real-time alerts and stream links.

Archives phase directories from completed milestones into versioned archive folders, showing a dry-run summary and moving directories only after confirmation.

Guides developers through Socratic exploration of ideas, offering research and routing outputs to planning artifacts.

Captures ideas, tasks, or issues during a GSD session as structured todos for later work, enabling a thought-to-capture-to-continue flow without losing context.

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.

Ingests video and audio from files, URLs, live feeds, or desktop capture; indexes and searches moments with timestamps; transcodes, edits timelines, generates media assets, and emits real-time alerts.

Creates technical explainer animations with Manim, covering graphs, workflows, and system diagrams, and produces storyboards, scene plans, and rendered MP4s.

Produces a maintainer-grade review of a pull request or large contribution, explaining the change tutorial-style and delivering a polished HTML or Markdown report with a concrete merge recommendation.

Diagnose and audit SEO issues affecting crawlability, indexation, rankings, and organic performance.

Produces clear, credible, and action-oriented marketing copy for landing pages and emails, enforcing brief confirmation and strict no-fabrication rules.

Guides collaborative dialogue to turn ideas into designs and specs, exploring intent and requirements before any implementation.

Creates detailed, bite-sized implementation plans from specs or requirements, with exact file paths, code, and TDD steps.

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries for database-like note views.

Improves user onboarding and activation by defining the aha moment, designing effective onboarding flows, and building engagement loops to boost retention.

Guides the creation, editing, and verification of agent skills using a test-driven development approach, with structured documentation and quality gates.

Creates agent company packages conforming to the Agent Companies specification, either from scratch or by wrapping an existing repository.

Audits top-level documentation against recent git history to detect drift, applies minimal edits, and opens a pull request.

Selects and scores marketing ideas for SaaS products using a feasibility scoring system to prioritize high-impact, low-effort opportunities.

Designs and optimizes customer referral and affiliate programs, covering program type selection, incentive structuring, and trigger-moment identification.

Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making.

Drafts Terms of Service and Privacy Policy documents by auditing a codebase and marketing site to infer company details, then asking only for missing information.

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax for use in Obsidian notes.

Analyzes campaign performance with multi-touch attribution, funnel conversion analysis, and ROI calculation for marketing optimization.

Guides open source license selection, comparison, compliance review, and drafting of LICENSE/NOTICE files using canonical texts.

Optimizes in-app paywalls and upgrade flows to convert free users to paid or upgrade users to higher tiers at moments of peak value.

Orchestrates multi-agent project builds with persistent state, parallel execution, and atomic git commits.

Test GitHub Actions workflows locally using act, covering installation, configuration, and usage patterns for debugging and iterative development.

Performs mutations on plyr.fm such as uploading, deleting, and liking tracks using the CLI, while the MCP server remains read-only.

Defines a structured eval-driven development workflow with define, implement, and verify phases, including capability, behavior, and non-functional checks, plus optional swarm mode for parallel evaluation.

Provides guidelines for writing conventional commit messages and pull request descriptions, including merge strategy and GitHub username verification.

Creates GitHub pull requests, issues, and discussions with semantic analysis, template selection, and label application.

Process PDFs with Python and command-line tools: extract text and tables, merge, split, rotate, create, watermark, OCR, and handle passwords.

Runs a local voice MCP server in Rust for text-to-speech and speech-to-text, with build, test, and configuration guidance.

Manage AWS EKS clusters, node groups, IRSA, add-ons, and workloads using AWS CLI and eksctl commands.

Performs security scanning, compliance checks, deployment planning, and infrastructure setup, with optional dependency auditing and bundle size analysis.

Coordinates multi-phase problem-solving workflows with structured task tracking and verification.

Search and explore coding session history across multiple AI agents, including Claude Code, Codex, Cursor, Gemini CLI, and Aider, with commands for indexing, searching, viewing, and exporting conversations.

Commits changes, rebases on main, and creates a pull request to finish a development task.