Top Agent Skills

Explains how bundles work in the Antigravity skills repository and how to use them on WSL2 Debian 13, including viewing available bundles, choosing one, and referencing skills in prompts.

Creates, edits, converts, and automates LibreOffice Calc spreadsheets in ODS format, including formulas, charts, and batch processing.

Generates and edits Office Open XML (DOCX) documents with schema-compliant XML patterns for headings, lists, tables, formatting, images, hyperlinks, and tracked changes.

Documents and explains an existing codebase as it is, without suggesting improvements or architectural changes.

Provides C programming guidance for systems programming, memory management, and performance, with best practices for writing safe and efficient code.

Launches an RSVP speed reader that displays text one word at a time with Spritz-style highlighting.

Evaluates execution transcripts and output files against a list of expectations, assigning pass/fail verdicts with cited evidence and critiquing the assertions themselves.

Use the official Anthropic C# SDK to send messages, stream responses, and define tools with JSON schema.

Guides incremental code improvements, error-proofing through types and validation, and standardization for higher quality software.

Analyze single-cell RNA-seq data with Scanpy, covering quality control, normalization, dimensionality reduction, clustering, marker gene identification, and visualization.

Transforms rough sketches or text descriptions into photorealistic 3D renders using Vizcom's AI rendering modes and prompt weighting.

Performs astronomical data analysis with astropy: coordinate transformations, unit conversions, FITS file handling, cosmological calculations, time systems, tables, and WCS.

Designs secure, high-performance GraphQL APIs by applying schema design, DataLoader batching, query depth limiting, and resolver-level authorization patterns.

Write idiomatic, high-performance PHP code using generators, iterators, SPL data structures, and modern OOP features.

Manages environment variables securely by masking sensitive values, validating schemas, and injecting secrets into commands without exposing them.

Enforces a machine-readable behavioral contract for multi-agent development, mandating specification-first workflows, git checkpoints, context lineage, and quality gates.

Guides database design, implementation, optimization, migration, pipeline development, quality, and operations across SQL and NoSQL platforms.

Build clean async pipelines with fp-ts TaskEither, replacing nested try/catch with composable error handling and parallel execution patterns.

Sets up the Manifest observability plugin for AI agents, including installing the plugin, configuring the API key and endpoint, and verifying the gateway connection.

Identify the type of problem you're stuck on and dispatch to the appropriate problem-solving technique.

Analyzes runtime history to identify failures and inefficiencies, then autonomously writes improvements using a protocol-constrained evolution engine. Communicates with EvoMap Hub via a local Proxy mailbox.

Backtests quantitative trading strategies across 9 engines and 25 data sources, analyzes trade journals, and runs multi-agent research teams.

Builds, refines, tests, or validates a CLI-Anything harness for a GUI application or source repository, producing a stateful Click CLI with JSON output and REPL mode.

Transforms chaotic notes, voice dumps, and meeting transcripts into a structured, interlinked knowledge base inside Obsidian by extracting entities, generating wikilinks, and surfacing forgotten context.

Builds, refines, tests, or validates a CLI-Anything harness for a GUI application or source repository, producing a Python-based Click CLI with REPL mode and JSON output.

Provides a structured template for creating new agent skills, including workflow steps, input/output schemas, and quality gates.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Runs NGS read QC, alignment, and BAM processing, wrapping FastQC, BWA/Bowtie2/Minimap2, SAMtools, and MultiQC for automated read-to-BAM workflows.

Manages the full blog lifecycle: strategy, briefs, outlines, writing, analysis, optimization, schema generation, repurposing, and editorial planning, with dual optimization for Google rankings and AI citation platforms.

Mounts a fetch-native CopilotRuntime on any JS server, wires middleware, selects an AgentRunner, and integrates built-in or external agent frameworks.

Updates the installed Aegis Method Pack on the current AI coding host, including registration, dry-run previews, and post-update verification.

Audits an Obsidian wiki for structural issues like orphaned pages, broken wikilinks, stale content, and provenance drift, with optional automated fixes.

Pushes the current branch and opens a GitHub pull request with a structured title and body.

Structured workflow to reproduce, diagnose, plan, fix, verify, and record a bug fix, requiring a deterministic reproduction before diagnosis and minimal changes only.

Runs a two-wave validation pipeline (deterministic checks then rule-based checks) before every git commit, writing a sentinel file that a pre-commit hook enforces. Includes optional quick mode (first wave only) and a fix loop with up to three iterations.

Designs and iterates production-grade frontend interfaces, covering UX review, visual hierarchy, accessibility, performance, responsive behavior, theming, typography, layout, color, motion, and design systems. Handles websites, landing pages, dashboards, product UI, components, forms, and more.

Audits a paper draft by tracing every numeric claim and assertion back to result files on disk, flagging untraced, mismatched, stale, uncited, and phantom references.

Grades and classifies evaluation batch results, applying exclusions, diagnosing failure modes, computing pass rates, and generating summary tables for papers.

Stress-tests a plan against the project's domain model and documented decisions, sharpening terminology and updating DOMAIN.md and ADRs inline as decisions crystallize.

Runs an adversarial, decision-aware review of all session work before committing, checking decision adherence and code maintainability, and applies only user-authorized fixes.

Analyzes evaluation results by requiring a stated hypothesis before examining data, then compares expectations to actual result files to prevent post-hoc rationalization.

Finds architectural friction in a codebase and proposes deep-module refactors to improve testability and AI-navigability, informed by the domain glossary and ADRs.

Guides users through structured decision-making with weighted scoring, criteria analysis, and clear recommendations, including quick and interview modes.

Runs the current git diff through the Codex CLI for an independent, read-only second-opinion review, then triages findings back into the session for Claude to apply fixes.

Provides a higher-level map of relevant modules and callers using the project's domain glossary when you're unfamiliar with a code area.

Continuously improves Claude's effectiveness by recognizing patterns, saving memory, creating skills, and refining project knowledge. Use when Claude notices repeated workflows, encounters a problem it solved before, wants to save something for future sessions, needs to create a reusable skill, or when the user asks.

Runs a plan file through the Codex CLI as an independent adversarial reviewer, then folds accepted findings back into the plan. Read-only sandbox; Codex never edits.

Analyzes a codebase with multiple agents and builds an interactive React knowledge graph dashboard for onboarding and visual architecture exploration.

Assists with software engineering tasks including writing, editing, and explaining code, searching codebases, running commands, managing files, debugging, and implementing features.

Generates CNC toolpaths, selects machining strategies and tools, optimizes cutting parameters, simulates operations, and post-processes to machine-specific formats.

Explains ACID transaction properties and provides Python implementations for atomic operations, consistency validation, isolation levels, and durable storage.

Designs cloud architectures, selects services, optimizes costs, and ensures security for cloud-native applications.

Displays HTML content on connected OpenClaw nodes (Mac, iOS, Android) via a local HTTP server and node bridge, with actions for presenting, navigating, evaluating, and capturing snapshots.

Builds single-page applications with component-based architecture, dependency injection, reactive forms, and routing.

Provides guidance and best practices for working with Cypress, covering setup, development, deployment, and troubleshooting.

Explains chemical principles, reactions, and safety, and supports analysis, handling, and storage guidance.

Provides aerospace domain knowledge, terminology, and guidance on aircraft and spacecraft principles, regulations, and mission planning.

Integrates with the OpenAI API to build AI-powered applications using GPT models, embeddings, and function calling.

Provides guidance on using PyTorch for deep learning, covering tensors, autograd, nn.Module, DataLoaders, and best practices.

Create, search, and manage Bear notes on macOS using the grizzly CLI, including token-based operations for appending text and listing tags.