Pre-Action Guard
A QA gate that validates potentially destructive or irreversible actions before execution.
Impasse Detector
Detects when the agent is stuck in a reasoning loop or unproductive state by analyzing tool usage and sentiment patterns.
MCP Connector
Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.
Generate .gitignore
Create or update .gitignore files by fetching standard templates from the GitHub/gitignore repository.
Detect Duplicate Files
Identify duplicate files across the workspace using SHA256 hashing to reduce redundancy and confusion.
Environment-Specific Bash Mastery
Generate optimized scripts that utilize the specific hardware (cores, GPU, OS) of the execution environment.
Dependency Tree Mapping
Generate comprehensive dependency graphs to identify "single-points-of-failure" and impact analysis chains.
llms.txt & Doc Parsing
Rapidly ingest documentation via the /llms.txt standard to gain "fast-track" understanding of libraries without scraping entire sites.
Async Feedback Loop
Enables mid-stream course correction by monitoring a FEEDBACK.md file for user interventions. Allows the agent to incorporate new instructions without restarting the task.
Agent-Swarm Spawner
Prepares isolated sub-workspaces for parallel agent execution. Copies context and generates specific mission instructions for "Worker" agents.
Adversarial Reviewer
Generates a 'Red Team' critique of recent code or plans to identify weak assumptions and edge cases.
Failure Postmortem
Structured logging and analysis of execution failures to prevent recurrence.
Skill Gap Identifier
Analyzes failures or user requests to automatically scaffold new skills, ensuring structural evolution.
State Overlay Consistency Checker
Detect and prevent state-visibility violations across execution contexts within a single transaction.
Paste Sanitizer
Convert mixed terminal output and instructions into safe, paste-ready command blocks.
Error-State Recovery
Wraps command execution in a self-healing loop. Uses heuristics to auto-fix common errors (missing deps, locked files) or escalates to the Agent with structured error context.
Clean Build Artifacts
Removes ignored build artifacts (bin, obj, node_modules) to reclaim space and fix ghost build errors. Safely respects .gitignore.
Update Intent Breadcrumbs
Updates standardized intent files (NEXT.md, STATE.json) to maintain context across agent sessions.
Context Window Pruner
Optimize information density by filtering workspace files based on relevance to the current task. Excludes high-noise files (lockfiles, assets) and prioritizes source code matching semantic queries.
Run EELS Test Suite
Automates running the Ethereum Execution Layer Specification (EELS) tests against a local EVM implementation. Handles venv setup, execution, and result parsing.
Project-Wide Rename
Safely renames a .NET project (solution, projects, namespaces, directories) from one name to another. Supports Planned (clean) and Recovery (dirty) modes.
Sync Multi-Repo State
Detects drift between multiple git repositories (e.g. forks, mirrors, or multi-module projects). Generates a drift report and optionally applies sync actions.
Deterministic Planner
Enforces a structural planning phase before execution. Generates and validates PLAN.json to ensure every task has a clear objective, steps, verification method, and rollback strategy.
fynd-backend-microservices
Expert debugging for FYND's Kubernetes/GCP/Kafka/Node.js backend. Use for pods crashing, Kafka lag, Redis memory high, API latency, DB migration failures, LLM cost spikes, memory leaks, and service failures.
deepdive
Universal data agent skill for natural language database querying, schema visualization, and automated chart generation. Use when working with databases, analyzing data, creating visualizations, exploring table structures, or needing insights from PostgreSQL, MySQL, SQLite, BigQuery, Snowflake, or Redshift. Triggers include "query the database", "analyze this data", "show me a chart", "visualize the schema", "what's in this table", or any data exploration tasks.
shadcn-baseui
Enforces Base UI patterns in shadcn/ui projects. Prevents LLMs from incorrectly suggesting Radix UI patterns (asChild, etc.) when working with Base UI.
cohere-rerank
Cohere reranking reference for two-stage retrieval, semantic search improvement, and RAG pipelines. Covers Rerank v4 models, structured data reranking, and LangChain integration.
cohere-typescript-sdk
Cohere TypeScript/JavaScript SDK reference for chat, streaming, embeddings, reranking, and tool use. Use when building Node.js or browser applications with Cohere APIs.
cohere-structured-outputs
Cohere structured outputs reference for JSON mode, JSON Schema validation, and strict tool parameters. Guarantees valid output structure for data extraction, classification, and function calling.
cohere-streaming
Cohere streaming reference for real-time text generation, tool use events, and RAG citations. Covers all stream event types and async streaming patterns.
cohere-python-sdk
Cohere Python SDK reference for chat, streaming, tool use, structured outputs, and RAG. Use when building Python applications with Cohere's Command models, embeddings, or reranking APIs.
cohere-langgraph
Cohere LangGraph agents reference for building ReAct agents, multi-tool workflows, agents with memory, and human-in-the-loop patterns. Covers both prebuilt and custom agent architectures.
cohere-java-sdk
Cohere Java SDK reference for chat, streaming, embeddings, reranking, and tool use. Use when building Java/Kotlin applications with Cohere APIs.
cohere-go-sdk
Cohere Go SDK reference for chat, streaming, embeddings, reranking, and tool use. Use when building Go applications with Cohere APIs.
cohere-embeddings
Cohere embeddings reference for vector search, semantic similarity, and RAG. Covers Embed v4 (multimodal, Matryoshka dimensions), input types (CRITICAL for search quality), batch processing, and LangChain integration.
cohere-cookbooks
Official Cohere cookbooks and tutorials for production patterns. Links to RAG implementations, agent workflows, enterprise integrations, and real-world use cases from the Cohere developer experience repository.
cohere-best-practices
Production best practices for Cohere AI APIs. Covers model selection, API configuration, error handling, cost optimization, and architectural patterns for chat, RAG, and agentic applications.
cohere-langchain
Cohere LangChain integration reference for ChatCohere, CohereEmbeddings, CohereRerank, and CohereRagRetriever. Use for building RAG pipelines, chains, and tool-calling workflows with LangChain.
digital-clone
>
mcp-expert
Expert in Model Context Protocol (MCP) server development. Use when building MCP servers, creating tools for Claude, implementing resources, debugging MCP connections, or integrating databases with Claude Code.
nodejs-expert
Expert Node.js and TypeScript development assistant. Use when writing, reviewing, or debugging Node.js code, TypeScript projects, async programming, streams, performance optimization, or npm packages.
sqlserver-expert
Expert in Microsoft SQL Server development and administration. Use when writing T-SQL queries, optimizing database performance, designing schemas, configuring SQL Server, or integrating SQL Server with Node.js using mssql package.
mcp-development
Complete MCP development toolkit for creating, debugging, testing, and reviewing MCP servers. Use when setting up new MCP projects, creating tools, debugging connection issues, reviewing MCP code, or generating documentation.
akash
>
project-migrate
Migrate a project directory to a new path while preserving Claude Code project memory and project-level knowledge. Use this skill when the user wants to move or copy a project to a different directory path — phrases like "/project-migrate", "migrate project to", "move project to new path", "relocate project directory". This skill requires the project-memory skill to be installed separately. It copies the project directory (preserving permissions), migrates Claude Code memory, and persists project knowledge via project-memory so the AI can quickly understand project progress in the new location.
commit
Generate commit messages following the Conventional Commits 1.0.0 spec and commit using gitflow-toolkit (`git ci -F`). Use this skill whenever the user wants to commit changes — phrases like "提交", "帮我提交", "提交变更", "提交一下", "提交代码", "/commit", "commit these changes", "commit this", "create a commit", "help me commit", or any explicit request to create a git commit. Also use when the user finishes a task and asks you to commit the result. This skill auto-stages files — users do not need to stage manually.
mise
Install missing language runtimes and dev tools via mise. Use when (1) a command fails due to missing runtime (e.g. node not found, python3 not found, go command not found), (2) user asks to install/setup a language runtime or SDK (node, python, go, rust, java, ruby, etc.), (3) user mentions version management for languages, or (4) setting up a new development environment.
api-docs
|
sfnext-configuration
Manage Storefront Next application configuration using config.server.ts, schema types, environment variables, and multi-site setup. Use when editing config.server.ts, adding PUBLIC__ environment variables, using useConfig or getConfig, or configuring multiple sites. NOT for initial project creation — see sfnext-project-setup.
sfnext-routing
Implement file-based routing in Storefront Next with React Router 7. Use when adding new pages, creating layout routes, defining route parameters, or understanding route module exports (loader, action, component, meta). Covers flat-routes conventions, nested layouts, and the _app prefix.
Page 1431 of 1621 · 81016 results