AI & ML

tanstack Skill

Full type inference philosophy (never cast, never annotate inferred values), Register module declaration, from narrowing on hooks and Link, strict:false for shared components, getRouteApi for code-split typed access, addChildren with object syntax for TS perf, LinkProps and ValidateLinkOptions type utilities, as const satisfies pattern.

nvidia Skill

Implement a fix for a reviewed security issue. Takes a directly requested issue number or scans for issues labeled `topic:security` and `agent:implementation-requested`. Reads the security review from the issue comments and implements the remediation plan. Trigger keywords - fix security issue, remediate security, implement security fix, patch vulnerability.

nvidia Skill

Launch and supervise OpenShell gator agents. Use when starting gator on issues or PRs, checking gator sandboxes, building the gator sandbox image, restarting stuck gators, inspecting gator logs, or experimenting with gator harness/model overrides. Trigger keywords - launch gator, start gator, run gator, gator sandbox, supervised gator, gator logs, restart gator.

ericgandrade Bundle

Use this skill when the user explicitly asks to create, write, improve, or optimize a prompt for use with an AI. Trigger on phrases like "write me a prompt", "improve this prompt", "create a system prompt", "how do I ask ChatGPT/Claude to...", or "quero um prompt para...". Do NOT trigger for direct task requests where the user wants the output, not the prompt.

ericgandrade Bundle

This skill should be used when the user needs to transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration.

adaptyvbio Skill

ESM protein language models for embeddings, sequence scoring, structure prediction, and binder design. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) or mutation-effect scores, (2) Getting protein embeddings for clustering or filtering, (3) Predicting complex structures with ESMFold2, (4) Designing binders by inverting ESMFold2, (5) Filtering designs by sequence plausibility. For diffusion-based structure prediction, use boltz or chai. For QC thresholds, use protein-qc. For gradient-based multi-objective design, use mosaic.

adaptyvbio Bundle

Structure prediction using Chai-1, a foundation model for molecular structure. Use this skill when: (1) Predicting protein-protein complex structures, (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using the Chai API for high-throughput prediction, (5) Need an alternative to AlphaFold2. For QC thresholds, use protein-qc. For AlphaFold2 prediction, use alphafold. For ESM-based analysis, use esm.

adaptyvbio Bundle

All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the start, (2) Designing around small molecules or ligands, (3) Want all-atom diffusion (not just backbone), (4) Require precise binding geometries, (5) Using YAML-based configuration. For backbone-only generation, use rfdiffusion. For sequence-only design, use proteinmpnn. For structure validation, use boltz.

adaptyvbio Skill

Structure prediction with Protenix, an open AlphaFold3 reproduction. Use this skill when: (1) Predicting complex structures with an AF3-class model, (2) Wanting an open alternative to AF3 alongside Boltz and Chai, (3) Validating designed binder-target complexes. For QC thresholds, use protein-qc. For ipSAE ranking, use ipsae.

ydnikolaev Bundle

Expert on Model Context Protocol (MCP) servers. Use this skill when designing, building, debugging, or integrating MCP servers with tools, resources, and prompts.

ydnikolaev Bundle

Analyzes new feature requests for EXISTING projects. Reads config/mcp context, performs Gap Analysis, and creates a Feature Brief.

ydnikolaev Bundle

Your project awareness buddy. Knows current state, reads docs, analyzes code, answers "where are we?" questions. Activate with "bro" or "project-bro".

ericgandrade Bundle

This skill should be used when the user needs to solve a complex task and wants a detailed execution plan using the best available resources. Analyzes user requirements, discovers available plugins/agents/skills/MCPs, performs intelligent matching with confidence scoring, and creates strategic execution plans with alternatives. Works across all AI CLI platforms.

rainmanjam Skill

AI features you ship to users: structured output, tool schemas, prompt injection, evals. Use when "the model returns bad JSON", "it hallucinates", "stop it calling the wrong tool", "add evals", or an LLM feature can trigger refunds, emails or writes. Covers schema-constrained output, idempotent tool calls, confirmation gates. For agents editing your repo use agent-guardrails.

ydnikolaev Bundle

Defines the philosophy and process for creating high-quality Antigravity skills. Use this skill when asked to create a new skill or standardize an existing one.

ydnikolaev Bundle

Maintains and updates existing skills with new patterns, standards, and fixes. Mass rollout of changes across multiple skills.

ydnikolaev Bundle

Creative partner for ideating and designing Antigravity skills. Conducts interviews, proposes ideas, defines boundaries, and writes specs for skill-creator. Does NOT create skills directly.

ydnikolaev Skill

Expert on the antigravity-factory project. Knows the entire codebase, skill creation workflow, Makefile commands, and project architecture. Activate this skill when working within the factory repository.

ydnikolaev Bundle

A minimal example skill demonstrating "The Antigravity Way". Use this as a reference when creating your own skills.

adaptyvbio Bundle

Generate protein backbones using RFdiffusion, a diffusion-based generative model for de novo protein structure generation. Use this skill when: (1) Designing binder scaffolds for a target protein, (2) Generating novel protein backbones from scratch, (3) Scaffolding functional motifs into new proteins, (4) Specifying hotspot residues for interface design, (5) Creating symmetric oligomers. For sequence design after backbone generation, use proteinmpnn. For structure validation, use alphafold or chai. For QC thresholds, use protein-qc.

openaec-foundation-three-js-claude-skill-package Bundle

Use when adding sound to a Three.js scene: background music, 3D spatial audio, or audio visualization. Prevents the common mistake of ignoring browser autoplay policy, not attaching AudioListener to camera, or wrong distance model. Covers AudioListener, Audio, PositionalAudio, AudioAnalyser. Keywords: audio, sound, AudioListener, PositionalAudio, 3D audio, spatial audio, music, AudioAnalyser, Web Audio API, play sound, add music, sound in 3D scene.

rainmanjam Skill

Pre-commit hooks, CI gates, lint rules, database constraints and branch protection. Use when a rule needs enforcing rather than documenting: "set up enforcement", "unformatted or untyped code must not get merged", "gate this in CI", "we agreed to X and people still do not", "stop secrets getting committed". Covers baselining and ratcheting so existing violations do not block anyone. For constraining an AI agent use agent-guardrails.

rainmanjam Skill

Stop an AI agent damaging your repo: PreToolUse hooks, permission deny rules, protected paths, verification gates. Use when "claude keeps force pushing", "CLAUDE.md says X but it still does Y", "stop the agent touching prod or .env", or making a repo safe for unattended agent work. For AI features you ship to users use llm.

platxa Bundle

Autonomous skill creator for Claude Code CLI. Use when the user asks to "create a skill", "generate a skill", or "build a new slash command". Uses multi-phase orchestrated workflow with Task tool subagents to research domains, design architecture, generate content, validate quality, and iteratively improve via eval infrastructure. Creates production-ready skills following the Agent Skills open standard and Claude Code extensions.

emz1998 Bundle

Use PROACTIVELY this agent when you need to design and create optimal Claude Code subagents, update existing agents with new capabilities, revise agent configurations, analyze project requirements to identify specialized roles, or craft precise agent configurations with appropriate tool permissions and model tiers. When the user specify "Create or Update subagent [name]", this skill must be triggered.

openaec-foundation-three-js-claude-skill-package Bundle

Use when loading and viewing IFC/BIM models in a Three.js scene. Prevents the common mistake of using deprecated web-ifc-three, ignoring AGPL-3.0 license implications, or loading large IFC files without streaming. Covers web-ifc (MIT), @thatopen/components (AGPL-3.0), IFC loading, spatial tree, property extraction. Keywords: IFC, BIM, web-ifc, IFC viewer, @thatopen/components, building model, architecture, IFC loading, spatial tree, BIM viewer, show IFC in browser, load building, web BIM viewer.

openaec-foundation-three-js-claude-skill-package Bundle

Use when loading 3D models (GLTF, FBX, OBJ), textures, or HDR environment maps in Three.js. Prevents the common mistake of not setting up DRACOLoader, wrong WASM path, or missing error handling. Covers GLTFLoader, DRACOLoader, KTX2Loader, TextureLoader, RGBELoader, FBXLoader, OBJLoader, LoadingManager. Keywords: GLTFLoader, GLTF, GLB, load model, DRACOLoader, texture, FBXLoader, OBJLoader, RGBELoader, HDR, LoadingManager, progress, export, GLTFExporter, save model, download 3D, import 3D file.

openaec-foundation-three-js-claude-skill-package Bundle

Use when a Three.js scene renders incorrectly: black screen, invisible objects, wrong colors, z-fighting, or broken shadows. Prevents the common mistake of wrong color space, missing material.side, or forgetting updateProjectionMatrix. Covers all common rendering errors with diagnosis steps and fix patterns. Keywords: black screen, invisible, wrong color, z-fighting, shadow artifact, rendering error, debug, nothing visible, dark, broken, nothing shows, model not appearing, screen is blank.

cadrianmae Skill

This skill should be used when the user asks to "initialize tracking", "enable/disable tracking", "toggle auto-tracking", "configure tracking verbosity", "export bibliography", "export methodology", "generate BibTeX", "create citation timeline", or anything involving the track plugin for reference and prompt tracking. Single unified interactive entry point.

emz1998 Bundle

Creates and maintains Agent Skills with effective triggers and progressive disclosure. Use when user requests to create a skill, generate a SKILL.md, build custom capabilities, or mentions "create skill", "new skill", or "skill configuration".

emz1998 Bundle

Crafts, refines, and optimizes prompts for Claude 4.x models using best practices for instruction clarity, tool usage, and long-horizon reasoning. Use when creating user/system prompts, refining existing prompts, optimizing model interactions, or when user mentions prompt engineering, prompt optimization, prompt refinement, or Claude 4.x prompting.

spences10 Bundle

Setup guide for essential MCP servers. Use when configuring MCP servers or when user asks about search, SQLite, or MCP management.

spences10 Skill

Secret-safe Claude Code sessions via nopeek CLI. Use when user asks about secrets, .env loading, credential safety, or keeping API keys out of conversation context.

cloud-officer Bundle

Exhaustive multi-phase code audit using parallel agents (security, dependencies, code quality, infrastructure, tests, and more). Use when the user wants a deep or thorough code review, a comprehensive audit, a security-and-quality sweep of a repo or subsystem, or a multi-agent review that goes beyond the current diff. Optionally scoped to a path or subsystem.

spences10 Bundle

Analyze session history for learnings and persist to skills. Solves "memory zero" - correct once, never again.

spences10 Bundle

Design and create Claude Skills using progressive disclosure principles. Use when building new skills, planning skill architecture, or writing skill content.