All Skills

Enforces disciplined task tracking across context boundaries. Use when starting any coding task, receiving a new user request mid-work, planning multi-step work, discovering sub-tasks or issues, before context compaction, switching between tasks, or resuming a previous session. Skip for purely informational questions with no code changes.

Assess and enhance software projects for enterprise-grade security, quality, and automation. This skill should be used when evaluating projects for production readiness, implementing supply chain security (SLSA, signing, SBOMs), hardening CI/CD pipelines, establishing quality gates, reviewing code or PRs, writing documentation (ADRs, changelogs, migration guides), or pursuing OpenSSF Best Practices Badge. Aligned with OpenSSF Scorecard, Best Practices Badge (all levels), SLSA, and S2C2F. By Netresearch.

Build system optimization covering compilation, caching, incremental builds, and developer tooling. Use when improving build times, configuring CI pipelines, or designing developer tools.

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

Validate data integrity during and after migration with comprehensive verification checks

Pre-send email quality review and scoring across 5 dimensions (subject line, copy quality, technical/HTML, deliverability, compliance). Analyzes subject lines, body copy, HTML structure, spam triggers, and CAN-SPAM compliance. Scores 0-100 with detailed recommendations for improvement. Use when user wants to review an email before sending, check email quality, or validate marketing email best practices.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

Reverse engineer and extract capabilities from any source — repos, local configs, binaries, articles, settings — into your agent workflow

Execute tasks using hive mind orchestration with parallel agents, automatic code review, and documentation updates. Use for feature execution, epic completion, or complex multi-task work.

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

Generate web UI/UX icon assets (favicon.ico, apple-touch-icon, PWA icons incl. maskable) and optionally Unreal Engine packaging icons (Windows .ico, macOS .iconset/.icns, Linux .png) from a single source SVG/PNG; use when you need correct multi-size icon files, safe-area guidance, manifests/head tags, or automation.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

List git-native-issues with optional filtering and shorthands

Review Clojure and ClojureScript code changes for compliance with Metabase coding standards, style violations, and code quality issues. Use when reviewing pull requests or diffs containing Clojure/ClojureScript code.

Container-based development for isolated, reproducible environments. Use when running npm commands, installing packages, executing code, or managing project dependencies. Trigger phrases include "npm install", "run the build", "start the server", "install package", or any code execution request.

Automate payer review of prior authorization (PA) requests. This skill should be used when users say \"Review this PA request\", \"Process prior authorization for [procedure]\", \"Assess medical necessity\", \"Generate PA decision\", or when processing clinical documentation for coverage policy validation and authorization decisions.

Optimize oversized CLAUDE.md files using progressive disclosure. Analyzes content tiers, detects encryption constraints, creates sub-documents, and rewrites the main file with a Sub-Documentation Table. Triggers: optimize CLAUDE.md, reduce CLAUDE.md size, CLAUDE.md too long, apply progressive disclosure to CLAUDE.md

Guide for setting up LaunchDarkly projects in your codebase. Helps you assess your stack, choose the right approach, and integrate project management that makes sense for your architecture.

Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an existing AGENTS.md for clarity, commands, boundaries, and repo-specific context. For Claude Code, also create CLAUDE.md as a symlink to AGENTS.md.

End-to-end planning and execution orchestrator. Chains SPARC or wave-planner (Stage 1), plan-review, linear, and hive-workers-skill into a single workflow. Automatically routes infra changes through SPARC research instead of wave-planner. Use when starting a new initiative, executing a set of Linear issues, or running plan-to-deployment.

Web UI/UX specialist guidance for designing, reviewing, and polishing web product UI (layout, usability, microcopy, accessibility, responsive behavior, forms, navigation). Use when asked to improve UI/UX, audit a page, design a screen, create a component spec, or generate HTML head/manifest/icon guidance for a web app; optionally applicable to Unreal UI (UMG) for UX heuristics.