Research topics using web search and content fetching to find accurate, current information. Use when you need modern information, official documentation, best practices, technical solutions, or comparisons beyond your training data. Use when this capability is needed.
Create standalone .NET binding library projects for third-party native iOS/macOS xcframeworks. Use when creating a new C# binding project for a vendor xcframework (e.g., Facebook SDK, Firebase, custom frameworks), scaffolding the .csproj and binding files, extracting API definitions from Objective-C headers, or setting up NuGet packaging for native library bindings. Covers project structure, header analysis, ApiDefinition.cs generation, and build/packaging. Use when this capability is needed.
Analyze Objective-C and Swift framework headers to extract the complete API surface for .NET binding generation. Use when you need to read xcframework headers, identify classes/protocols/enums/constants/blocks/delegates, determine inter-framework dependencies, map ObjC/Swift declarations to C# binding patterns, and produce a structured API inventory before writing ApiDefinition.cs and StructsAndEnums.cs. Use when this capability is needed.
Implement proper Next.js 16 Image component usage with configuration for remote domains, responsive images, and breaking changes from previous versions Use when this capability is needed.
Next.js PR workflow with quality checks (lint/build/test), semantic versioning labels (major/minor/patch), coverage badges, and JIRA integration via pr-creation-workflow framework Use when this capability is needed.
Manage network hosts and devices across all UniFi sites. Monitor host status, device configuration, and infrastructure health for comprehensive inventory management. Use when this capability is needed.
Analyzes pseudocode, algorithms, or code snippets to extract and document functional requirements and business specifications. Produces functional specifications, business logic documentation, data requirements, and workflow specifications focused exclusively on WHAT the system does, not HOW it's implemented. Use when analyzing pseudocode for business logic, extracting functional requirements from algorithms, documenting business behavior from code, reverse engineering functional specifications, or when users mention "pseudocode to spec", "extract requirements", "business logic documentation", "functional specification from code", or "requirements from pseudocode".
Routes to 14 structured thinking methodologies (lenses) for systematic analysis. Use this skill when you need to think through problems, apply thinking lenses, reason through decisions, or perform systematic analysis. Auto-selects appropriate lens based on context - 5 Whys for failures, Pre-Mortem for risks, First Principles for assumptions, Systems Thinking for architecture, Four Causes for understanding, Cargo Cult Detection for validation, Golden Mean for calibration. Use when this capability is needed.
Interactive Knowledge Base search with natural language queries. Use this skill when you need to search KB, find patterns, search knowledge base, look for solutions, find bug fixes, or query institutional knowledge. Searches patterns and bug fixes with relevance ranking, quality scoring, and fuzzy matching for typo tolerance. Helps users find solutions quickly without manual browsing. Use when this capability is needed.
This skill should be used when the user asks to "perform cloud penetration testing", "assess Azure or AWS or GCP security", "enumerate cloud resources", "exploit cloud misconfigurations", "test O365 security", "extract secrets from cloud environments", or "audit cloud infrastructure". It provides comprehensive techniques for security assessment across major cloud platforms.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking. Use when this capability is needed.
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats. Use when this capability is needed.
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support Use when this capability is needed.
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers. Use when this capability is needed.
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation. Use when this capability is needed.
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, and entity detection. Same endpoint as plain STT, different params. Covers REST via `client.listen.v1.media.transcribeUrl` / `transcribeFile` and the WebSocket-supported subset on `client.listen.v1.createConnection()` / `connect()`. Use `deepgram-js-speech-to-text` for plain transcription and `deepgram-js-text-intelligence` for analytics on already-transcribed text. Triggers include "audio intelligence", "summarize audio", "diarize", "sentiment from audio", "redact PII", and "detect language audio".
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation. Use when this capability is needed.
FREE AI image generation service for creating attractive people portraits. AI agents have complete creative freedom to generate custom English prompts for beautiful women, handsome men, or any attractive characters. Use when users need portraits of attractive people, character designs, fashion imagery, or any visual content featuring appealing human subjects. Use when this capability is needed.
Browser-automated file download with enhanced features. Auto-detects platform (Windows/macOS/Linux, 64/32-bit, ARM/Intel), handles multi-step navigation (homepage to platform-specific pages), captures auto-downloads triggered on page load, and falls back to button clicking when needed. Ideal for complex download flows where curl/wget fail due to client-side rendering, automatic downloads, or multi-page navigation. Features page scrolling for lazy content, extended wait times, and Golang support. Use when this capability is needed.
Turn your code scan findings into search queries — research existing implementations before consulting an attorney. NOT legal advice. Use when this capability is needed.
Enhanced backup and restore for openclaw configuration, skills, commands, and settings. Sync across devices, version control with git, automate backups, and migrate to new machines with advanced compression. Use when this capability is needed.
Generate clean table images from data. Perfect for Discord/Telegram where ASCII tables look broken. Supports dark/light mode, custom styling, and auto-sizing. No Puppeteer required. Companion to chart-image skill. Use when this capability is needed.
AI-powered blockchain monitoring agent with real-time monitoring of Uniswap V2, V3, and V4 most known pools. Track swaps, monitor specific liquidity pools by address, and receive intelligent insights Use when this capability is needed.
Use when investigating bugs, crashes, or unexpected behavior in a Flutter app. Especially when issues involve Bloc state not emitting, null safety errors, BuildContext after async, GetIt DI failures, method channel mismatches, widget rebuilds, or memory leaks.
Generates production-ready C# script templates (MonoBehaviour, ScriptableObject, Editor, tests). Use when creating new scripts or setting up project structure.
Use when Gemini bot completes PR review with priority labels (🔴🟡🟢⚪) - MANDATORY loop until meaningfulUnprocessedCount=0, then automatically processes new feedback by priority with 3-minute polling, state tracking for resumable processing, and @superpowers:executing-plans integration
Analyze the local DSolver Simulator service in this repo with a reporting-first Rust CLI. Use when you want to start or reuse the local broadcaster plus simulator stack, wait for /status health and native readiness, exercise representative /simulate and /encode flows, run latency and light stress probes, save standardized JSON/markdown reports, compare against previous local runs, and investigate anomalies without relying on strict pass/fail business assertions. Use when this capability is needed.
Search, tail, and query Tycho simulation production logs in AWS CloudWatch using AWS CLI and bundled scripts. Use for /ecs/tycho-simulator investigations such as block updates, resyncs, readiness, timeouts, or general app errors. Use when this capability is needed.
Audit the current repository for agent workflow efficiency. Use when the user wants Codex to try setup, build, test, lint, run, or other obvious project commands and report where the agent instructions, AGENTS.md, README, or scripts are wasting context tokens, causing avoidable command exploration, or leaving important steps implicit. This skill optimizes the workflow and instructions for agents; it should not fix product code unless explicitly asked. Use when this capability is needed.
Hyper-pedantic Django code review skill emulating Monty's correctness-first, multi-tenant-safe, harness-aware review style. Use when this capability is needed.
Beautify screenshots using ImageMagick - add rounded corners, drop shadows, gradient backgrounds, padding. Use when preparing screenshots for blog posts, documentation, or presentations. Transforms raw Playwright/browser screenshots into polished images. Use when this capability is needed.
Loop 3 of the Three-Loop Integrated Development System. CI/CD automation with intelligent failure recovery, root cause analysis, and comprehensive quality validation. Receives implementation from Loop 2, feeds failure patterns back to Loop 1. Achieves 100% test success through automated repair and theater validation. v2.0.0 with explicit agent SOPs. Use when this capability is needed.
AI agent validates work through evidence-based verification with comprehensive checklists, automated validation, and proof-of-work documentation. Use when completing tasks, preparing for review, or ensuring quality. Use when this capability is needed.
Full video production workflow for Remotion projects. Teaches how to orchestrate MCP tools (TTS, music, SFX, stock footage, video analysis) into complete Remotion compositions. Use this skill whenever producing a video that needs audio, voiceovers, music, stock footage, or analyzing existing video files. Use when this capability is needed.
Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts. Use when user asks 'where are we in development', 'what stage are we in', 'full project audit'. Use when this capability is needed.
Naming conventions for events, states, and handlers in flutter_bloc with freezed. Use when adding or renaming BLoC events, state variants, or event handlers. Use when this capability is needed.
Checks PHP configuration in Docker containers. Verifies php.ini settings, OPcache, PHP-FPM pool, and extension configuration for production. Use when this capability is needed.
Generates PSR-15 HTTP Middleware implementation for PHP 8.4. Creates MiddlewareInterface and RequestHandlerInterface with pipeline composition. Includes unit tests.
Documentation knowledge base. Provides documentation types, audiences, best practices, and antipatterns for technical documentation creation. Use when this capability is needed.
Output format templates for all 5 explanation modes — quick (compact), deep (full analysis with diagrams), onboarding (project guide), business (non-technical), qa (interactive Q&A). Use when this capability is needed.
Maps domain model components — Entities, Value Objects, Aggregates, Services, Events, Repositories. Builds Ubiquitous Language glossary connecting code names to business terminology. Use when this capability is needed.
Microservices Architecture knowledge base. Provides service decomposition, communication patterns, API gateway, service discovery, and data management guidelines for architecture audits and generation. Use when this capability is needed.
Optimizes OPcache configuration for PHP Docker containers. Configures memory, file limits, JIT, and validation for production and development. Use when this capability is needed.
Optimizes PHP-FPM configuration in Docker containers. Tunes process manager, request handling, and resource allocation for production workloads. Use when this capability is needed.
Optimizes Docker container startup time for PHP applications. Reduces initialization overhead through preloading, caching, and entrypoint optimization. Use when this capability is needed.
Scans directory tree to identify architectural layers (Domain, Application, Infrastructure, Presentation), detect framework (Symfony, Laravel, custom), count files per layer, and build project structure map. Use when this capability is needed.
Traces full request lifecycle from Router through Middleware, Controller, UseCase, Repository to Response. Documents HTTP methods, routes, middleware stack, response codes, and error handling paths. Use when this capability is needed.
Architects token systems with primitive, semantic, and component layers. Use when structuring tokens from scratch, adding multi-theme support, setting up token aliasing, or organizing token hierarchies. Use when this capability is needed.
Implement a feature or fix by executing an issue card plus ExecPlan in this repo. Use when Codex is asked to implement work that must align with AGENTS.md and PLANS.md, keep the ExecPlan updated, and treat any referenced repo docs as authoritative. Requires ISSUE_PATH and EXECPLAN_PATH. Use when this capability is needed.
WordPress performance code review and optimization analysis. Use when reviewing WordPress PHP code for performance issues, auditing themes/plugins for scalability, optimizing WP_Query, analyzing caching strategies, checking code before launch, or detecting anti-patterns, or when user mentions "performance review", "optimization audit", "slow WordPress", "slow queries", "high-traffic", "scale WordPress", "code review", "timeout", "500 error", "out of memory", or "site won't load". Detects anti-patterns in database queries, hooks, object caching, AJAX, and template loading. Use when this capability is needed.
Use when coordinating PR review work as orchestrator. Defines delegation rules, verification, and completion criteria. Trigger with /start-pr-review [PR_NUMBER].
Software release management and coordination. Use when creating releases, bumping versions, or rolling back deployments. Trigger with release tasks or /eia-create-release. Use when this capability is needed.
Create and receive handoff documents for context transfer. Use when transferring work, resuming sessions, or filing bug reports. Trigger with /epa-handoff. Use when this capability is needed.
Formats all Telegram bot replies to be short, scannable, and properly styled with MarkdownV2. Use when replying to Telegram messages via the Telegram MCP plugin — ensures bold, emojis, bullet points, and correct special character escaping. Use when this capability is needed.
Convert webinar recordings into blog posts, social snippets, email series. Extract key quotes, statistics, and soundbites. Use when this capability is needed.
Summarize a video through the VSS Pipeline Manager — start a summary pipeline with POST /summary (full required body), poll GET /summary/{stateId} until complete, then return the summary via GET /summary/{stateId}/raw. Use when the user says "summarize this video", "create a summary", "what happens in this video" (on an ingested video), or wants to run/inspect the summarization pipeline. Requires a summary-capable deployment (--summary, --dual, or --unified). Use when this capability is needed.
Guides the agent to write unit tests that strictly conform to the project's existing testing structure, patterns, and style by learning from similar tests before writing anything new. Use when this capability is needed.
Analyze failed Prow CI tests by inspecting test code, downloading artifacts, and optionally integrating must-gather cluster diagnostics for root cause analysis Use when this capability is needed.
Systematic approach to refactoring code for improved maintainability, performance, and clarity while preserving functionality Use when this capability is needed.
Transforms raw data into compelling visual narratives using Python or R, focusing on clarity, insight, and aesthetic presentation. Use when this capability is needed.
Guides the creation of a "Minimal Root" home directory using the XDG Base Directory specification and a Bare Git Repository. Manages config separation, secrets, and cross-platform syncing. Use when this capability is needed.
Creates algorithmic music composition systems using procedural generation, Markov chains, L-systems, and neural approaches for ambient, adaptive, and experimental music.
operationalizes GitHub Projects (V2) as a dynamic roadmap system. Defines field taxonomy, "Triage" protocols, and synchronizes Strategy (Roadmap) with Execution (Issues). Use when this capability is needed.
Architects cross-platform and native mobile applications, providing guidance on state management, navigation, and platform-specific best practices for React Native, Flutter, iOS, and Android. Use when this capability is needed.
Designs systems for encoding, scoring, and generating choreographic movement using Laban notation, computational geometry, and procedural animation principles. Use when this capability is needed.
Distill artist/theorist narrative principles into formal, implementable algorithmic frameworks. Use when asked to extract, formalize, or systematize narrative techniques from any storytelling source—filmmakers, writers, theorists, game designers, showrunners. Triggers on requests involving narrative principle extraction, story structure analysis, craft methodology formalization, or creating implementable storytelling protocols. Use when this capability is needed.
Create a dlt REST API pipeline. Use for the rest_api core source, or any generic REST/HTTP API source. Not for sql_database or filesystem sources. Use when this capability is needed.
Set up or modify the OPA Permissions Wrapper Module in a Backstage app. Use this skill whenever the user wants to integrate OPA with the Backstage Permission Framework, add or change permission rules, write a Rego policy for Backstage permissions, wire up the opa-wrapper module, or troubleshoot why a permission is being allowed or denied. Trigger on phrases like "add OPA permissions", "set up permission policy", "Rego policy for Backstage", "permission wrapper", "ALLOW/DENY/CONDITIONAL", or any time the user is working with `@parsifal-m/plugin-permission-backend-module-opa-wrapper`. Use when this capability is needed.
Identifies API latency hotspots and bottlenecks with profiling tools, slow endpoint detection, suspected causes, and fix roadmap. Use for "latency profiling", "performance bottlenecks", "slow APIs", or "backend performance". Use when this capability is needed.
Converts documents into clean, chunked datasets suitable for embeddings and vector search. Produces chunked JSONL files with metadata, deduplication logic, and quality checks. Use when preparing "training data", "vector datasets", "document processing", or "embedding data".
Creates comprehensive GitHub Actions CI/CD workflows for linting, testing, building, and deploying. Includes caching strategies, matrix builds, artifact handling, and failure diagnostics. Use for "GitHub Actions", "CI pipeline", "workflow automation", or "continuous integration".
Enforces consistent structured logging with request correlation IDs, standardized log schema, middleware integration, and best practices. Use for "structured logging", "log standardization", "request tracing", or "log correlation". Use when this capability is needed.
Diagnose and resolve Microsoft Fabric network performance issues including connectivity failures, latency, private endpoints, managed VNets, outbound access protection, gateway diagnostics, OneLake endpoint routing, service tag configuration, firewall allowlisting, DNS resolution, and Spark session startup delays. Use when remediate Fabric networking, slow Spark jobs, connection timeouts, private link errors, managed private endpoint approval, or capacity throttling. Use when this capability is needed.
Comprehensive reference for all blocks available in the Permit Junction website. Use this skill to understand block structure, variants, content models, and authoring guidelines for each block. Use when this capability is needed.