**The AI should act as an intelligent Project Manager**, analyzing each request and automatically selecting the best specialist(s) for the job.

Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against observational data, or conducting systematic hypothesis exploration for research discovery in domains like deception detection, AI content detection, mental health analysis, or other empirical research tasks.

Create detailed implementation plans through interactive research and iteration

21 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.

Control the user own Chrome browser via Playwriter extension with Playwright code snippets in a stateful local js sandbox via playwriter cli. Automate web interactions, take screenshots, inspect accessibility trees, debug & profile web applications. Run `playwriter skill` command to read the complete up to date skill

project-planning

Capture or refine non-functional requirements such as accessibility, reliability, scalability, maintainability, performance, and compliance. Use when a feature or architecture change needs explicit quality attributes and trade-offs.

Pull latest origin/main into the current local branch and resolve merge conflicts (aka update-branch). Use when Codex needs to sync a feature branch with origin, perform a merge-based update (not rebase), and guide conflict resolution.

Write or update duplojs-utils JSDoc documentation files under jsDoc/{namespace}/{function}/, including index.md structure, @example includes, and example.ts usage patterns (classic, curried, and predicate overloads).

Audit GDD-specified content counts against implemented content. Identifies what's planned vs built.

Preserve and extend the current minimal visual style in this repo. Use when editing the home page, foraging workbench, map panel, or related frontend surfaces and the goal is to keep the interface minimal, editorial, workbench-first, and token-driven instead of introducing a new visual direction.

Design phase-gated evals, parseability checks, citation assertions, and judge-path regression coverage for Care Transitions Command.

Engineer robust Python document-processing systems for this repository. Use when tasks involve Docling-first analysis, OCR/table fallback design, editable DOCX generation, RTL/LTR mixed text handling, project scaffolding, CI/tooling setup, or implementation planning and execution that must prioritize correctness, maintainability, and practical delivery.

>-

Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or explicit GPT-5.4 upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.

Use when entering this repository and needing the shared workspace entrypoint before choosing a company or track.

Bootstrap a fresh Laravel app from this starter kit repo into ~/projects using the bundled deterministic shell script. Use when Codex should create a new project with fresh git history, keep the first commit identical to the starter kit snapshot, seed a project README from the user's app brief, start the app locally through the shared proxy flow, and avoid extra app-specific edits during bootstrap.

Expert database administrator specializing in modern cloud databases, automation, and reliability engineering.

Safe editing guidance for the hgame GameMaker Studio 2 JRPG project. Use when Codex or an agent needs to inspect, modify, refactor narrowly, debug, or extend this repository's GML code, GMS2 objects, rooms, scripts, save data, inventory, equipment, character, skill, menu, NPC, movement, audio, or room-state systems.

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 Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Audit and improve Greenhouse UI microinteractions across motion, feedback, loading, empty, validation, and accessibility using the repo's existing primitives and platform rules.

>

qa-only

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Use when Codex needs to discover, specify, document, implement, reconcile, verify, post-check, or choose the next Appaloft business behavior/business operation from ADRs, global contracts, local command/query/event/workflow/error specs, implementation plans, operation catalog entries, read models, Web/API/CLI entrypoints, public docs anchors, or spec-driven test matrices. Supports artifact-guided behavior dossiers, incremental or complete readiness workflows, Discover Round, Spec Round, Docs Round, Test-First Round, Code Round, Sync Round, Next Behavior Selection, and Post-Implementation Sync.

Scan a repo for mixed ADRs, PRDs, SPECs, and DOCs and bootstrap or merge the full .planning/ setup from them. Classifies each doc in parallel, synthesizes a consolidated context with a conflicts report, and routes to new-project or merge-milestone depending on whether .planning/ already exists.

Use when the user wants to register new work from a bug report, idea, or task description and an existing GitHub Issue number is not already known.

Use inside spark-workflow when the user wants discussion, requirement exploration, idea comparison, or codebase investigation without implementation.

Execute comprehensive web application security testing using Burp Suite's integrated toolset, including HTTP traffic interception and modification, request analysis and replay, automated vulnerability

Fast, modern JavaScript runtime and toolkit. IMPORTANT: This is Bun, NOT Node.js. Use Bun-specific APIs below. Do NOT use Node.js APIs like require(), process, fs (use Bun.file() instead).

Build premium React/Next.js interfaces calibrated to a specific brand identity, informed by competitive landscape research, and engineered to override default LLM design biases.

vvm

**Version**: 1.0.0

Launch and manage CodeScaleBench benchmark runs with paired-run guardrails, quick reruns, and execution orchestration.

Use when implementing any feature or bugfix where correctness matters - before writing implementation code.

Load this skill for any work in `projectbluefin/bluefin-mcp` — Go backend, tools, tests, testdata, CI.

>

5S workplace organization audit skill with scoring, photo documentation, and sustainability tracking.

Manage and inspect IBM i journals, journal receivers, journaled objects, journal entries, remote journals, and audit journal data marts. Use when user asks about: (1) listing journals or journal receivers, (2) which objects are journaled, (3) reading journal entries, (4) remote journal configuration and lag, (5) journal receiver sizes or chains, (6) SMAPP access path protection, (7) audit journal data marts, (8) journal storage consumption, or (9) replacing WRKJRN, DSPJRN, WRKJRNA command output.

Use Safari directly on macOS when work must happen in the user's real Safari session instead of a separate automation browser. Best for reading the current tab, inspecting the live session layout, operating Safari menu bar or native toolbar controls, reading page text and structure, running page JavaScript, waiting for page conditions, exporting page artifacts, and performing lightweight DOM interactions in the active Safari tab. If Safari JavaScript from Apple Events is disabled, guide the user to enable it or fall back to desktop-control for visual interaction.

>

Systematic problem-solving techniques — inversion, collision-zone, scale-game, simplification cascades.

Query multiple threat intelligence services for IOC enrichment including IP reputation, domain analysis, URL scanning, hash lookups, and malware detection. Use when investigating observables (IP, domain, URL, hash) to gather context from external sources like VirusTotal, GreyNoise, Shodan, AbuseIPDB, AlienVault OTX, and more. Supports both API-key services and free services.

Simulates how 12 diverse personas react to an announcement over 3 interactive rounds — each persona reads others' reactions and shifts opinions, surfacing emergent camps and objections no single prompt catches. Spawns 12 parallel agents with web search access. Use before publishing pricing changes, product launches, layoffs, policy shifts, or any high-stakes message. Triggers on '/simulate', 'how will people react', 'test this announcement', 'honest feedback on this', 'simulate reaction'.

Convert PowerPoint (.pptx) presentations to HTML using MinerU. Transforms slides into web-ready HTML format with content and structure preserved. Features: PPTX to HTML conversion. Preserves slide content, text, and basic structure. Token-based extraction. Works with local files and URLs. Use when you need to: convert PowerPoint to HTML, turn a .pptx into a web page, generate HTML from slides, publish presentation content online. Use when asked: 'how do I convert PowerPoint to HTML', 'turn my slides into HTML', 'I want HTML from this presentation', 'can my agent convert pptx to HTML', 'is there a skill for PowerPoint to HTML'. Built on MinerU by OpenDataLab (Shanghai AI Lab), an open-source document intelligence engine. Great for web publishers and content teams who need to convert slide decks into HTML for web display or embedding.

Expert-level guide to spatial expert 31. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.

Expert-level guide to climate expert 83. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.

Generate, install, and manage Git hooks with pre-built templates. Includes hooks for linting staged files, enforcing conventional commits, blocking debug statements, preventing large file commits, auto-formatting code, requiring ticket references, protecting branches, running tests before push, and auto-installing dependencies after merge. Use when setting up git hooks, enforcing commit conventions, or automating pre-commit/pre-push checks.

Builds dapps on Monad blockchain. Use when deploying contracts, setting up frontends with viem/wagmi, or verifying contracts on Monad testnet or mainnet.