Core Workers fundamentals including handlers, configuration, and Service Bindings. Load when creating new Workers, configuring wrangler.jsonc, implementing fetch/scheduled/queue handlers, using Service Bindings for RPC, generating types with wrangler types, or building microservices.

Build fully-integrated 3-statement models (IS, BS, CF) in Excel with working capital schedules, D&A roll-forwards, debt schedule, and the plugs that make cash and retained earnings tie. Pairs with excel-author.

Expert in Tauri auto-update implementation with focus on signature verification, rollback mechanisms, staged rollouts, and secure update distribution

Perform initial analysis of a codebase - detect tech stack, directory structure, and completeness. Gear 1 of the 6-gear reverse engineering pipeline. Automatically detects programming languages, frameworks, architecture patterns, and generates analysis-report.md.

Run a structured discovery session to build an Allium specification through conversation. Use when the user wants to create a new spec from scratch, elicit or gather requirements, capture domain behaviour, specify a feature or system, define what a system should do, or is describing functionality and needs help shaping it into a specification.

Orchestrate event description audits by delegating chunk work to the event-descriptions-worker subagent. Resolve a project name to projectId via get_context when needed, then spawn worker subagents over cursors for a bounded run window and write outputs into run-scoped directories. Use when auditing missing event descriptions at scale without doing per-event analysis directly in this skill.

Use when building Go applications requiring concurrent programming, microservices architecture, or high-performance systems. Invoke for goroutines, channels, Go generics, gRPC integration.

Iterative Swarm Loop — Submit a holistic project description, get a company team that keeps sprinting until everything is built. Combines autonomous looping with Hydra-scale parallel swarms. Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.

Default operating skill for llmdoc-enabled projects. Use when a project has llmdoc/, when initializing llmdoc, when updating project knowledge, or when Codex CLI hooks should reinforce the workflow.

Working with the OxCaml extensions to OCaml. Use when the oxcaml compiler is available and you need high-performance, unboxing, stack allocation, data-race-free parallelism

Declarative hyperparameter management for ML/AI experiments. Use when Claude needs to: (1) Create CLI applications with type-hinted parameters and auto-generated help (2) Configure ML training scripts with @proto.cli, @proto.prefix, or @proto decorators (3) Set up multi-namespace configurations with namespaced CLI arguments (4) Read configuration from environment variables using EnvVar (5) Create hyperparameter sweeps using piter or Sweep (6) Work with Union types for subcommand-like CLI patterns

Execute and coordinate work on PLAN files with phased breakdown. Tracks progress via JSON state, coordinates worker sub-agents in worker mode, and manages commits. Use when user references a PLAN file or asks to continue/execute a plan.

Query Polymarket: markets, prices, orderbooks, history.

Generate release notes by analyzing git commits and diffs. Use when asked to create release notes, changelog entries, or summarize code changes between versions.

Initialize or reconfigure the .things/ directory - creates config, registry, shared resources, and git repository. Detects and migrates existing config.yml automatically. Required before any brenna-plugs career plugin can store data.

Generate Shiny Mediator handlers, contracts, middleware, and scaffold projects for .NET applications

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.

Dividir e separar imagens em múltiplas partes independentes. Use esta skill sempre que o usuário pedir para dividir imagem em grade/grid, separar elementos de uma imagem, extrair ícones de sprite sheet, cortar imagem em pedaços, fatiar em colunas ou linhas, auto-detectar elementos em fundo uniforme, separar imagens compostas. Também ativa para 'split', 'grid', 'sprite sheet', 'separar elementos', 'dividir em partes', 'extrair de imagem', 'desmembrar', 'fatiar', 'split horizontal', 'split vertical', 'auto-split', 'detectar elementos', 'collage para imagens individuais'. Inclui detecção automática de elementos com OpenCV.

Setup Unicorn Studio WebGL shaders for stunning visual effects. Use this skill when the user says "setup shaders", "add unicorn studio", "webgl effects", "shader effects", "visual effects", or "unicorn.studio".

Apply advanced pixel art techniques including dithering, palette optimization, shading, antialiasing, and color theory. Use when the user mentions "dithering", "dither", "Bayer", "Floyd-Steinberg", "palette", "colors", "reduce colors", "optimize palette", "color limit", "shading", "shadows", "highlights", "lighting", "light source", "antialiasing", "smooth", "smoothing", "anti-alias", "AA", "color ramp", "gradient", "hue shifting", "saturation", "value", "contrast", or wants to "refine", "polish", "improve", "enhance", "make better", "add depth", "add dimension" to existing pixel art. Trigger on retro palette names (NES, Game Boy, C64, PICO-8), texture terms ("metal", "fabric", "stone", "wood"), and visual quality terms ("professional", "clean", "smooth", "vibrant").

Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping

Quick lookup for Effect TypeScript library APIs, patterns, and source code. Use when you need to find Effect functions, understand Effect patterns, or look up implementation details.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

# Claude-Mem OpenClaw Plugin — Setup Guide

Validates planning artifacts (spec.md, plan.md, data-model.md, contracts/) for quality, completeness, and consistency. Checks for mandatory sections, cross-artifact consistency, and constitution compliance. Always run after /speckit.plan completes.

Use when analyzing Rspack/Webpack bundles from local `rsdoctor-data.json` and producing evidence-based optimization recommendations.

This skill should be used when the user asks to "add a transaction", "create a beancount entry", "record an expense", "balance my accounts", "query my finances", "check account balances", "categorize spending", "write beancount", "edit .beancount files", "run a BQL query", "reconcile accounts", or mentions beancount, double-entry accounting, or ledger files. Provides comprehensive beancount syntax, directives, and query language expertise.

A skill that blends the wisdom of top industry experts, ensures token-efficient PRDs, and organizes outputs in a clear folder structure.

Guide the user through integrating Hyperspell into their project

Guides creation of custom, interactive data visualizations with D3.js — bar/line/scatter charts, network diagrams, geographic maps, hierarchies, and real-time data updates with zoom/pan/brush interactions and animated transitions. Use when chart libraries (Highcharts, Chart.js) lack the customization needed and you require low-level control over data-driven DOM manipulation, scales, shapes, and layouts. Invoke when user mentions D3, d3.js, custom visualization, force-directed graph, or data-driven SVG.

Use when creating custom Bazel rules, toolchains, providers, or aspects. Use when extending Bazel for new languages, build systems, or custom actions. Use when debugging Starlark rule implementations or understanding Bazel build phases.

Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.

Git workflow automation - commit/push with sign-off, create/list/compact/rebase PRs, and contribute to upstream repos. Use this skill whenever the user mentions PR, pull request, create PR, show my PRs, list PRs, squash commits, compact commits, rebase PR, commit and push, push updates, push changes, contribute to a repo, fork and submit, or wants to manage any aspect of Git operations.

Use when the user wants to automate capture of marketing screenshots for a SwiftUI iOS app across multiple locales, devices, or appearances. Covers full-screen shots, isolated element renders (carousel cards, widgets), and reproducible output naming. Triggers on marketing screenshots, locale screenshots, widget renders, App Store assets, fastlane-alternative, simctl screenshots.

Lark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM messages/reactions/chat changes, VC meeting ended, Minutes generated, Whiteboard updated, etc.). Use for Lark bots, real-time message processing, long-running subscribers, streaming webhook/push handlers. Supports `--max-events` / `--timeout` bounded runs and a stderr ready-marker contract — designed for AI agents running as subprocesses.

Manages the student's learning progress. Reads and updates course state, completed modules, solved exercises, and learning metrics. This skill is used automatically when the tutor needs to know or update progress.

Save and restore session state for continuity across context compressions. Invoke with "/memory-checkpoint" to save current session state, or "/memory-checkpoint your search query" to search past checkpoints by semantic similarity.

## Quick Start

Generate .NET MAUI Shell pages, ViewModels, navigation, and source-generated routes using Shiny MAUI Shell

Extract tacit engineering knowledge through guided interviews and generate structured steerings. Use when user mentions "steerings", "tacit knowledge", "conventions", "engineering practices", "interview", or wants to document team/project knowledge. Also activates when user asks for "steerings for X", "document X conventions", "continue steerings", "resume interview", or wants to extract knowledge about a specific topic. Supports reviewing and transforming existing steerings to standard format. Auto-detects existing sessions and offers to continue incomplete ones.

Detects stories that are too big and applies splitting heuristics. Identifies linguistic red flags (and, or, manage, handle, including) and suggests concrete splitting strategies. Use when breaking down requirements or splitting large work.

This skill provides comprehensive guidance for implementing advanced SwiftUI animations, transitions, matched geometry effects, and Metal shader integration. Use when building animations, view transitions, hero animations, or GPU-accelerated effects in SwiftUI apps for iOS and macOS.

Log a professional experience - accomplishments, lessons, expertise, decisions, influence, or insights. Extracts context from arguments or conversation history for fast capture, or runs a full guided interview when context is sparse.

This skill should be used when the user asks to "create a location", "add a location", "magic system", "political system", "build the world", "add culture", "world history", "technology system", "religion", "economy", or wants to develop any aspect of a story's world and setting.

WRAP decision framework countering the four villains—narrow framing, confirmation bias, short-term emotion, and overconfidence. Use for major decisions or when stuck between options.

ESX Legacy Framework for FiveM - Player management, jobs, economy, inventory, weapons. Use when creating ESX resources or working with xPlayer, PlayerData, ESX functions.

Validate uxscii components and screens against schema with interactive menu or direct script calls

Analyzes integration surfaces across multi-system ecosystems. From starting-point repos and config directories, discovers connected systems, profiles each one, maps cross-system capabilities, tiers functionality (T1/T2/T3/PRUNE), and generates a layered implementation plan (L0-L3) with dependency-ordered epics.

Process a Johnny.Decimal inbox by reading items from 00.01 Inbox folders, classifying them against the JDex and folder structure, and routing them to the correct location. Use this skill whenever the user mentions processing their inbox, filing items, sorting their JD inbox, triaging captured notes, or any variation of "process my inbox," "sort my inbox," "file my stuff," "what's in my inbox," or "triage my captures." Also trigger when the user drops files into an inbox folder and asks what to do with them, or when they say things like "I just dumped some stuff in my inbox" or "clean up my inbox." This skill handles single-system and multi-system JD setups.

Configure, diagnose, and use lossless-claw effectively in OpenClaw, with emphasis on key settings, summary health, and recall-tool usage.

Launch ralph.sh in background. Lightweight mode (default) or full Pod crew (--pod). Best for large features (10+ tasks).

Build vs Buy advisor. Use when users say: 'I want to build...', 'Help me create...', 'Can you code...', 'I need a tool/app/script'. Searches for existing libraries, SaaS, and open source solutions before vibe coding. Estimates token costs and provides comparison tables.

Create, modify, validate, and optimize README.md files following GitHub best practices.

Meta-skill for generating new skills with proper format and structure. Use when creating new skills for the swarm system or when agents need to generate skill scaffolds. Ensures skills follow conventions (frontmatter format, directory structure, bundled resources).

List and (later) control torrents on a Whatbox seedbox via rTorrent XML-RPC. Use when the user asks to list torrents, check seedbox status, manage rTorrent, or mentions Whatbox / rTorrent / a magnet link in this project.

Generate chapter clips from YouTube videos with yt-dlp and ffmpeg. Use when asked to download YouTube videos/subtitles, generate fine-grained chapters, cut precise clips, or generate per-chapter English SRTs.

Maps and documents codebases of any size by orchestrating parallel subagents. Creates docs/CODEBASE_MAP.md with architecture, file purposes, dependencies, and navigation guides. Updates CLAUDE.md with a summary. Use when user says "map this codebase", "cartographer", "/cartographer", "create codebase map", "document the architecture", "understand this codebase", or when onboarding to a new project. Automatically detects if map exists and updates only changed sections.

EDIFACT INVOIC parsing for German telecom providers Telekom, Vodafone and O2/Telefónica. Covers provider detection via UNB segment, SIM/ICCID and phone number extraction, MOA/DTM/RFF qualifier tables, and billing period identification.

Look up Elm package documentation, list project dependencies, search the Elm package registry, and read module exports. Use when working with Elm projects, elm.json files, or needing information about Elm packages.

Slices features into vertical deliverable pieces using the Hamburger Method. Generates 4-5 implementation options per layer and composes minimal end-to-end slices. Use when slicing work, breaking down features into layers, or delivering incrementally.

Run vet immediately after ANY logical unit of code changes. Do not batch your changes, do not wait to be asked to run vet, make sure you are proactive.

Minimal Chrome DevTools Protocol tools for browser automation and scraping. Use when you need to start Chrome, navigate pages, execute JavaScript, take screenshots, or interactively pick DOM elements. Triggers include "browse website", "scrape page", "take screenshot", "automate browser", "extract DOM", "web scraping".

Comprehensive guidance for integrating Jupiter APIs (Swap, Lend, Perps, Trigger, Recurring, Tokens, Price, Portfolio, Prediction Markets, Send, Studio, Lock, Routing). Use for endpoint selection, integration flows, error handling, and production hardening.

CRITICAL: Use for Makepad 2.0 DSL syntax and property system. Triggers on: makepad dsl, script_mod!, makepad syntax, makepad property, makepad 2.0 syntax, colon syntax, merge operator, named instance, let binding, mod.widgets, register_widget, script_component, type_default, widgets_internal

Scan your LinkedIn contacts' companies for matching job openings

Retrospect and improve a skill based on execution experience.

When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' 'partner program,' 'referral incentive,' 'how to get referrals,' 'customers referring customers,' or 'affiliate payout.' Use this whenever someone wants existing users or partners to bring in new customers. For launch-specific virality, see launch-strategy.

Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.

Help users define AI product strategy. Use when someone is building an AI product, deciding where to apply AI in their product, planning an AI roadmap, evaluating build vs buy for AI capabilities, or figuring out how to integrate AI into existing products.

This skill should be used when the user asks to configure, optimize, or troubleshoot their display/monitor setup. Triggers on "optimize my monitors", "configure displays", "rotate monitor", "set up my screens", "display settings", "monitor resolution", or any request to adjust multi-monitor arrangements, resolutions, refresh rates, or orientations on macOS.

Autofix common code-quality issues by running a pipeline of focused sub-agents (one-class-per-file, etc.). Use when the user wants to clean up code smells, normalize file structure, or run autofix on a set of files.

Use when querying the bknd source repository with btca CLI. Covers setup, configuration, and query patterns for learning bknd internals including data module, authentication, media handling, and adapter configuration.

Start a project-driven learning journey for any technical topic — programming languages, tools, frameworks, or concepts. Teaches through real projects, Diffity tours, and interactive conversation, adapting to the learner's pace.

Use when conducting systematic research in any domain (AI, healthcare, manufacturing, etc.), transforming vague interests into structured research through conversational discovery, or when users need evidence-based insights from broad exploration to actionable plans

Use two independent agents for reviews or research, then collate findings to identify common findings, unique insights, and divergences

Help users navigate tough feedback, performance conversations, and conflict. Use when someone needs to give hard feedback, have a performance conversation, fire someone, address conflict with a colleague, or deliver disappointing news like a denied promotion.

Use this skill when handling user input in Phaser 4. Covers keyboard keys, mouse clicks and movement, touch events, pointer handling, drag and drop, hit areas, interactive objects, and gamepad support. Triggers on: keyboard, mouse, touch, pointer, drag, drop, click, input, gamepad, cursor keys.

Must be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are saved for future turns.

# MemoryBench Integration Skill

Triages plan complexity to avoid heavyweight execution for trivial changes

Create user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into development-ready work with clear outcomes and testable conditions.

Extract specific XML elements from source files using Python and optionally format with xmllint. This skill should be used when users need to isolate a single XML element (like InstrumentVector with Id="0") from a larger XML document, preserving the complete element structure including opening and closing tags.

Critical Akka.NET best practices including EventStream vs DistributedPubSub, supervision strategies, error handling, Props vs DependencyResolver, work distribution patterns, and cluster/local mode abstractions for testability.

Complete guide for asyncio concurrency patterns including event loops, coroutines, tasks, futures, async context managers, and performance optimization

Export Google Scholar paper(s) to Zotero via BibTeX. Gets citation data from Google Scholar's cite dialog, then pushes to Zotero desktop. Supports single or batch export.

Set up hierarchical Intent Layer (AGENTS.md files) for codebases. Use when initializing a new project, adding context infrastructure to an existing repo, user asks to set up AGENTS.md, add intent layer, make agents understand the codebase, or scaffolding AI-friendly project documentation.

Manage git worktrees with iTerm2 integration. Use when user asks to create isolated development environments, work on features in parallel, manage worktrees, open worktrees in new tabs/windows, switch between worktrees, or close completed worktrees. Triggers on "create worktree", "new worktree", "feature branch with worktree", "open worktree", "switch worktree", "close worktree", "list worktrees", or mentions wanting to work on multiple features simultaneously.

Use when a user mentions Jupiter token verification, VRFD eligibility, paying 1000 JUP to verify a token, submitting a verification request, or updating metadata via the Jupiter express verification flow.

Query and manage Linear issues, projects, and team workflows.

Use when the user wants to extract a Miro board's specs (documents, diagrams, prototypes, tables, frames, images) to local `.miro/specs/` files for AI-assisted planning and implementation — accepts a board URL or single-item URL.

Invoke before creating or modifying Nette Forms. Provides form controls, validation, rendering patterns. Use when working with form factories, form controls, validation rules, form events, rendering forms in Latte, Bootstrap integration, form containers, or form error handling. Also trigger for $form/$data in Nette context.

QBCore Framework for FiveM - Player management, jobs, gangs, economy, inventory. Use when creating QBCore resources or working with Player object, PlayerData, QBCore functions.

Linter-driven refactoring patterns to reduce complexity and improve code quality. Use when linter fails with complexity issues (cyclomatic, cognitive, maintainability) or when code feels hard to read/maintain. Applies storifying, type extraction, and function extraction patterns.

Capture feedback about Teamcraft itself and turn it into a well-structured GitHub issue on the plugin's repo. Vets whether the problem is really a Teamcraft skill defect (vs. misuse, the harness, or the user's own project) by root-causing against the actual skill source, then helps the developer decide whether to file and publishes via the GitHub CLI. Use when the user says 'improve teamcraft', 'a teamcraft skill did the wrong thing', 'file feedback on teamcraft', 'report a teamcraft bug', 'I have an idea to make teamcraft better', or when a Teamcraft skill clearly misbehaved and the user wants that captured upstream.

Build AI agents, workflows and durable background tasks with Trigger.dev. Use when creating tasks, triggering jobs, handling retries, scheduling cron jobs, or implementing queues and concurrency control.

Validates plugin structure, components, and best practices against schemas