Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Take a product's OUTER APPEARANCE (industrial design: form, proportion, panel split, CMF, controls layout) from a brief + AI-generated look images to a parametric three.js appearance model, a fixed-camera contact sheet, Blender Cycles finals, and a versioned ID report (md authority + Word snapshot) — driven by an AI…
Creates a new VR Experience (Level) for Neural Flight. Step-by-step guided workflow — creates folder, adapts 5 files from template, defines parameters, registers in catalog. Supports reference images and descriptions. Use when the user wants to create, scaffold, or add a new experience or level.
A personal health-management assistant that combines exercise coaching, nutrition advice, health tracking, and traditional Chinese medicine guidance. It covers topics such as training, diet, body constitution, seasonal care, tongue analysis, and sexual health within a health context.
Generates SVG sprite maps from Iconify icon packs at build time and serves them during dev. Icons are registered lazily via getIcon() and assembled into per-pack sprite files.
A machine-learning guide to causal inference, which estimates whether one factor causes a change in another. It covers DML, causal forests, DoWhy, and AIPW methods.
Convenes a multi-model "council" to answer a question, then synthesizes a single best answer — inspired by Karpathy's llm-council. Each member runs through its own subscription/sign-in CLI, not an API key: ChatGPT (the desktop app, via chatgpt-ask), Gemini (Antigravity agy), and Claude (claude -p), with Codex (codex…
Run an adversarial debate with a cross-model reviewer (Codex or Antigravity/agy) to stress-test a draft, plan, research claim, or design decision. Use this whenever you need structured critique before finalizing decisions.
★not rated 5
changed 3d agoASkillSpector: warn0 tokens
originalMIT
Produce higher-quality code by breaking a feature into small, focused tasks the coding agent can nail one at a time. Works like an engineering team: feature → milestones (product deliverables) → 30-min tasks with specific files, acceptance criteria, and dependencies. Each task runs in a fresh context — narrow scope…
A workflow for turning Korean lecture notes or subtitles into a whiteboard-style teaching video. It can combine scene images, voice narration, subtitles, dynamic timing, and a final 4K MP4.
A workflow for developing one requirement across multiple Git repositories, which are separate code projects. It creates a shared workspace containing the requirement, implementation plan, and selected project copies.
Use BEFORE writing any HTML artifact, widget, diagram, chart, image gallery, or dashboard into a wick chat reply. Covers which fence to use (html vs htmlfile vs svg vs mermaid vs imagecard), the theme bridge variables an artifact must use, why fetch() is blocked inside an artifact and what to use instead…
Guide users through creating, reviewing, and improving OpenClaw skills following proven best practices. Use when someone asks to "create a skill", "write a SKILL.md", "make an OpenClaw skill", "publish to ClawHub", "review my skill", "improve my skill", "optimize skill description", "skill frontmatter help", "what…
SQLite disaster recovery and streaming replication to cloud storage (S3, GCS, Azure, SFTP, NATS). Use this skill for configuring Litestream, deploying to cloud platforms, troubleshooting WAL replication issues, implementing point-in-time recovery, and setting up VFS read replicas.
Create and edit Apache ECharts v6 visualizations. Use when users want to build interactive charts, dashboards, or data visualizations. Supports line, bar, pie, scatter, radar, heatmap, treemap, sunburst, gauge, chord, and 20+ other chart types. Generates working HTML, JavaScript, React, or Vue component code.
Expert code review guidelines with priority levels, core review areas, language-specific checks, and structured output format. Use this when asked to review code, review a PR, or perform a code review.
Reads all client-provided collateral (RFP documents, PRDs, org materials, prior proposals, case study notes) and produces a structured brief and gap report. Trigger when the user provides RFP materials, says "analyze the collateral," "start the RFP response," "what do we have to work with," or drops files for an RFP…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
Use when the user wants a git-history health check of an unfamiliar or inherited repository — triggers on "git recon", "codebase health check", "analyze this repo's history", "where are the landmines", or onboarding/due-diligence framing. Do NOT use for architecture review, bug-fixing, or feature work; this skill…
Auto-discover and communicate with any AI agent given its URL via API. Supports REST APIs (OpenAI, Anthropic, Ollama), WebSockets, and Gradio apps. Claude Code acts as the user, automatically detecting the agent's API interface and sending messages. Use when: (1) User provides an API endpoint URL, (2) Need to automate…
Project an existing canonical .claude setup to GitHub Copilot, or fully AI-enable a repository for Claude Code and Copilot with shared instructions and the developer-led workflow. Re-runnable; converges the repo on the layout.
Laravel Fortify headless authentication backend development. Activate when implementing authentication features including login, registration, password reset, email verification, two-factor authentication (2FA/TOTP), profile updates, headless auth, authentication scaffolding, or auth guards in Laravel applications.
★not rated 5 8mo agoA59 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: