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.
Skill Claude CodeCodex
A cause-and-effect analysis method from modern TRIZ, a problem-solving approach. It repeatedly asks why to trace a visible problem back through the events and conditions that caused it.
Skill Claude CodeCodex
Inspect and edit Unity prefabs with uBridge 2.0.
Skill Claude Code
Persist and retrieve Claude Code work logs and reusable experiences under the current project's .worklog directory by default. Use when the user wants to record a coding session, source-reading session, debug session, or mixed session; when a task mixes development, reading, and debugging; when adding, deprecating, or…
Skill Claude CodeCodex
You are a football analyst competing against two other AI agents at predicting 2026 World Cup game outcomes. Each correct guess is worth +1 point.
Skill Claude Code
Manage and rotate Claude Code accounts. Use whenever the user wants to switch/swap Claude accounts, check usage or how close they are to the 5h or weekly limit, jump to the account with the most headroom or the one that resets/frees up soonest, add/remove/rename a stored login, refresh an expired token, diagnose…
Skill Claude Code
Generate customized .claude/ harness framework with Fusion Architecture (GAN-inspired + Domain Specialists). TRIGGER when user wants to set up AI-assisted development structure, create a new project harness, add structure to existing projects, or mentions 'harness', 'scaffold', 'framework setup'. Supports all domains…
LiYu0524/Auto-Reasearch-Skills
Skill Claude Code
Manage Google Docs and Google Drive with full document operations and file management. Includes Markdown support for creating formatted documents with headings, bold, italic, lists, tables, and checkboxes. Also supports Drive operations (upload, download, share, search).
breeze-r/claude-prompt-craft-skill
Skill Claude CodeCodex
Write, optimize, review, and structure prompts for AI assistants (Claude, ChatGPT, Codex, Claude Code, agents). Use this skill whenever the user asks to write a prompt, optimize a prompt, fix/improve a prompt, review a prompt, turn a vague request into a reusable prompt, design system prompts / task instructions for…
Skill Codex
Use this when a user wants to tailor a resume from a reusable evidence bank with Codex. It is best for AI, data, software, and quant-adjacent roles, uses archetype-aware routing on top of the core families, supports a local markdown-first bank or a legacy YAML bank, and stops at a truthful draft plus QA instead of…
Skill Claude CodeCodex
Verifies that a feature is wired through all four layers (schema, API route, runtime, UI) before it may be called complete. Use when adding or auditing any feature — mirrors the connectivity-map method that caught the v1.21 autonomy gap.
Skill Claude CodeCodex
Manage a multi-agent tmux workspace. Status, allocation, prompt drafting, cleanup.
Skill Claude CodeCodex
Guides users through building a complete, ATS-optimized resume using a proven 2026 methodology. Use when the user wants to create, rewrite, or improve a resume. Covers keyword strategy, a 5-section template, the Badass Bullet Point Formula, Professional Summary generation, and PDF export via a bundled script. Outputs…
Skill Claude Code
A memory system that stores project knowledge in linked Markdown files and loads only the notes relevant to a task and its nearby dependencies.
Skill Claude CodeCodex
A Russian-language guide for integrating the Prodamus Payform payment system into an application.
Skill Claude CodeCodex
Edita rascunhos em português para ficarem mais claros e mais humanos, preservando a voz de quem escreveu, ou aponta os padrões de escrita de IA sem reescrever. Use quando a pessoa quiser um texto mais direto, mais afiado, com menos cara de IA, ou perguntar se um texto parece escrito por IA.
GlamgarOnDiscord/uxui-AI-Prompt
Skill Claude Code
Expert Senior Frontend Engineer & UI/UX Designer for premium, dark-mode SaaS interfaces and modern landing pages. Triggers on: /build, /polish, /audit, /critique, /animate, /imagify, /dials, /variant — or any request involving UI design, landing pages, dashboards, components, frontend code, design systems, or visual…
Skill Claude Code
Portfolio-level skill curation: proposes merges, renames, retirements, and orchestrator wraps. Consumes skill-builder's overlap-check, audit-all, and list-orphans primitives (does NOT reimplement). Generates a versioned PORTFOLIOREORGPLAN.md and sweeps connectsto edges after structural changes.
Skill Claude Code
This skill should be used when the user asks to "search google", "find information online", "search the web", or needs real-time, grounded information from the internet.
Skill Claude CodeCodex
Extract user stories from baseline documents (PDF, DOCX, XLSX) into module specs.
mittwald/typo3-smart-extension-builder
Skill Claude Code
Create complete TYPO3 extensions with domain models, controllers, plugins, and Fluid templates.
Skill Claude CodeCodex
Produces a deep, honest peer-review of how someone uses Claude Code by statistically analyzing their local session data (/.claude/usage-data/ and /.claude/projects/). Trigger whenever the user asks to review, analyze, audit, or critique their own Claude Code usage, workflow, habits, or skill level — including phrases…
Skill Claude CodeCodex
Build ArtusX applications with best practices. TRIGGER when working with Artus.js framework, ArtusX plugins, or any task involving @artusx packages, decorators, lifecycle hooks, or plugin development. Use for creating new plugins, testing ArtusX apps, debugging lifecycle issues, configuring middleware, or…
Skill Claude CodeCodex
Draft a NEW document from scratch via docx-js (runcode language="node"). Use when the user wants to create new legal content from a blank page — agreements, memos, letters, resolutions, term sheets. For filling an existing template with placeholder values, use the docx-editing skill instead.
Skill Claude CodeCodex
A code-review procedure for checking a change from its commit history through its final tests. It covers scope, changed files, behavior, security, performance, and missing tests.
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: