Skills

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.

otsukare

10081

WillHsiaoNYC/Claude-Code-Skill-Otsukare

Skill Claude Code

Use when starting a long or token-heavy task that could exhaust the Claude Code 5-hour or 7-day usage limit mid-run, or any long unattended run that must survive a usage-limit pause and pick the work back up afterward. Triggers on "otsukare", "watch my usage", "pause if I hit the limit".

not rated 24 4mo ago A 72 tokens original MIT

paper-figure-styling

10082

zhousodo/paper-submission-check

Skill Codex

Comprehensive figure styling, color scheme, typography, axis/grid design, aspect ratio, legend system, statistical visualization, layout, table design, caption formatting, cross-reference audit, cross-figure consistency, export quality pipeline, hyperlink color policy, and cross-publisher adaptation (Elsevier, IEEE…

not rated 24 6mo ago A 231 tokens original MIT

agent-memory

10083

taichuy/agentMemory

Skill Claude CodeCodex

Initialize or repair an agentMemory .memory directory and root instruction files for Claude Code, Codex, OpenCode, and Gemini CLI. Use when the user invokes /skills, asks to install agent memory, initialize .memory, set up AGENTS/CLAUDE/GEMINI memory pointers, or avoid repeating the agentMemory install command.

not rated 24 6mo ago A 71 tokens original Apache-2.0

fredrikc3-sketch/VibeConfigStarterKit

Skill Claude CodeCodex

NON-NEGOTIABLE compliance gate for any project that configures D365 Finance modules (General Ledger, AP, AR, Fixed Assets, Cash & Bank, Tax, Budgeting, Project Accounting, Expense). Captures the customer's applicable accounting and regulatory frameworks (US GAAP, IFRS, local GAAPs, SOX, ASC 606 / IFRS 15, ASC 842 /…

not rated 24 6mo ago A 210 tokens

skill-issue

10085

krispuckett/skill-issue

Skill Claude CodeCodex

Audit and review all installed agent skills. Run on-demand or via cron to get a health report: skill inventory, usage tracking, version checks, dependency health, and actionable recommendations (keep, update, review, remove). Use when asked to review skills, check for skill updates, find unused skills, or audit the…

not rated 24 9mo ago A 70 tokens original MIT

huashu-design

10086

pc-software-org/huashu-design-en

Skill Claude CodeCodex

Huashu Design - Integrated design capabilities using HTML for high-fidelity prototypes, interactive demos, slideshows, animations, design variant exploration + design direction consultant + expert review. HTML is a tool not a medium, embody different experts (UX designer/animator/slideshow designer/prototyper)…

not rated 24 2mo ago C 535 tokens original MIT

azure

10087

clawdata/clawdata

Skill Claude CodeCodex

Manage Azure cloud resources -- resource groups, storage, databases, functions, and data services using the az CLI.

not rated 24 8mo ago A 24 tokens

swift-mlx-lm

10088

PicoMLX/mlx-swift-lm-skill

Skill Claude CodeCodex

MLX Swift LM - Run LLMs and VLMs on Apple Silicon using MLX. Covers local inference, streaming, wired memory coordination, tool calling, LoRA fine-tuning, embeddings, and model porting.

not rated 24 8mo ago A 52 tokens copy · 100% MIT

typesetter

10089

Wamikmk/typesetter

Skill Claude CodeCodex

Turn any content into a beautifully typeset, single-file HTML document in the user's established reading design (warm paper, serif body, blueprint accents), because the user finds raw markdown daunting to read. PRIMARY TRIGGER is the slash command "/paper [topic or content]": when the user types this, ALWAYS trigger…

not rated 24 4mo ago A 0 tokens

korrodesign

10090

KorroAi/korrodesign

Skill Claude Code

Design Copilot with two enforcement layers (Taste Guardian + Blind Spot ESLint plugin, 14 rules). Works standalone with zero dependencies. 7-phase design pipeline. Produces Awwwards-level websites with automated UI hygiene enforcement.

not rated 24 changed 1mo ago A 50 tokens original MIT

fast-edit

10091

includewudi/fast-edit

Skill Claude CodeCodex

A tool for editing large files, making batch changes, writing files from pasted or standard-input text, and checking, undoing, rolling back, or restoring edits.

not rated 24 8mo ago A 57 tokens

mckinsey-consultant

10092

pennypny163/mbb-deck-builder

Skill Claude CodeCodex

A structured business-problem-solving method based on McKinsey-style analysis, including issue trees, hypotheses, and research reports or presentations.

not rated 24 6mo ago A 82 tokens copy · 89% MIT

first-principles

10093

reshadat/first-principles-destructor

Skill Claude CodeCodex

First principles destructor — strips any statement, business model, product idea, process, or industry belief down to its physics/math/logic floor. Calculates the convention tax (what you pay because of habit vs necessity). Rebuilds from reality. Use when evaluating pricing, hiring timelines, product approaches, team…

not rated 24 5mo ago A 106 tokens original MIT

hu-chen-feng-skill

10094

123pyLeo/hu-chen-feng-skill

Skill Claude CodeCodex

A Chinese-language framework for judging decisions through practical constraints, evidence, returns, risks, and ordinary people's circumstances. It is associated with the direct analytical style of Hu Chenfeng.

not rated 24 7mo ago A 115 tokens original MIT

vibe-coding-prd

10096

1killermouse/vibe-coding-prd-skill

Skill Codex

A guide for turning product requirements, competitor research, ideas, or documents into a short Markdown plan that coding agents can follow.

not rated 24 4mo ago A 119 tokens

skillbox

10097

christiananagnostou/skillbox

Skill Claude CodeCodex

Manage skills with the skillbox CLI.

not rated 24 12d ago A SkillSpector: pass 10 tokens original MIT

generating-code-connect

10098

bitovi/superconnect

Skill Claude CodeCodex

Generates Figma Code Connect mappings for React or Angular repos, validates them with pre-checks and the Figma CLI, and can publish via figma connect. Use when a user provides a Figma file URL and a component repo and asks for Code Connect files, figma.config.json, or validation.

not rated 24 9mo ago A 67 tokens original MIT

memory

10099

aictx/memory

Skill Claude CodeCodex

Use this skill when working in a project that uses Memory by Aictx as product-layer project memory. It guides the agent to query memory on demand mid-task, save product-meaningful changes after meaningful work, and sync memory at session end.

not rated 24 +1 3mo ago A SkillSpector: warn 52 tokens original MIT

doc

10100

OpenKnots/okcode

Skill Claude CodeCodex

Edit and review docx-style documents.

not rated 24 6mo ago A 10 tokens original MIT

gx

10101

ashsidhu/gx-ghostty

Skill Claude CodeCodex

Use when interacting with Ghostty terminals — listing, peeking, sending text, managing windows/tabs/splits, or controlling Claude Code teammates.

not rated 24 6mo ago A 30 tokens original MIT

about-oneclaw

10102

GNHua/oneclaw

Skill Claude CodeCodex

Comprehensive knowledge base about OneClaw -- architecture, features, tools, and configuration.

not rated 24 +1 8mo ago A 22 tokens

embinder

10103

celesnity/Embinder

Skill Codex

Integrate the Embinder WebMCP SDK into an existing product and make its browser experience AI-native. Use when a coding agent must inspect any web application or platform, inventory every page and user-facing function, expose real actions and live context through Embinder, add the resident agent, cursor, spotlight…

not rated 24 3mo ago A 96 tokens

simlab-auto-research

10104

collinear-ai/simlab

Skill Claude CodeCodex

You are running an autonomous experiment loop that optimizes a system prompt for an AI agent evaluated on SimLab tasks. You will modify system-prompt.md, run the agent against tasks, measure the average reward, and iterate.

not rated 24 3mo ago A 0 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: