Skill Claude CodeCodex
Fetch, verify, and install agent skills stored entirely on the Solana blockchain, given only a Metaplex Core asset address.
not rated 4 2mo ago A 33 tokens
original MIT
muhosekerci/imgui-ui-ux-engineering
Skill Codex
Proactively design, improve, or review high-quality Dear ImGui tools, C++ editor panels, game-development interfaces, debugging dashboards, visualization screens, and desktop workflows. Use when Dear ImGui is named or supplied code contains direct evidence such as ImGui::, imgui.h, ImGuiContext, or ImGui backend…
not rated 4 27d ago A 174 tokens
original MIT
dfo-pvf
2115Skill Claude CodeCodex
A tool for examining complete PVF file collections from Dungeon & Fighter, a multiplayer action role-playing game. It covers game data such as animations, skills, monsters, attacks, and AI behavior.
not rated 4 4mo ago A 124 tokens
forms-builder
2116Skill Claude CodeCodex
Creates and edits monday.com WorkForms - public intake forms that capture responses as new items on a backing board. Useful for request intake, bug reports, lead capture, event signups, internal submissions, and any flow that turns a user-submitted form into a tracked work item. Use when user asks to "create a form"…
not rated 4 3mo ago A 143 tokens
original MIT
meta-skill-creator
2117Skill Claude Code
A skill for creating, restructuring, and checking reusable packages of instructions for coding agents. It covers how the package is triggered, tested, documented, and improved from real usage.
not rated 4 2mo ago A 245 tokens
original MIT
systems-thinking
2118Skill Claude CodeCodex
Use when a problem involves interacting actors, feedback loops, delays, incentives, constraints, unintended consequences, or repeated patterns over time. Use when applying systems thinking, causal loop analysis, system mapping, leverage point identification, or dynamic complexity diagnosis.
not rated 4 28d ago A 51 tokens
original Apache-2.0
runes-minting
2119Skill Claude CodeCodex
Use this skill when the user wants to mint, etch, or create a Rune (Bitcoin fungible token via the Runes protocol). Triggers on: "mint a rune", "etch SOVEREIGN", "create rune token", "issue runes", "fair launch", "open mint", "mint more of an existing rune", or any request involving Rune names (uppercase A–Z with…
not rated 4 5mo ago A 135 tokens
claude-patch
2120huybuidac/claude-code-patchkit
Skill Claude Code
Patch Claude Code CLI binary to unlock hard-coded limitations. Use when the user wants to apply, revert, or check status of binary patches after upgrading Claude Code. Community-contributed patches for model restrictions, feature flags, and schema unlocks.
not rated 4 17d ago A 53 tokens
original MIT
shopline-payments
2121boyonglin/shopline-payments-skill
Skill Claude Code
A guide for connecting Taiwanese SHOPLINE Payments to a website or service. It covers redirect and embedded checkout, local payment methods, transaction handling, refunds, cancellations, and signed webhook notifications.
not rated 4 7mo ago B 138 tokens
original MIT
stm
2122mdsohaib/screenshot-time-machine
Skill Claude Code
Screenshot every page of the running localhost dev server and report which pages changed since the last snapshot. Use after editing anything users can see (pages, components, CSS/Tailwind, layouts, templates) to visually verify before saying you're done, and when the user says "check the UI", "does it look right"…
not rated 4 4d ago A 112 tokens
original MIT
oguzkr/skill-agent-session-handover
Skill Codex
Use this skill when the user asks one local AI agent to inspect, continue from, hand off, summarize, or compare another local agent session, especially Cursor agent transcripts under /.cursor/projects, Codex sessions under /.codex/sessions, and Claude Code transcripts under /.claude/projects.
not rated 4 1mo ago A 64 tokens
original MIT
xhs-post-writer
2124lindixu6-hash/ai-content-workflow-skills
Skill Claude CodeCodex
A Chinese-language writing workflow for creating posts and spoken scripts for Xiaohongshu, a Chinese social media platform. It develops a topic through several draft stages and preserves the user’s real experiences and evidence.
not rated 4 16d ago A 47 tokens
original MIT
token-antiflash
21250xlayerghost/solidity-agent-kit
Skill Claude CodeCodex
When this skill is triggered, DO NOT directly implement all strategies. Follow this workflow.
not rated 4 1mo ago A 91 tokens
original MIT
pwrl-work-execute
2126Skill Claude Code
Execute tasks with quality gates (inline, serial, or parallel modes).
not rated 4 2mo ago A 20 tokens
modest-curator478/claude-skills
Skill Claude Code
AUTO-TRIGGER: Apply this skill when the user needs to defend, justify, or grow a marketing budget in front of a CEO, CFO, board, or executive team. Trigger phrases include: "budget review," "defending the budget," "CEO wants to cut marketing," "justify marketing spend," "prove ROI," "board presentation," "marketing…
not rated 4 2d ago A 197 tokens
copy · 100% MIT
read-research-paper
2128Skill Claude CodeCodex
Renders ANY research paper (URL / arXiv ID / DOI / PDF / pasted text) into a visually engaging multi-format reading experience — with mind maps, method flowcharts, key-finding infographics, comparison tables, related-work timelines, and a plain-English layer alongside the technical content. Activates on slash commands…
not rated 4 4mo ago A 172 tokens
original MIT
grill-to-spec
2129Skill Claude Code
Convert a completed grill-me session into a spec file. Captures only the task and the decisions locked during grilling — no implementation details, no invented decisions. Use when the user asks to write a spec from a grill, save grill decisions, or after a grill-me session concludes.
not rated 4 3mo ago A 61 tokens
original MIT
audit-this-project
2130Skill Claude Code
Run an independent security audit of this repository before trusting it. Use when the user asks whether this project is safe, what it sends over the network, what it does to their computer, whether it is malware or spyware, or asks for a security review of this codebase.
not rated 4 16d ago A 59 tokens
copy · 100% MIT
book-skills-creator
2131Skill Claude CodeCodex
Create modular, source-grounded Agent Skill packs from explicitly selected books or documents. Use when a user wants atomic skills, combo workflows, a router, references, a skill map, and validation derived from a specific source.
not rated 4 2mo ago A 50 tokens
original MIT
rapids-first
2132Skill Claude CodeCodex
Use only when the user explicitly mentions "rapids-first" or "RAPIDS first", to prefer the RAPIDS GPU stack (cudf, cuml, cupy, cupyx) and its zero-code accelerators over pandas, scikit-learn, numpy and scipy when writing Python data-science, ML, ETL or numerical code.
not rated 4 19d ago A 76 tokens
original MIT
Skill Codex
A guided process for first-pass legal review of Russian-law contracts, offers, policies, and personal-data handling. It is intended as risk analysis, not a replacement for a licensed lawyer.
not rated 4 4mo ago A 76 tokens
original MIT
Skill Codex
Use this skill when the user wants to review, verify, or revise a TeX or PDF research paper by checking whether claims, tables, figures, citations, and conclusions are actually supported by code, experiment runs, logs, and reproducible evidence. The manuscript must not be more confident than the experiments.
not rated 4 4mo ago A 67 tokens
Skill Claude CodeCodex
English guide for VS Code extension development — from scaffolding to Marketplace publication. Covers webview patterns, CSP security, TreeView, testing, packaging, AI customization, and troubleshooting. Adapted from aktsmm/agent-skills with corrections for VS Code 1.74+ APIs.
not rated 4 4mo ago A 64 tokens
murpick
2136Skill Claude CodeCodex
Use when the user shares reference materials (screenshots, screen recordings, links, or a local folder) about products they like and wants competitive research or feature selection before building something similar; when they ask for a "feature menu", "à la carte" picking, or say they want to choose which features to…
not rated 4 1mo ago A 90 tokens
original MIT
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: