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.
KKunkuner/openclaw-retail-trader
Skill Codex
Build A-share retail-style trading suggestions for OpenClaw. Use when Codex needs to analyze China A-share stocks or ETFs with retail trader logic, including theme chasing, da-ban, di-xi, trend swing setups, sentiment cycle, sector rotation, buy and sell planning, stop loss, take profit, position sizing, and…
Skill Claude CodeCodex
A Chinese-language editing skill that identifies common patterns associated with machine-written prose and rewrites the text to sound more natural. It uses a phrase library and several layers of checks.
Skill Codex
A production workflow for turning approved content into editable and exportable media such as technical diagrams, GIFs, animated web pages, videos, audio, and podcasts.
ForceInjection/cuda-code-skill
Skill Claude CodeCodex
CUDA kernel development, debugging, performance optimization, linear algebra, and multi-GPU communication for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, parallel algorithms, or CUDA library calls. Covers cuBLAS/cuBLASLt GEMM operations, CUDA Math API (half, bfloat16, FP8, FP6…
Skill Claude CodeCodex
Diagnose TermCanvas agentmux nodes that fail to appear and terminal canvases that become janky, resize repeatedly, or show corrupted/unreadable xterm text as terminal count grows, plus duplicate terminal views created after a release relaunch. Use when a child agent is missing, restored terminals duplicate or move to…
Skill Claude CodeCodex
A single search tool for past conversations held by local coding agents such as Claude Code and Codex. It can also help trace which agent tool or command produced a file.
Skill Claude Code
Migrate a Jakarta Faces project from one version to another (e.g. JSF 2.3 to Faces 4.1).
Skill Claude CodeCodex
Close feature [agent] [--adopt] - merges branch, cleans up, optionally adopts from losers.
Skill Claude CodeCodex
Complete development guide for contributing to PawFlow: architecture, patterns, conventions, and key subsystems.
yudong-94/storytelling-viz-skill
Skill Codex
Story-first Plotly workflow for turning a dataset into a polished interactive visualization with local review artifacts. Use this skill when the user wants a concise, intuitive chart with a clear takeaway, plus final index.html and preview.html, without website publishing work.
Skill Claude CodeCodex
Set up Bridge Commander for the first time (an empty folder becomes a board with a lieutenant already on it), or turn the current directory into a workspace and become its founding lieutenant (the teleport), or re-enter an existing one. Use when the user asks to init/set up bridge command, open the bridge board, or…
Skill Claude CodeCodex
Integrate patient-authorized EHR record retrieval into a digital health app using Fasten Connect — provider linking, webhook ingestion, FHIR record handling, and the data privacy decisions that come with holding the records.
Skill Claude CodeCodex
Aggressively strip redundant proof code from a Verus codebase while keeping verification passing. Use when you want to slim down Verus proof bloat, simplify redundant proof asserts, or run postprocess cleanup without breaking verification.
Skill Codex
Convert user-supplied photos into reference-locked 3:4 travel, coffee, or movie ticket posters with either the original horizontal landscape composition or a tall portrait-photo keepsake composition. Landscape defaults to a photo-derived matte palette; portrait defaults to the supplied reference's muted olive woven…
Skill Claude CodeCodex
This guide documents patterns and best practices for orchestrating Multica through the MCP server, from an LLM chat (Claude Desktop, Codex Desktop, Claude Code, or any MCP-capable client).
Skill Claude CodeCodex
Add WeChat (微信) as a channel. Uses ilink bot long-poll API for message receiving and sending. Supports text, image, video, file, and voice messages. No public URL or webhook needed. Works alongside any other channel. Language-agnostic — auto-generates code for the target project's language and framework.
Skill Claude CodeCodex
An AI running coach that uses data from a COROS sports watch to create and adjust training plans for races such as 5K, half-marathons, and marathons.
Skill Claude Code
Repère et corrige les marques d'écriture par IA dans un texte en français. À utiliser quand l'utilisateur demande d'humaniser un texte en français, de le relire, de retirer les tics IA, ou dit qu'un texte « sonne IA » / « sonne ChatGPT » / « fait IA ».
Skill Claude Code
Builds SVG user-flow diagrams for an audit (entry → screens → conversion/drop-off) following the PLAYBOOK §11a constants. Use when the user asks for a "flow diagram", "user flow", or "flow map".
Skill Claude CodeCodex
A writing guide for WeChat public-account articles. WeChat public accounts are channels used to publish articles in China; this guide targets people exploring side projects, independent software, and AI work.
Skill Claude Code
Release Dart packages in the aiclientsdart monorepo. Detects changes since last release, bumps semver, writes changelogs, publishes to pub.dev, creates git tags, and creates a combined GitHub release. Use for releasing packages, publishing, version bumping, or creating releases.
Skill Claude CodeCodex ✓ vendor
Load when reflecting on AI collaboration quality or tracking growth over time. Analyzes session history to surface how deeply you think with AI tools and whether your orchestration sophistication matches your cognitive depth. Provides actionable nudges to push toward more strategic work.
Skill Claude CodeCodex
How an AI coding agent should operate inside CodeGrid — the macOS canvas that runs Claude, Codex, Gemini, Cursor, Grok, and shells side by side and lets them collaborate. Use this skill whenever you are running in a CodeGrid pane, or a user asks you to spawn/list/control agents, open a project, drive the workspace, or…
Skill Codex
Full notes on graph-native authoring, lossless projection, named relational reads, and scope limits.
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: