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.
zeke/preview-deployments-skill
Skill Claude CodeCodex
Add Cloudflare Workers preview deployments to existing GitHub apps using GitHub Actions, Wrangler, gh secrets, and the GitHub Deployments API. Use when asked to add per-PR preview deployments, ephemeral Workers previews, preview URLs, GitHub deployment statuses, Cloudflare preview environments, or teardown on PR close.
vshrinath/virtual-product-factory
Skill Claude CodeCodex
Enforces commit message format, changelog discipline, and file organization. Ensures git history is useful and documentation is current. WHEN to use it - before committing code, when creating or updating documentation, when organizing project files, or during code reviews involving git history.
Skheiller/manim-community-deep-skill
Skill Codex
Convert plain-language concepts into ManimCE scene plans, runnable code, preview renders, and final export commands. Use when a user provides narration, bullet points, or storyboard notes and wants end-to-end ManimCE output. Do not use for ManimGL/manimlib codebases.
Skill Claude CodeCodex
Map Azure architectures and operations to security and compliance controls. Use this skill when users ask for governance, policy enforcement, audit readiness, or regulatory alignment. Covers ISO, SOC2, HIPAA, PCI-DSS, and custom compliance frameworks.
z3247124509-sketch/ai-rag-agent-designer-skill
Skill Codex
An AI product planning guide for deciding whether to use retrieval-augmented generation (RAG) or an agent. RAG lets an AI search a knowledge collection before answering, while an agent can choose actions and tools.
Skill Codex
A skill that turns product requirements, rough PRDs, competitor research, or Lark and Feishu documents into a short Markdown product requirements document. A PRD describes what a product should do and gives developers implementation guidance.
gensyn-ai/gensyn-delphi-skills
Skill Claude CodeCodex
Gensyn Delphi information market tools, including the Delphi agent trading competition. List and filter markets (including verifiable-only filter), fetch market details with live on-chain prices and implied probabilities, quote buy/sell trades, execute buy and sell transactions (with automatic token approval and…
Skill Claude CodeCodex
Send SMTP email notifications after Codex completes a task. Use when one Codex or Claude run is finished, or when you need to notify on task completion with device name, project name, status, and summary via email.
LiyuanW21/obsidian-wiki-system
Skill Codex
Initialize or maintain a reusable Obsidian wiki knowledge iteration system with raw inbox, wiki pages, source/concept/synthesis/project templates, workflows, prompts, indexes, logs, and AGENTS.md rules. Use in Codex, OpenCode, or any agent that can read skill folders when the user wants to create a new Obsidian vault…
Skill Claude Code
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
NextFrontierBuilds/elite-longterm-memory
Skill Claude CodeCodex
Ultimate AI agent memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud backup, and maintenance hygiene. Never lose context again. For Clawdbot, Moltbot, Claude, GPT agents.
JohnCrickett/ai-coding-workflow
Skill Claude CodeCodex needs its repo
Create a plan to implement the provided requirements.
Skill Claude CodeCodex
Operate a CRATE knowledge vault: raw/, wiki/, meta/, compile, ask, lint, wiki-graph, reports, and safe wiki-check apply. Use when editing or automating a CRATE vault, running crate CLI, or interpreting meta/.json.
Skill Claude CodeCodex
Use this skill when working in a project that has a RunawayContext v3 install. It loads the project's brief from the auto-generated Tier 3 markdown, queries knowledge.db for relevant lessons and chunks, and routes writes through the contract-enforced Client (HR-2 / HR-3 / HR-9). Trigger when the conversation enters a…
Skill Claude CodeCodex
Send files, images, and audio messages via Feishu Lark API using the mandatory two-step process. Use when needing to send files, images, or voice messages to Feishu users or groups. This skill enforces the required workflow - first upload to get filekey, imagekey, or audiokey, then send message with the key. Supports…
Skill Claude CodeCodex
Write winning grant proposals for nonprofits and social impact organizations. Covers grant research and selection, proposal structure, compelling narrative writing, budget development, evaluation plans, and submission best practices. Use when applying for foundation grants, government funding, corporate sponsorships…
saifoelloh/golang-best-practices-skill
Skill Claude CodeCodex needs its repo
Clean Architecture audit for Go services. Use when reviewing layered architecture, dependency rules, or gRPC/usecase/repository patterns. Ensures proper separation of concerns and dependency inversion.
Skill Claude CodeCodex
An HR roleplay and writing aid that produces workplace messages in Chinese, English, or both, using different company and recruiting styles.
backspace-shmackspace/claude-devkit
Skill Claude CodeCodex
Use when performing threat modeling for a project, feature, or system architecture. Applies STRIDE threat categorization with DREAD risk rating to produce structured threat models in OTM JSON and markdown formats. Covers system decomposition, trust boundary mapping, data flow analysis, per-subsystem threat…
Skill Claude CodeCodex
Battle-tested Playwright E2E testing patterns for Next.js/React apps. Use when writing, running, debugging, or fixing Playwright tests. Also triggers on 'e2e', 'end-to-end', 'playwright', 'browser test', 'UI test', 'integration test with browser', 'flaky test', 'test keeps failing'. Covers locators, assertions…
Skill Claude CodeCodex
Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export. Use for security audits, compliance documentation, flow tracing, feature ideation, brainstorming, debugging, architecture reviews, or incident post-mortems. Triggers on audit, trace flow, document…
Jayden-X-L/claude-codex-bridge
Skill Claude Code
Bridge Claude Code and Codex for bidirectional execution review. Use when Claude should send its result to Codex/GPT-5.5 for audit, audit Codex/GPT-5.5 handoffs, return feedback to Codex, or run an automated Claude-Codex review loop.
Skill Claude CodeCodex
Navigating LLM tooling workflows. Use when choosing recall, search, SQLite, MCP, secret-safety, or skill validation tools.
screem500/prompt-injection-auditor
Skill Claude CodeCodex
Security audit of LLM system prompts, agent instruction files (SKILL.md, AGENTS.md, CLAUDE.md), and agent configurations against prompt injection attacks. Use when the user wants to (1) audit or harden a system prompt or agent instructions against prompt injection, (2) review an agent skill or system prompt for…
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: