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
Coordinate multi-agent development pipelines using shared JSON task files. Use when dispatching work across dev team agents (code-agent, test-agent, docs-agent, monitor-bot), tracking pipeline progress, or running sequential/parallel workflows. Covers project init, task assignment, status tracking, agent dispatch via…
Skill Claude CodeCodex
How to hand work to another agent, run Autopilot, and work through an issue backlog with safe parallelism. Loaded into every session.
Skill Claude Code
Coordinate a model-diverse local code review, automatically repair actionable findings with sequential workers, and re-review to a final verdict. Use for /review or when launched as an SC ensemble reviewer.
Skill Claude Code
Use when the user asks about optimizing NVIDIA Blackwell (SM100, B200) or Hopper (SM90, H100) GPU kernels — tcgen05/TMEM/CLC/NVFP4/2-SM cooperative, warp specialization, FlashAttention-4, DeepGEMM, FlashMLA, MoE, grouped GEMM, CuTe-DSL/PTX/Triton on Blackwell, or wants concrete PR references from…
Skill Claude Code
Generate an articulated (pull-out drawers / openable doors) 3D GLB model from a reference image, with real PBR textures (diffuse/roughness/normal) and headless render verification. Use when the user asks to build an articulated model (GLB/glTF) from an image, add textures or physical material parameters (roughness…
ailabs-393/ai-labs-claude-skills
Skill Claude CodeCodex
This skill should be used whenever users request personal assistance tasks such as schedule management, task tracking, reminder setting, habit monitoring, productivity advice, time management, or any query requiring personalized responses based on user preferences and context. On first use, collects comprehensive user…
Skill Codex
Generate checklist-first CodexBridge /agent drafts from natural-language intake using bounded action routing, skill-owned task typing, scope clarification, and immutable prompt scaffolds. Use when implementing, testing, or simulating first-host /agent add or bare /agent draft creation, especially for repo-aware code…
Skill Claude CodeCodex
A research workflow for Tushare, a Chinese financial-data service covering Chinese stocks, funds, company reports, money flows, news, and economic data.
Skill Claude CodeCodex
Extract evidence-based style guides and motion appendices from websites or web apps. Use when Codex needs reusable visual language, semantic tokens, component/state rules, runtime animation evidence, or style references that preserve design signal while stripping product-specific structure and content.
Skill Claude CodeCodex
A routing guide for Anima image generation through ComfyUI, a visual system for running image-generation workflows. It covers validating visual requirements and preparing prompts and settings.
zhizhuodemao/ai-reverse-toolkit
Skill Claude Code
A tool-assisted process for making deliberately hard-to-read JavaScript easier to understand. It uses Babel, a JavaScript parsing and code-generation toolkit, to decode strings, simplify expressions, remove unused code, and restore control flow when applicable.
zclllyybb/lofisu-identity-engine
Skill Claude CodeCodex
A role-playing guide based on an analysis of LofiSu’s public GitHub activity and online course-selling behavior. It describes how to respond from that person’s inferred perspective and communication style.
Skill Claude Code
Full structural hard-mode orchestration state machine with per-phase dispatch (H1), adversarial verification (H4), convergence policing (H6), territory contracts (H7), and churn detection (H5). Invoke for /orchestrate --hard.
Skill Claude CodeCodex
Headless grilling pass that challenges an approved implementation plan against the existing codebase and domain model, then writes an ADR draft and a PRD draft into the Foreman feature directory. Self-answers every question it can from the code/docs and surfaces the rest as an "Open questions for reviewer" block…
Skill Codex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
Skill Claude CodeCodex
Run NTM for multi-agent tmux orchestration, work triage, robot mode, safety, coordination, and local APIs. Use when spawning swarms, dispatching work, or operating ntm as an agent or human operator.
Skill Claude CodeCodex
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
Zchary1106/agent-interview-hub
Skill Claude CodeCodex
Collect and curate public AI Agent, LLM, RAG, MCP, and AI application interview experiences for agent-interview-hub.
Skill Claude CodeCodex
Secure dependency upgrades with supply chain protection, cooldowns, and staged rollout. Use when upgrading deps, configuring security policies, or preventing supply chain attacks.
Skill Claude CodeCodex
Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries external LLM APIs…
Skill Claude CodeCodex
Interact with the Mintlify REST API to manage deployments, trigger builds, and query documentation site metadata programmatically.
Skill Claude CodeCodex
MemMesh TypeScript SDK reference (@thinkfleet/memory-sdk) for the hosted platform at app.memmesh.ai. Covers the ThinkFleetMemory client — observe / search / list, the predict + lattice prediction surface, closed-loop learning (recordDecision / recordOutcome), emergent behavior discovery, and the health / financial…
Skill Claude CodeCodex
Detect whether a passage shows AI-like writing signals and return an explainable risk estimate with confidence, caveats, and next steps.
Skill Claude Code
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a sponsio.yaml, audit tool…
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: