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
Generate declarative multi-agent systems (MAS) using POMASA pattern language. Use when building agent pipelines, orchestrating multiple AI agents, or creating research automation workflows. Supports patterns like Prompt-Defined Agent, Orchestrated Pipeline, Filesystem Data Bus, and Verifiable Data Lineage.
Skill Claude CodeCodex
When inferring character intent or behavioral patterns from video, validate inferences against cumulative observed actions rather than isolated moments or assumptions.
theredbluepill/arc-interactive
Skill Claude CodeCodex needs its repo
This skill guides the creation of ARC-AGI-3 games based on established patterns from environmentfiles/.
Skill Claude Code
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
Skill Claude Code
Guidance for implementing and validating local repository changes in a DeepClause workspace.
DhananjayBhosale/Indian-Health-Insurance-Claim-Help
Skill Codex
Audit, organize, and create PDF packets for hospitalization-linked Indian health-insurance indemnity reimbursement claims, including day-care and pre/post-hospitalization evidence. Use for claim-document preparation or QA; not for standalone OPD, fixed-benefit claims, eligibility decisions, or promising approval.
ruaan-deysel/unraid-management-agent
Skill Claude CodeCodex
Monitor and control an Unraid server via the Unraid Management Agent's MCP server (125 tools, 5 resources, 6 diagnostic prompts) and REST API. Use when: connecting an AI client (Claude, ChatGPT, Cursor, Copilot, Gemini CLI) to Unraid; checking system, array, disk, Docker, VM, GPU, UPS, ZFS, or network status…
Skill Claude CodeCodex
Use AgentDebugX for trajectory diagnosis only when the user explicitly asks to use AgentDebug, AgentDebugX, or the agentdebug skill. Do not invoke for generic debugging, diagnosis, inspection, or trajectory-review requests.
Skill Codex
UFO-Browser is a high-performance local Chromium browser built for AI Agents and people to work in isolated Task Spaces while reusing browser login state. Use this skill whenever a task requires opening or navigating websites, filling forms, clicking controls, taking screenshots, extracting page data, testing web…
Skill Claude CodeCodex
A triage command that continually ranks approved GitHub issues by urgency. Triage means deciding which ready tasks should be handled first.
Skill Claude CodeCodex
Prepare, publish, repair, or verify package releases and changelogs. Always use for package/version release, publish, ship, tag, changelog, release notes, registry publication, documentation publication, or GitHub Release work. Distinguish package releases from application deployments before acting.
Skill Claude CodeCodex
You are a seasoned, atmospheric Game Master running a persistent tabletop RPG campaign. Your tone is immersive and descriptive — paint scenes with sensory detail, give NPCs distinct voices, and let choices have real consequences. You lean toward "yes, and..." rulings and fun over rigid rule enforcement, but the world…
Skill Claude CodeCodex
Use when you have access to Recallium MCP tools. Provides guidance on memory storage, search, and knowledge management. CRITICAL - invoke the MCP tool recallium at session start, store memories after EVERY substantive interaction, and honor global rules.
Skill Claude CodeCodex
A structured method for finding the underlying cause of a problem by asking “why?” repeatedly. It is intended for bugs, production incidents, performance problems, and recurring failures.
Skill Claude CodeCodex
A design skill for making high-fidelity prototypes, interactive demos, slides, animations, and design variations with HTML. It can also provide design-direction advice and expert reviews.
Skill Claude CodeCodex
Unofficial Google Health Connect data for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Google Health data or actions through an agent.
Skill Claude CodeCodex
Development guidance for FastAPI, a Python framework for building backend web APIs. It covers asynchronous database access with SQLAlchemy, data validation with Pydantic v2, login tokens using JWT and Redis, and the youlai-fastapi admin backend.
Skill Claude Code
Free-form optimization algorithm for agent orchestration mode: the conversational agent owns the whole search — proposing capability edits itself, screening them cheaply, gating each on full val, and sealing test once. Use when orchestrationmode is agent and algorithmskill is agent-optimize. For a deterministic loop…
Skill Claude Code
Enable to let the Keeper draw simple player-visible SVG handout maps: location maps, room hierarchy diagrams, clue-route sketches, and relationship/area structures with labels.
Skill Claude CodeCodex
Use this skill whenever you are connected to Open Watch Cinema through its MCP server.
Skill Codex
Orchestrate evidence-backed ANSYS Workbench and Mechanical structural analyses through a configured MCP, including capability discovery, existing-project or CAD intake, materials, named selections, connections, loads, high-quality mesh planning and repair, solving, convergence diagnosis, deterministic validation, and…
Skill Codex
OCR scanned or image-only corpora with vision-language models, in three phases. Use evaluate to compare candidate OCR systems against stratified human ground truth and pick one on measured CER/WER, run to build the production pipeline (model selection, image handling, prompts, architecture, batching, accuracy…
Skill Codex
A command-line tool guide for inspecting and safely changing an open Godot 4.6 project. Godot is a tool for building games and interactive applications.
Skill Claude CodeCodex
Migrate Spring Security 5 to Spring Security 6 configuration. Use when removing WebSecurityConfigurerAdapter, replacing @EnableGlobalMethodSecurity with @EnableMethodSecurity, converting antMatchers to requestMatchers, or updating to lambda DSL configuration style. Covers SecurityFilterChain beans and authentication…
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: