Skills

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.

investment-advisor

17377

niqinggood/openkitty-light

Skill Codex

Provide educational risk profiling, diversified asset-allocation examples, and portfolio review guidance. Use for investment planning, risk assessment, diversification, or portfolio-review requests; never execute trades or promise returns.

not rated 5 2mo ago A 42 tokens original MIT

dungnotnull/daily-quest-retention-system-agent-skill

Skill Claude CodeCodex

This document is the canonical, human- and machine-readable registry for the skill: how skills are registered, resolved, exec, and validated. It is the contract surface between the harness, the sub-skills, and any external orchestrator (Claude Code, a custom agent runtime, or CI).

not rated 5 2mo ago A 0 tokens original MIT

dungnotnull/ar-vr-graphics-hardware-tuning-agent-skill

Skill Claude CodeCodex

Graphics & Hardware Configuration Advisor for VR/AR Games — XR Graphics & Hardware Performance Tuning evidence-backed analysis & decision-support harness. Use this skill whenever optimizing VR/AR graphics settings, configuring hardware for XR applications, analyzing performance bottlenecks, tuning reprojection and…

not rated 5 2mo ago B 153 tokens original MIT

4ier/openclaw-feishu-group-chat

Skill Claude CodeCodex

Teach OpenClaw how to work in Feishu (Lark) group chats — recognize who's talking, behave properly in groups vs DMs, respect multi-user privacy, and format messages for the platform. Use when connecting OpenClaw to Feishu and you want your agent to be a competent group participant, not just a responder.

not rated 5 6mo ago A 75 tokens

bgo

17381

Yuru778/bgo

Skill Claude CodeCodex

Automated Blender build-go workflow. Automatically builds, removes old version, installs, enables, and launches Blender with your extension/add-on. Use when you want to quickly test changes, execute complete build-to-launch cycle, or run custom packaging scripts with automatic Blender launch.

not rated 5 8mo ago A 56 tokens

q-which-tools

17382

jlong/quiddity

Skill Claude Code

Discover what tools a project uses and save the configuration to .quiddity/tools.json. Pass category names as arguments (e.g., /q-which-tools issues source-control).

not rated 5 6mo ago A 41 tokens original MIT

dungnotnull/mangrove-forest-ai-conservation-agent-skill

Skill Claude CodeCodex

AI-Based Mangrove Forest Monitoring & Conservation — Professional-grade harness for evidence-backed mangrove forest analysis with remote sensing, deforestation detection, health assessment, blue carbon estimation, and restoration planning. Use this skill when users mention mangrove forests, coastal ecosystems…

not rated 5 2mo ago A 118 tokens original MIT

dungnotnull/game-server-stability-optimization-agent-skill

Skill Claude CodeCodex

Dedicated Game Server Stability & Performance Optimization — Expert Game Server Reliability & Performance Engineering analysis harness. Use this skill whenever the user mentions game servers, multiplayer infrastructure, server optimization, dedicated game hosting, cloud gaming architecture, server scaling, load…

not rated 5 2mo ago A 133 tokens original MIT

bityield

17386

ErlebnisW/bityield

Skill Claude CodeCodex

BTC and equity options volatility trading knowledge base, centered on the BitYield strategy framework. Use when the user mentions options, vol surface, skew trading, kurtosis, Risk Reversal, Butterfly, Delta hedging, implied volatility, Vega, Vanna, or asks to analyze/trade options on BTC, NVDA, AAPL, TSLA, META…

not rated 5 5mo ago A 140 tokens

sp-1

17387

dot-Justin/SP-1-knowledgebase-skill

Skill Claude CodeCodex

This skill should be used when the user asks about the Teenage Engineering SP-1 stem player (or "Stem Player SP-01"), the nRF52840-based Kanye/TE collaboration device, custom firmware development for it, custom stems / album encoding, the bootloader trigger ("Track 1 + Track 4"), solderless.engineering, the…

not rated 5 4mo ago A 213 tokens

dungnotnull/indie-artist-brand-development-agent-skill

Skill Claude CodeCodex

This project ships a modular skill-registry agent framework that orchestrates evidence-backed Independent Artist Branding & Creative Marketing analysis. Skills are declared as markdown files (skills/.md) with YAML frontmatter, augmented by a registry manifest (skills/registry.yaml), and executed by a hook-wrapped…

not rated 5 2mo ago A 0 tokens original MIT

accessibility-compliance

17389

on-deck-society/love-stack

Skill Claude Code

Audit a web UI against WCAG 2.2 Level AA accessibility standards. Identify violations and recommend fixes before shipping.

not rated 5 5mo ago A 29 tokens original MIT

powerpoint-business

17392

Noi1r/powerpoint-business

Skill Claude Code

Create visually polished business and humanities PowerPoint presentations using SVG-native generation. LLM generates SVG slides directly (1280x720) — exported as editable SVG-embedded PPTX (Office 365+). 5 specialized agent roles (Consultant → Researcher → Planner → Designer → Reviewer) collaborate through a 8-phase…

not rated 5 6mo ago A 295 tokens

solar-thermal-crop-dryer

17393

dungnotnull/solar-thermal-crop-dryer-agent-skill

Skill Claude CodeCodex

Solar Thermal Crop Dryer Design (Heat-Pump Hybrid) — Production-grade evidence-backed analysis harness for Solar Thermal Crop Drying & Post-Harvest Engineering. Use whenever user asks about solar drying, crop dryer design, heat pump dehumidification, drying kinetics, post-harvest engineering, or agricultural thermal…

not rated 5 2mo ago A 71 tokens

pm-for-aidlc

17394

vishalform/pm-for-aidlc

Skill Claude CodeCodex

Use when doing AI product management on an AI system itself — writing or debugging evals, prompts, agent/RAG/tool design, model selection and routing, the data flywheel, eval-gated shipping, online quality/groundedness/drift monitoring, safety/red-teaming, or inference cost and unit economics. Triggers: AI PM, AIDLC…

not rated 5 3mo ago A 235 tokens original MIT

grug-brain-development

17395

supersterling/grug-brain-dev

Skill Claude CodeCodex

Apply the grug brain philosophy to software development - fight complexity, prefer simplicity, and build maintainable code. Use when the user asks to "simplify this code", "is this too complex", "should I abstract this", "review for over-engineering", "grug brain", "keep it simple", or when reviewing code for…

not rated 5 8mo ago A 89 tokens

babysit-pr

17396

Wibias/github-delivery

Skill Claude CodeCodex

Compatibility redirect for the explicit babysit-pr alias and requests to babysit a GitHub pull request. Routes to github-delivery; not a standalone PR or CI workflow.

not rated 5 changed 2d ago A 39 tokens original MIT

dungnotnull/industrial-waste-heat-recovery-agent-skill

Skill Claude CodeCodex

Industrial Waste-Heat Recovery System Design — Production-grade evidence-backed analysis harness with flexible agent architecture, skill registry, and modular sub-agents. Use for: waste-heat recovery design, heat exchanger selection, ORC systems, pinch analysis, energy efficiency assessment, industrial thermal system…

not rated 5 2mo ago A 113 tokens original MIT

council

17398

tashisleepy/tashi-workstation

Skill Claude CodeCodex

5-advisor war room for high-stakes decisions. Independent analysis → anonymous peer review → chairman verdict with confidence scoring, kill criteria, and decision rules. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this', 'force council'.…

not rated 5 5mo ago A 138 tokens original MIT

njupt-thesis

17399

HenryLiu0405/njupt-thesis-skill

Skill Claude CodeCodex

A Chinese-language workflow assistant for Nanjing University of Posts and Telecommunications graduation theses and projects.

not rated 5 3mo ago A 388 tokens original MIT

paper2slides

17400

inhyeoklee/paper2slides-skill

Skill Claude CodeCodex

Generate a show-ready journal club presentation from a scientific paper PDF using the paper2slides library and agent-driven scientific comprehension.

not rated 5 4mo ago A 28 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: