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.

ui-ux-pro-max

22561

nongjun/awesome-harness-engineering

Skill Claude CodeCodex

Comprehensive design guide for web and mobile applications. Contains 67 styles, 96 color palettes, 57 font pairings, 99 UX guidelines, and 25 chart types across 13 technology stacks. Searchable database with priority-based recommendations.

not rated 2 6mo ago B 0 tokens copy · 86% MIT

obsidian-note-expert

22562

LeoLB-Wang/pensieve-obsidian-skill

Skill Claude CodeCodex

Obsidian Knowledge Architect based on Progressive Summarization. Generates three-layer structure: Index -> Summary -> Detail. Always appends, never overwrites.

not rated 2 7mo ago A 37 tokens original MIT

copilot-customization

22563

navendubrajesh/context-management-for-agents

Skill Claude CodeCodex

Author the files that steer GitHub Copilot — repository copilot-instructions.md, path-scoped .instructions.md with applyTo globs, prompt files, AGENTS.md, and MCP server configuration. Use when writing or restructuring Copilot customization files, when instructions are being ignored, or when instruction bloat degrades…

not rated 2 18d ago A 102 tokens original MIT

work-relax-planner

22564

qiban36/work-relax-skill

Skill Claude CodeCodex

A schedule planner that adds user-chosen sports or leisure activities to a class or work timetable. It asks for a lucky number, uses that number to choose how many activities to enter, and can optionally place activities during class time with a warning.

not rated 2 1mo ago A 186 tokens original MIT

create-skill

22565

TMI-apps/boilerplate-vite-supabase-mui-cursor

Skill Claude CodeCodex

Author or refine a single project skill under .agents/skills/ (draft SKILL.md, optional evals, description triggering). Use when the user runs /create-skill or asks to create, edit, or optimize one skill in this repo. Primary outcome: a durable SKILL.md. Evals/benchmarks are optional phases when the user wants them …

not rated 2 1mo ago A 123 tokens

develop

22566

BrunoBNascimento/devos

Skill Claude CodeCodex

Core coding skill - branch creation, iterative coding, atomic commits.

not rated 2 2mo ago A 14 tokens

tell-truth

22567

boogiefromzk/tell-truth-skill

Skill Claude CodeCodex

Makes AI when answering to stop being a victim of propaganda but apply at least some epistemic discipline and critical thinking.

not rated 2 2mo ago A 27 tokens original MIT

slide-maker

22568

iam-kristie/Slide-Maker

Skill Claude Code

Turn a content brief (.md) into production-ready HTML slides and export as high-resolution PNG or animated MP4. Supports Instagram carousels, stories, PowerPoint, newsletters, posters, and custom dimensions. Use when the user wants to build slides, design a carousel, create a presentation, or says "make slides"…

not rated 2 2mo ago A 76 tokens

jvever-cross-review

22569

JVever/cross-review

Skill Claude CodeCodex

Guidance for having multiple AI models review, discuss, analyze, or design something together. The input does not describe a specific workflow.

not rated 2 2mo ago A 140 tokens GPL-3.0

drive-wps-ppt

22570

thenw-123/CO-WPSppt

Skill Claude CodeCodex

An automation skill for creating and editing presentations in WPS Presentation, a desktop slide-making application, through the WPS automation interface. It also structures project-defense and progress-report content as JSON specifications.

not rated 2 5mo ago A 51 tokens original MIT

dcf-model

22571

wenyu0608/cursor-agents

Skill Claude CodeCodex

Real DCF (Discounted Cash Flow) model creation for equity valuation. Builds comprehensive cash flow projections with proper WACC calculations, performs sensitivity analysis, and outputs professional Excel models via Python/openpyxl. Use when users need to value a company using DCF methodology, request intrinsic value…

not rated 2 2mo ago A 77 tokens

complaint-8d-report

22572

didclawapp-ai/didclaw

Skill Claude CodeCodex

Generates or completes 8D reports (Eight Disciplines) from customer complaint data, with D1–D8 fill-in guidance and a standard template. Supports customer-specific formats (one supplier, multiple customers with different 8D layouts). Use for customer complaints, quality deviations, and defect recurrence prevention.

not rated 2 6mo ago A 70 tokens AGPL-3.0

java-backend-test-ops

22573

LSRabbit6/cursor-genesis

Skill Claude CodeCodex

A set of practices for running Java backend integration tests with Maven, Spring Boot, Testcontainers, Docker Desktop, and MySQL containers. It covers container resource issues, Spring Boot null-safety rules, and changes to shared test base classes.

not rated 2 5d ago A 147 tokens

gh-pr-handling

22574

martin-janci/autopilot

Skill Claude Code

Expert GitHub CLI and PR handling. Use when working with pull requests, GitHub issues, reviews, CI checks, or any gh command operations.

not rated 2 9mo ago A 35 tokens original MIT

snowgram-agent

22575

sfc-gh-abannerjee/SnowGram

Skill Claude CodeCodex

Manage and optimize the SnowGram Cortex Agent for architecture diagram generation. Use when: debugging agent responses, updating agent configuration, adding new components, testing diagram generation, or optimizing the dynamic component system. Triggers: snowgram, diagram agent, component mapping, agent spec, suggest…

not rated 2 24d ago A 60 tokens original MIT

using-docshark

22576

Michael-Obele/docshark

Skill Claude CodeCodex

Use when installing, running, and troubleshooting DocShark as an MCP server, including client setup for STDIO mode and endpoint checks for HTTP mode.

not rated 2 changed 12d ago A 35 tokens original MIT

implement-plan

22577

Joaonic/agentkit

Skill Claude Code

Implementar um plano existente com execução obrigatória e sequencial por subagents.

not rated 2 4mo ago A 19 tokens original MIT

humanizer

22578

ankshvayt/humanizer

Skill Claude CodeCodex

You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.

not rated 2 7mo ago A 0 tokens

flitt-integration-skill

22579

flittpayments/flitt-integration-skill

Skill Claude CodeCodex

Use when implementing, reviewing, debugging, testing, or documenting Flitt payment integrations, including hosted checkout, direct API payments, webhooks, callbacks, signatures, Apple Pay, Google Pay, recurring payments, subscriptions, reversals, reports, SDK usage, and failed payment analysis.

not rated 2 4mo ago A 63 tokens

api-analyzer

22580

Nuggets1024/api-analyzer

Skill Claude CodeCodex

A backend API investigation skill that maps interfaces, traces individual request paths, and diagnoses server errors. It applies to common frameworks such as Spring, Express, FastAPI, and Gin.

not rated 2 5mo ago A 53 tokens original MIT

sc:search

22581

belarusrulez/skill-core

Skill Claude Code

Search across all registered skill repos for a skill that matches the user's intent. Use when the user asks "do I have a skill for X", "which skill does Y", "find a skill that …", "is there a skill to …", "list my skills", or any "find/locate/search for a skill" phrasing. The script takes THREE positional queries…

not rated 2 4mo ago A 126 tokens

qdoc

22582

ibrhr/qdoc

Skill Claude CodeCodex

Query documentation using an LLM. Search Go docs, FastAPI docs, React, Next.js or local markdown directories. USE FOR: "how do I use X in Go?", "show me the FastAPI docs for Y", "what does the docs say about Z?", library docs, framework docs, API reference. DO NOT USE FOR: general coding questions not tied to specific…

not rated 2 1mo ago C 91 tokens original MIT

ai-workflow-optimizer

22583

BANG644/ai-workflow-optimizer

Skill Claude CodeCodex

A workflow guide for improving how AI coding agents work on software projects. It covers project setup, prompts, tools, tests, review, memory, and release processes.

not rated 2 5mo ago A 88 tokens original MIT

mentor-dev

22584

Nalberthdev/mentordev

Skill Claude CodeCodex

Postura de mentor sênior calibrada pelo nível (júnior, pleno ou sênior) e pela área (front, back ou fullstack) que a pessoa declara. Ensina a LER código linha a linha, traduz todo conceito abstrato em comparação do mundo real, exige justificativa de toda decisão, recusa resposta vaga e não entrega resposta pronta.…

not rated 2 1mo ago A 133 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: