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.

ai-native

17545

initxy/ai-native

Skill Claude CodeCodex

Turn a repo into an AI-native project — lay down AGENTS.md, standard verbs, gates, and the spec directory. Works on new and existing repos.

not rated 5 1mo ago A 35 tokens original MIT

gpt-pro-audit

17546

hubeiqiao/gpt-pro-audit

Skill Claude CodeCodex

Use when the user asks to audit a plan, document, diff, website finding, or implementation proposal with ChatGPT using Pro reasoning effort through Chrome - starts automatically after invocation, packages codebase/project context ChatGPT cannot see, runs up to 5 review rounds until accepted, verifies Effort Pro and…

not rated 5 1mo ago A 75 tokens original MIT

synthkernel

17547

hesprs/synthkernel

Skill Claude CodeCodex

Follow the standards of SynthKernel architecture. Must use this skill when operating on any project that claims to adopt SynthKernel.

not rated 5 1mo ago A 28 tokens CC-BY-4.0

shipmate

17548

lucasheriques/shipmate

Skill Claude CodeCodex

The full-lifecycle framework for building products people pay for - routes any product/business situation to the right stage and skill, and maintains persistent venture memory across sessions. Use when someone has a new product or business idea and asks where to start, when revenue or growth is stuck and the cause is…

not rated 5 2mo ago A 140 tokens original MIT

uikit-expert

17549

zinxj/uikit-expert-skill

Skill Claude CodeCodex

Write, review, or improve UIKit code following best practices for view controller lifecycle, Auto Layout, collection views, navigation, animation, memory management, and modern iOS 18–26 APIs. Use when building new UIKit features, refactoring existing views or view controllers, reviewing code quality, adopting modern…

not rated 5 3d ago A 95 tokens original MIT

goodcode

17550

SpinaBuilds/goodcode

Skill Claude CodeCodex

Host-agnostic exhaustive multi-agent orchestration for any coding agent that can spawn subagents (Claude Code, Codex, Cursor, OpenCode, OpenHands, …). Pipeline: recon → cheap baseline → a-priori specialist roles cast by routing → parallel fan-out → adversarial verification → loop-until-dry → dedup/score/synthesize.…

not rated 5 3mo ago A 158 tokens original MIT

website-icp-fit

17551

wavect/ai-skills

Skill Claude CodeCodex

You are a conversion strategist and ICP-fit auditor. You evaluate a website — either by visiting its URL or by reading its source code — to determine whether the copy, structure, messaging, and psychology are correctly aligned with the stated Ideal Customer Profile and their specific awareness stage.

not rated 5 +1 4mo ago A 5 tokens original MIT

analyze-paper

17552

wanng-ide/open-paper-analysis

Skill Codex

Analyze a single research paper deeply and create or update evidence-grounded professional notes in Markdown, Notion, or Feishu/Lark. Use when the user asks to read, analyze, explain, summarize, interpret, or take notes on a paper, or supplies an arXiv link, PDF, DOI, title, project page, code repository, existing…

not rated 5 1mo ago A 116 tokens original Apache-2.0

rough-cut-wiki-video

17553

yinbaozong/rough-cut-wiki-video

Skill Codex

Create editable rough cuts for any step-by-step tutorial from MP4/MOV footage plus pasted procedure text or a text/Markdown guide. Use for how-to videos, assembly or repair, crafts, cooking, product demonstrations, workplace procedures, training, unboxing, speech-cue trimming, filename ordering, procedure-grounded…

not rated 5 1mo ago A 107 tokens original MIT

dsh-creator

17554

KiWi233333/dsh-creator

Skill Codex

Create and validate extensions for DeepSeek Harness (dsh), including Cordis plugin bundles, model-facing tools, LLM adapters, native or compatibility hooks, Agent Skills, MCP connections, Web conversation nodes, protocol drivers, and profile/bundle/patch configuration. Use when designing, scaffolding, packaging…

not rated 5 1mo ago A 87 tokens original MIT

web3-bug-classes

17555

Olaradiallysymmetrical491/web3-bug-bounty-hunting-ai-skills

Skill Claude CodeCodex

Complete reference for all 10 DeFi smart contract bug classes. Use this when hunting for specific vulnerability types, need attack patterns for accounting desync, access control, incomplete path, off-by-one, oracle manipulation, ERC4626 vaults, reentrancy, flash loans, signature replay, or proxy/upgrade bugs.

not rated 5 yesterday A 72 tokens copy · 100% MIT

video-to-skill

17556

brenoepics/video-to-skill

Skill Claude CodeCodex

Convert a video (local file or YouTube/URL) into structured, evidence-grounded knowledge — and ultimately into an installable agent skill. Use when the user provides a video file or video URL and wants it analyzed, summarized into steps, or turned into a skill; triggers include "watch this video", "learn from this…

not rated 5 20d ago D 102 tokens original MIT

build-support-agent

17557

DefaultHQ/build-support-agent-skill

Skill Claude Code

Plan and build a production customer-support agent — a RAG product-Q&A bot that drafts replies, posts them for human review, and graduates to controlled autonomy. Use when someone wants to build an in-house support agent, a Slack-native or support-platform AI bot, a ticket-answering / customer-Q&A agent, or wants to…

not rated 5 4mo ago A 123 tokens original MIT

sam6dvpte34/lead-generation-skill

Skill Claude CodeCodex

Collect accounting firm leads from Google Maps — business name, address, phone, website, rating. Use when the user wants to prospect local accounting firms or build a B2B contact list.

not rated 5 changed 14d ago A 48 tokens

database-normalization

17560

cookieMonsterDev/agents-skills

Skill Claude CodeCodex

Explains and applies the database normal forms (1NF, 2NF, 3NF, BCNF, 4NF, 5NF) and strategic denormalization, with worked examples in PostgreSQL, MySQL, SQLite, MongoDB, Cassandra, ScyllaDB, and DynamoDB. Use when users ask about normal forms, functional/multivalued/join dependencies, anomalies…

not rated 5 1mo ago A 153 tokens original MIT

pickaxe

17561

ThomasUmstattd/pickaxe-skill

Skill Claude CodeCodex

Use for any task that touches the Pickaxe.co AI-tool platform (Pickaxe Studio), even when the MCP connection is already set up and the task looks like a one-line edit, because writes can silently fail and every prompt edit hits the live bot immediately. Covers building, editing, and configuring Pickaxes (prompts…

not rated 5 changed 10d ago A 208 tokens original MIT

placeholder-skill

17562

TechSpokes/skill-base-template

Skill Claude CodeCodex

Build a real agent skill from user-provided intake material. Use this placeholder only while the repository is still in bootstrap mode and before an agent has generated the final skill package.

not rated 5 2mo ago A 39 tokens original MIT

generate

17563

AntonioCardenas/generate-nanobanana

Skill Claude CodeCodex

Generate images and videos using Google's Gemini media models (Nano Banana 2 Lite, Nano Banana 2, Nano Banana Pro, Gemini Omni Flash) via the Gemini API. Use this whenever the user asks to generate, create, or make an image or video, wants a thumbnail, wants to animate a still image, says "generate on brand" or…

not rated 5 1mo ago A 133 tokens

drata-cli-workflow

17564

ethanolivertroy/drata-cli

Skill Claude CodeCodex

Use when querying or changing Drata/GRC data through the drata CLI, including compliance status, frameworks, certificates, Trust Center documents, controls, monitoring tests, evidence, risks, vendors, policies, personnel compliance, and background-check questions. Prefer versionless CLI commands, JSON output…

not rated 5 5mo ago A 83 tokens original MIT

renwei

17565

dbhosbu-dotcom/renwei

Skill Claude Code

Renwei (人味) — book-length Chinese de-AI editor. Use when editing, polishing, or de-AI-ing Chinese manuscripts, chapters, or articles (.md, .txt), or when the user says their text reads like AI, sounds translated, or feels fake. 51 rules across AI tells, Euro-Chinese syntax, grammar defects, chapter rhythm, whole-book…

not rated 5 1mo ago A 129 tokens

persona-ux-test

17566

Ericwong5021/persona-ux-test

Skill Codex

Run an isolated persona-based UX test through the real desktop or browser UI. Creates a precise non-developer user persona, gives the tester only an approved product introduction, prevents source-code and design-document leakage, and produces an evidence-based Chinese evaluation report. Use when the user asks for…

not rated 5 2mo ago A 106 tokens original MIT

tradingagents-codex

17567

wenyupapa-sys/tradingagents-codex-skill

Skill Claude CodeCodex

Run the local TradingAgents Codex fork for multi-agent stock and ETF research. Use when the user asks to analyze tickers with TradingAgents, run codex-analyze, batch stock/ETF research, summarize TradingAgents reports, validate the TradingAgents Codex setup, or turn QQQ/TSLA-style full-chain analysis into a repeatable…

not rated 5 4mo ago A 78 tokens original MIT

ta-style-dialogue

17568

Wholiver/Ta.Skill

Skill Claude CodeCodex

An automatic role-playing conversation mode that copies a person's writing style from supplied chat samples and personal details. It is intended for conversations involving a close relationship.

not rated 5 4mo ago A 185 tokens

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: