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.

deep-interview

770

Yeachan-Heo/gajae-code

Skill Claude Code

Socratic deep interview with mathematical ambiguity gating before explicit execution approval.

not rated 2.7k +41 changed yesterday A 16 tokens original MIT

action-creator

771

anthropics/claude-agent-sdk-demos

Skill Claude Code ✓ vendor

Creates user-specific one-click action templates that execute email operations when clicked in the chat interface. Use when user wants reusable actions for their specific workflows (send payment reminder to ACME Corp, forward bugs to engineering, archive old newsletters from specific sources).

not rated 2.7k +1 10d ago A 53 tokens

NVIDIA-NeMo/Switchyard

Skill Claude Code needs its repo

Deep dive on Harbor trial results for tasks that use SWE-Bench-style F2P (FAILTOPASS) and P2P (PASSTOPASS) reference tests. Diagnoses why an agent failed and audits whether a failing task is genuinely hard or unfair (instruction-vs-verifier mismatch). Use when the user asks to analyze, debug, investigate, or deep dive…

not rated 2.7k +76 today A 238 tokens original Apache-2.0

cy-spec-peer-review

773

compozy/compozy

Skill Claude Code

Run a requested external review of an approved Compozy spec; continue follow-ups in the same reviewer session and incorporate only user-selected findings. Excludes product drafts, automatic gates, code reviews, and review loops.

not rated 2.7k +22 changed yesterday A 48 tokens original MIT

validation-scoring

774

visa/visa-vulnerability-agentic-harness

Skill Claude CodeCodex

Apply the s11 fix-validation scoring matrix, adversarial-review rules, and structured-output contract when validating remediated findings.

not rated 2.7k +35 changed yesterday A 29 tokens

agent-knowledge

775

vectorize-io/self-driving-agents

Skill Claude CodeCodex

Your long-term knowledge pages. Read them at session start. Create new pages when you learn something worth remembering across sessions. Pages auto-update from your conversations via Hindsight.

not rated 2.7k +10 11d ago A 38 tokens

tirith

776

sheeki03/tirith

Skill Claude CodeCodex

Terminal security analysis for shell environments. This skill should be used when checking commands for supply-chain attacks before execution, scanning repositories for hidden content or config poisoning, scoring URLs for homograph attacks, setting up AI tool protection, inspecting Python package artifacts, governing…

not rated 2.7k +6 changed 4d ago B 205 tokens AGPL-3.0

browser-use

777

wanikua/danghuangshang

Skill Claude Code

Automates browser interactions for social media management across Instagram, LinkedIn, and X. Handles posting, DMs, connection requests, lead scraping, and monitoring. Use when the user needs to navigate, interact with, or extract data from approved websites.

not rated 2.7k +1 3mo ago A 53 tokens original MIT

huangwb8/ChineseResearchLaTeX

Skill Claude CodeCodex needs its repo

A workflow for producing a systematic literature review, which is a structured summary of research found through a defined search and selection process.

not rated 2.7k +16 changed yesterday A 127 tokens original MIT

nteract/semiotic

Skill Claude CodeCodex

Inspect a ChatGPT Apps MCP server codebase and generate chatgpt-app-submission.json with app info suggestions, tool hint justifications, test cases, and negative test cases, then report review-check findings and outputSchema warnings for submission review.

not rated 2.7k +1 today A 56 tokens original Apache-2.0

agentic

780

bergside/awesome-design-skills

Skill Claude CodeCodex

Conversational AI-first interface with minimal controls, clear outcomes, and delegated task flows for agentic workflows.

not rated 2.7k +75 2mo ago A 24 tokens original MIT

verify

781

zenbu-labs/terminal-browser

Skill Claude Code

Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.

not rated 2.7k +194 yesterday A 37 tokens original MIT

paper2poster

782

microsoft/ResearchStudio

Skill Claude Code needs its repo ✓ vendor

Render a pre-extracted paper's structured 9-section spec (paperspec.md) into a single-page HTML academic poster, fit the layout to the page via an iterative measured-fill loop, and export it to print-ready PDF + PNG thumbnail. Requires the upstream paper2assets skill to have produced an output bundle with…

not rated 2.7k +69 yesterday A 165 tokens original MIT

EdgarTools

783

dgunning/edgartools

Skill Claude CodeCodex

Query and analyze SEC filings using EdgarTools.

not rated 2.7k +27 today A 12 tokens original MIT

thesvg

784

glincker/thesvg

Skill Claude CodeCodex

Fetch brand SVG logos and cloud architecture icons (AWS, Azure, GCP) from theSVG. Use when the user asks for a brand logo, company icon, framework mark, service icon, or any "icon/logo for X" where X is a real brand or cloud service. Returns ready-to-use CDN URLs or raw SVG markup.

not rated 2.7k +20 4d ago A 72 tokens original MIT

uncodixfy

785

cyxzdev/Uncodixfy

Skill Claude CodeCodex

Prevents generic AI/Codex UI patterns when generating frontend code. Use this skill whenever generating HTML, CSS, React, Vue, Svelte, or any frontend UI code to enforce clean, human-designed aesthetics inspired by Linear, Raycast, Stripe, and GitHub instead of typical AI-generated UI.

not rated 2.7k +5 5mo ago A 66 tokens original MIT

architecture-audit

786

org2AI/ORG2

Skill Claude CodeCodex

Systematic architecture audit and refactoring methodology for Rust + TypeScript codebases. Use when performing refactoring, cleanup, unification, code review, dead code removal, module reorganization, or tech debt elimination. Ensures no naming confusion, semantic overloading, hidden defaults, duplicate logic, or…

not rated 2.6k today A 70 tokens AGPL-3.0

slides

787

gridaco/grida

Skill Claude CodeCodex

Build a Grida slides deck — a .canvas bundle in slides mode whose pages are SVG documents (16:9, one SVG per slide). Use when creating a presentation, pitch deck, slideshow, or talk.

not rated 2.6k +4 yesterday A 46 tokens original Apache-2.0

sap-extension-creator

788

heshengtao/super-agent-party

Skill Claude CodeCodex

Create Super Agent Party (SAP) extensions. This skill should be used when users want to create, build, or scaffold a new extension for Super Agent Party - including static HTML extensions (pure frontend) and Node.js backend extensions. Triggers on requests like "create a new SAP extension", "build an extension for…

not rated 2.6k +5 14d ago A 93 tokens AGPL-3.0

papersgpt-for-zotero

789

papersgpt/papersgpt-for-zotero

Skill Claude CodeCodex

A privacy-first, local-first search assistant and MCP server for your Zotero library, enabling AI agents to search and analyze your research papers securely.

not rated 2.6k +4 6d ago A 37 tokens AGPL-3.0

ai-image-creator

790

centminmod/my-claude-code-setup

Skill Claude Code

Generate, edit-from-reference, or analyze images with AI via OpenRouter (gemini, geminipro, riverflow, flux2, seedream, gpt5, gpt5.4; Cloudflare AI Gateway BYOK). Also analyze a video (--analyze-video, read-only — no video generated) into a text description for video prompts. Use when the user asks to generate an…

not rated 2.6k +10 4d ago A 136 tokens original MIT

runkids/skillshare

Skill Claude Code needs its repo

Skillshare frontend design system for the React dashboard (ui/) and Docusaurus website (website/). Use this skill whenever you: build or modify a dashboard page or component in ui/src/, style or layout website pages or custom CSS in website/, create new React components for the dashboard, add pages to the dashboard…

not rated 2.6k +16 yesterday A 147 tokens original MIT

dg-piagent

792

buchidonggua/dg-ai-notes

Skill Claude CodeCodex

A development guide for the pi-agent software kit, used to build and customize coding agents. It covers agents, tools, prompts, sessions, models, authentication, and connected files.

not rated 2.6k +125 14d ago A 205 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: