Packages
619 resultsthesis-figure-skill
A Claude Skill that converts pasted thesis/paper text or uploaded images into publication-ready diagrams, primarily generating LaTeX/TikZ code or draw.io XML. It claims to run compile/visual checks and iterate until a scored quality target is met.
antigravity-awesome-skills
Antigravity Awesome Skills is an installable GitHub library/installer CLI that places reusable SKILL.md agent playbooks into directories for various AI coding assistants (e.g., Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and others). It also provides curated bundles and ordered workflows/playbooks plus installer metadata for plugin marketplace-style distributions where supported.
theHarvester
theHarvester is an OSINT reconnaissance tool that gathers externally visible information about a target domain, including names, emails, IPs, subdomains, and URLs by querying multiple public resources (passive modules) and optionally running active enumeration and screenshots.
verify
A Claude Code plugin (“opslane-verify”) that performs spec-driven verification: it interprets an acceptance-spec document, extracts acceptance criteria, runs one browser automation agent per criterion (Playwright) against a local dev server, then a judge step reviews screenshots/traces to produce pass/fail results with evidence (screenshots and session recordings).
Agentic-SEO-Skill
An LLM-first, agentic SEO analysis skill for Antigravity, Claude Code, and Codex. It orchestrates multiple specialist sub-skills (technical SEO, content/E-E-A-T, performance/CWV, schema, sitemap, visual checks, links, GEO/AEO, entity SEO, hreflang, programmatic safeguards, plus GitHub repo SEO/benchmarking) to collect evidence from target URLs (and optionally run verification scripts) and generate structured audit outputs and prioritized action plans.
CordysCRM
Cordys CRM is an open-source, self-hosted CRM system that manages the full sales lifecycle (leads to cash) including accounts/contacts, opportunities, contracts, and payments/collection workflows. It also advertises integration points (open API/standard interfaces, BI via DataEase) and AI/agent enablement via a “CRM Skills” interface.
awesome-openclaw-agents
awesome-openclaw-agents is a curated collection of copy-paste ready OpenClaw agent templates (SOUL.md configurations) plus a quickstart and machine-readable agent listing (agents.json). It also references an MCP servers section and an external deployment/creation flow via CrewClaw, but the provided README content does not include concrete API/MCP technical specifications for the repository itself.
OpenManus-RL
OpenManus-RL is a Python-based RL tuning/finetuning codebase for agentic LLM systems, paired with an OpenManus-RL dataset of agent trajectories. It positions Verl (Volcano Engine Reinforcement Learning) as the primary RL training framework (e.g., PPO/DPO/custom reward modeling) and includes environment setup scripts for benchmarks such as WebShop and ALFWorld.
playwright-bot-bypass
playwright-bot-bypass is positioned as an automation skill that uses stealth browser variants (rebrowser-playwright / undetected-chromedriver) and example scripts/templates to reduce detection signals (e.g., removing webdriver exposure) to make web automation and scraping more likely to work without CAPTCHA/login.
stable-audio-tools
Provides training and inference code (primarily Python/PyTorch + PyTorch Lightning) for conditional audio generation models, including a Gradio-based demo runner for loading Hugging Face pretrained checkpoints and running local training scripts driven by JSON config files.
claude-code_rails-upgrade-skill
Provides a Claude Code skill that assists with upgrading Ruby on Rails applications between versions by generating detection scripts, upgrade reports (with code examples), and previews of `rails app:update` configuration changes, using a sequential (no-skips) upgrade strategy and advising a dual-boot approach.
h8mail
h8mail is a Python CLI tool for email OSINT and “breach hunting” style lookup. It matches email patterns from inputs/files/URLs, searches local breach datasets (e.g., BreachCompilation / Collection1-style dumps), and can query multiple third-party breach/recon services (including HaveIBeenPwned and others) for related emails, cleartext credentials, and/or password/hash intelligence depending on the provider and API keys.
marketing-skill-pack
A one-command installer for an “AI Marketing Hub” suite: clones/updates several Claude Code-related repos, installs their skills, and downloads a WordPress plugin (WP MCP Ultimate) for MCP-based WordPress abilities.
prompt-architect
CLI/Agent Skills-compatible tool that transforms vague prompts into structured, expert-level prompts using a set of research-backed prompt frameworks, optionally asking clarifying questions and iteratively refining with before/after comparisons.
awesome-agent-skills
awesome-agent-skills is a curated directory/repository of “Agent Skills” resources, tutorials, and pointers to many skill projects and ecosystems (e.g., Claude/ChatGPT skill usage patterns and third-party skill stores/harnesses). It describes a standard on-disk structure for skills (SKILL.md with optional references/scripts/assets) and provides guidance for discovering/adding/updating skills via CLI tools for different environments.
buyer-eval-skill
A free open-source Claude skill that evaluates B2B software vendors by prompting for buyer context, conducting domain-expert question exchanges, optionally engaging vendor AI agents via the Salespeak Frontdoor API, cross-referencing claims against independent sources, and producing a comparative, evidence-tagged scorecard plus risk analysis and demo-prep questions.
Continuous-Claude-v3
Continuous Claude is a local Python-based “Claude Code” extension that aims to provide persistent, token-efficient context across sessions using a memory system, continuity/ledger handoffs (YAML), and multiple specialized agents and skills. It also claims to reduce token usage via TLDR multi-layer code analysis and indexing, and to improve code-quality via shift-left validation (e.g., ruff/pyright) after edits.
OpenClaw-Medical-Skills
OpenClaw Medical Skills is an open-source collection of 869 “skills” (each a self-contained SKILL.md module under a skills/ directory) that extend OpenClaw/NanoClaw Claude-based agent workflows for biomedical and clinical research tasks. It primarily operates as a local plugin/skills library (copy/sparse-checkout) rather than a standalone API service.
rt-claw
RT-Claw is an OpenClaw-inspired intelligent assistant for embedded devices. It provides an AI chat engine that calls an LLM over HTTP, supports tool-use via function calling (30+ built-in tools), and includes a framework for skills, memory (RAM + persistent NVS/flash), swarm-style node discovery/remote tool invocation, scheduled tasks, and a UART chat-first shell with /commands. It is designed to run across multiple OSAL targets (FreeRTOS, RT-Thread, Linux) and includes networking components (HTTP client, Ethernet/WiFi).
drozer
drozer is an open-source Android security testing framework that lets a user interact with a connected Android device/emulator by assuming the role of an app. It can enumerate and probe app components and IPC endpoints, execute modules, and install/run a drozer agent on the device (typically via adb).