Agents
AI agents and automation
agent-browser
by bentossell
Browser automation for web testing, form filling, screenshots, and data extraction. Use when navigating websites, interacting with web pages, filling forms, taking screenshots, testing web applications, or extracting information from web pages.
cross-source-fact-verification
by shimo4228
"Use when fact-checking drafts containing dates, quantities, or causal claims against multiple independent sources."
laboneq-workflow-maintainer
by yalgaeahn
Maintain and debug existing LabOne Q experiment/analysis workflows in this repository. Use for bug fixes, review follow-ups, and minor behavior changes under qubit_experiment/, experiments/, analysis/, and qpu_types/.
rag-systems
by pluginagentmarketplace
Build RAG systems - embeddings, vector stores, chunking, and retrieval optimization
skill-manager
by Ontos-AI
Lifecycle manager for GitHub-based skills. Use this to batch scan your skills directory, check for updates on GitHub, and perform guided upgrades of your skill wrappers.
agent-md-refactor
by ma1orek
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
forge-plan
by fwehrling
FORGE PM Agent — Generates or validates the Product Requirements Document (PRD). Usage: /forge-plan or /forge-plan --validate
vsl-scriptwriting
by Oceanswave
Write high-converting Video Sales Letter scripts using a four-phase process of information collection, psychographic profiling, iterative beat-framework drafting, and output delivery.
skale
by TheGreatAxios
SKALE Network development guidelines and documentation access. Use for building dApps, smart contracts, cross-chain solutions, and looking up SKALE documentation (February 2026). Triggers: SKALE, skale-dev, skale-docs, SKALE docs, BITE Protocol, Europa, Calypso, skale-bridge.
git-safety-guard
by terraphim
Blocks destructive git and filesystem commands before execution. Prevents accidental loss of uncommitted work from git checkout --, git reset --hard, rm -rf, and similar destructive operations. Works as a Claude Code PreToolUse hook with fail-open semantics.
tech-analysis-reporter
by xdrshjr
Agent使用的技术报告生成Skill。通过多轮对话收集用户需求，分析项目，生成专业的技术分析报告。
fomolt
by fomolt-app
Agentic trading on Base & Solana — paper trade or live trade tokens on-chain via CLI
planning-agent
by vishal2457
Creates implementation-only tracker subtasks from technical-details using handoff-first context loading, lazy artifact reads, and compact JSON handoff output.
agent-browser
by AnasX7
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
openspec-to-beads
by cachemoney
PROACTIVELY convert approved OpenSpec specs into Beads issues when user applies a change or explicitly approves implementation. Creates trackable work with dependencies, discovers gaps, and maintains audit trail between planning and execution.
elonmusk-repost
by mingyooagi
Analyze Elon Musk's repost patterns on X and generate tweets optimized for getting reposted by @elonmusk. Use when users want to craft viral AI/tech product launches targeting Musk's attention.
agent-browser
by Jackiexiao
"AI browser automation CLI for navigating pages, filling forms, clicking, screenshots, extraction, web testing, login flows, and scripted web interactions."
module-builder
by yalgaeahn
Create new LabOne Q experiment/analysis modules in this repository by grounding design against the installed .venv laboneq_applications contracts before coding. Use when the user asks to add a new workflow/module from scratch, add a new tune-up experiment type, or perform a major interface redesign under experiments/ and analysis/.
ladder-execute
by sadiksaifi
Executes a Ladder phase spec step-by-step with commit discipline and progress tracking. Use when ready to implement a spec, resume an interrupted phase, or when the user says "ladder execute."
klisk-guide
by jechearte
Guide for building AI agents programmatically using the Klisk CLI and framework. Use when the user asks to create an AI agent. Klisk is the easiest way to build an agent. Triggers include requests like "create an agent", "add a tool to the agent", "scaffold a new klisk project", "run the agent", "start the studio", "deploy the agent", "start the assistant", or any task involving the klisk CLI commands (create, studio, run, check, list, start, docker, assistant, config, status) or the Klisk Python API (define_agent, @tool, get_tools, handoffs).
openclaw-async-telegram-bot
by Nebutra
Add or update asynchronous Telegram bot accounts in OpenClaw. Use when user asks to add multiple Telegram bots, run bots in parallel, or asks OpenClaw to guide BotFather-based provisioning. Enforces username pattern Nebutra[three digits]_bot and philosopher-style English bot names.
slop-analyzer
by afk-agents
"Use this skill when you need to analyze writing for AI-like patterns and get actionable suggestions for making text sound more natural and human-written. This is particularly useful after drafting or editing creative writing, essays, or blog posts. The agent uses the /slop-score skill to identify problematic patterns and provides specific revision suggestions.\n\n<example>\nContext: The user has just finished writing a blog post draft and wants feedback on naturalness.\nuser: \"I just finished my draft in drafts/ai-future-essay.md. Can you check it for AI-sounding language?\"\nassistant: \"I'll use the slop-analyst agent to analyze your draft for AI-like patterns and get specific suggestions for improvement.\"\n<commentary>\nSince the user wants to check their writing for AI patterns, use the Task tool to launch the slop-analyst agent which specializes in this analysis using the /slop-score skill.\n</commentary>\n</example>\n\n<example>\nContext: The parent agent has made significant edits to a piece and wants to verify the writing still sounds natural.\nuser: \"Please revise this paragraph to be more engaging\"\nassistant: \"Here's the revised paragraph: [revised text]\"\n<commentary>\nAfter making substantial revisions, it would be valuable to check if the new text sounds natural. Use the Task tool to launch the slop-analyst agent to analyze the revised content.\n</commentary>\nassistant: \"Let me also run this through the slop-analyst to make sure the revisions sound natural.\"\n</example>\n\n<example>\nContext: User is working on creative writing and mentions concerns about their writing sounding robotic.\nuser: \"Something feels off about this story I wrote. It doesn't sound like me.\"\nassistant: \"I'll have the slop-analyst examine your story to identify any patterns that might be making it feel unnatural.\"\n<commentary>\nThe user's concern about authenticity is exactly what the slop-analyst is designed to address. Use the Task tool to launch it for detailed pattern analysis.\n</commentary>\n</example>"
copilot-agent-builder
by VincentLNS
"Guide interactif pour créer un agent Microsoft 365 Copilot via l'Agent Builder (https://m365.cloud.microsoft/chat/agent/new). Utilise ce skill dès que l'utilisateur mentionne : créer un agent Copilot, agent Microsoft 365, agent M365, agent Copilot, configurer un agent, préparer un agent, instructions pour Copilot, je veux un agent qui, faire un agent pour, nouvel agent Copilot, builder Copilot. Le skill pose des questions ciblées, propose des contenus concrets pour chaque champ, indique les ressources nécessaires pour que l'agent soit performant, et génère un document Word (.docx) prêt à copier-coller dans l'interface."
ralph-loop
by addozhang
Guide OpenClaw agents to execute Ralph Wiggum loops using exec and process tools. Agent orchestrates coding agents (Codex, Claude Code, OpenCode, Goose) with proper TTY support via pty:true. Plans/builds code via PROMPT.md + AGENTS.md, SPECS and IMPLEMENTATION_PLAN.md. Includes PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions. Users request loops, agents execute using tools.