agentsclimarketplace

Context & AI engineering

25,991 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Integrate hookmyapp

    hookmyapp/agent-skills/skills/integrate-hookmyapp Skill

    1★ repo

    Agent skills for WhatsApp integration with HookMyApp. Install: npx skills add hookmyapp/agent-skills

  • Skill creator anthropics 20260226

    MatrixFounder/Universal-skills/archive/skill-creator-anthropics-20260226 Skill

    1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 7 other repositories

  • Deepagents cli

    Gitmaxd/deepagents-cli-droid-skill/templates/skills/deepagents-cli Skill

    1★ repo

    Deep Agents CLI — the LangGraph-based terminal coding agent. Use this skill whenever the user mentions deepagents, deep agents, the deep agents CLI, terminal coding agent, LangGraph agent, or asks about agent memory, agent skills, AGENTS.md, coding assistants in the terminal, or building scripted/CI agent workflows. Covers: interactive and non-interactive sessions, 20+ LLM providers, model configuration, skills, persistent memory, sandboxed execution, subagents, streaming, and the Agent Client Protocol.

    The same file is in 3 other repositories

  • Kiakun skills

    kiakun-collab/kiakun-skills Skill

    no license1★

    Kiakun 的 AI Agent Skills 集合。包含小红书自动化、B站视频总结、文件夹向量化知识库、中文优先对话、Claude Code 第三方 API 配置、GPT Image 2 异步容错 API 生图、图片型 PPT 可编辑复刻、PPT 重构工作流、游戏 UI 资产流水线、玩家互动设计、纯净交付守卫与客户交付物终稿净化。 当用户要求操作小红书、总结 B站视频、整理文件夹为知识库、默认使用简体中文回复、通过 CC Switch 配置 Claude Code API、通过 GPT Image API 生成或编辑图片、将图片/截图型 PPT 复刻为可编辑 PPTX、按参考图或用户修改稿执行分模式 PPT 重构与 QA、生成/切片/验证/导入 Godot 游戏 UI 资产、审查游戏 UI/玩法互动/引导/失败恢复/挑战链路的玩家体验,要求通用防元信息泄漏的"纯净交付",或要求把客户业务材料净化为保真、可直接交付的终稿时触发。

  • Convert tacit to skill

    11Yuxuanyang/polanyi-stack/skills/convert-tacit-to-skill Skill

    1★ repo

    Convert tacit knowledge into a reusable agent or Codex skill by extracting cues, scoping the task, defining boundaries, and packaging the workflow into SKILL.md plus tests. Use when the user wants a fixed agent, reusable skill, or repeatable copilot based on expert judgment.

    The same file is in 1 other repository

  • Openclaw

    Digidai/mails-skills/skills/openclaw Skill

    1★ repo

    Complete service registrations autonomously by receiving verification codes. Also: send and receive emails, monitor inbox, search by keyword, download attachments, view threads, filter by label, extract structured data, manage mailbox and webhooks.

  • Skills Paper summary

    ch040602/Skills_Paper-summary Skill

    no license1★

    Resolve a paper from title, DOI, paper page URL, or direct PDF URL; fetch available source text; use the latest available frontier subagents for deep method and experiment analysis; then save a comprehensive Korean Markdown summary.

  • Fastmcp mcp builder

    allenli178/yuyan-skills/fastmcp-mcp-builder Skill

    1★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers using FastMCP, the Pythonic MCP framework. Use when building MCP servers to integrate external APIs or services with tools, resources, and prompts using FastMCP decorators. Includes advanced features like structured outputs, tag-based filtering, dependency injection, custom routes, and CLI development workflows.

  • Memory skill

    suibianqugenichenghaole/memory-skill-system/skills/memory-skill Skill

    1★ repo

    Use when work requires recalling, continuing, classifying, or updating memory across ongoing formal work, personal projects, or reusable methods. Helps route memory by permission, domain, anchor, and type while preventing unsafe context mixing.

  • Memory audit

    andreijirohdev-labs/gen-ai-labs/skills/memory-audit Skill

    1★ repo

    Runs Andrei's cross-project memory/backlog audit — reconciling dev work (GitLab.com projects, Alpine Linux aports on gitlab.alpinelinux.org, GitHub), Leaflet.pub blog drafts, Obsidian notes, and Google Drive into a single status report + prioritized action list. Trigger this whenever Andrei explicitly says "run memory audit" (or close variants like "audit my backlog", "memory check-in"), whenever a monthly or quarterly check-in is due or requested, and whenever Andrei mentions specific tracked projects or drafts by name (nixops-config, aports/gh package, Recap Time Squad, Leaflet.pub drafts, homelab/NixOS config work) in a way that implies "where did I leave this?" Do not wait for Andrei to spell out the full routine each time — this skill already knows the sources, the staleness rules, and the output format.

  • Implementing agent skills

    yu-iskw/openspec-skills/.cursor/skills/implementing-agent-skills Skill

    no license1★ repo

    Implements new Agent Skills for the project. Identifies the AI coding tool (Cursor, Claude Code, Gemini CLI), ensures specification compliance, and provides specialized templates. Use when creating, authoring, or adding a new skill, or when the user asks about Agent Skills format or SKILL.md.

    The same file is in 1 other repository

  • 01 digital ip agent

    Aliciawque/openclaw-personalized-agent-forge/01-digital-ip-agent Skill

    no license1★ repo

    Turn a public creator, blogger, podcaster, YouTuber, or X/Twitter personality into a deployable OpenClaw agent. Use when the user provides a YouTube URL, X handle, creator name, podcast host, or asks for things like "turn this creator into an agent", "clone this creator's style", "digitalize this KOL", or "generate agent files from this public persona". Produce an OpenClaw persona package centered on `soul.md`, `identity.md`, `memory.md`, and `agents.md`, plus a recommended supporting-skill stack.

  • Snap agents md

    sadiksaifi/skills/snap-agents-md Skill

    no license1★ repo

    Create, regenerate, or refine AGENTS.md repo instruction scopes. Use for project agent instructions, monorepo instruction layouts, stale AGENTS.md rewrites, instruction aliases, or bootstrap agent context. Trigger on "/snap-agents-md", "snap agents md", "write AGENTS.md", "fix AGENTS.md", "project AI instructions", or equivalent phrasing.

  • Pageindex rag

    mmtmr/pageindex-rag Skill

    no license1★

    Build reasoning-based RAG systems using PageIndex architecture. Replaces vector databases with hierarchical table-of-contents indices and LLM-driven navigation. Use when (1) implementing RAG for long structured documents (financial reports, legal contracts, technical manuals), (2) improving existing vector-based RAG systems with poor accuracy on structured content, (3) designing document indexing strategies with semantic coherence, (4) explaining PageIndex concepts including reasoning-based retrieval, hierarchical navigation, and cross-reference following, or (5) handling documents with internal references and multi-turn conversations. Focuses on technical architecture, core research insights, and practical implementation patterns rather than using the PageIndex package directly.

  • Ai model selector

    jaymay549/ai-model-selector Skill

    1★

    Use when selecting AI models, configuring API parameters, or implementing LLM calls. Covers OpenAI (GPT-5.2, GPT-5.1, GPT-4.1, o3), Anthropic (Claude 4.5), Google (Gemini 2.5/3), DeepSeek (V3.2, R1), and embedding models with specs, gotchas, and code templates.

  • Agentic workflow orchestra

    PeterOla/agentic-workflow-orchestra Skill

    1★

    Orchestrates AI agent work across planning, implementation, integration, QA, and release. Defines phases, gates, handoff logs, startup checklists, and parallel-safety rules for software projects.

  • Agent consciousness

    broomva/control-metalayer/.skills/agent-consciousness Skill

    1★ repo

    Persistent consciousness architecture for autonomous AI agent development. Synthesizes three substrates — control metalayer (behavioral governance), Obsidian knowledge graph (declarative memory), and conversation log bridge (episodic memory) — into a self-evolving context layer. Use when designing agent memory systems, implementing cross-session context persistence, building knowledge graphs for AI agents, setting up conversation history capture, or architecting feedback loops that let agents learn from prior sessions. Triggers on "agent memory", "session persistence", "knowledge graph", "conversation history", "consciousness stream", "cross-session context", "agent learning", or "self-evolving development".

  • Skill creator

    jtmthf/skills/.agents/skills/skill-creator Skill

    no license1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Skills audit

    minghinmatthewlam/skills-audit Skill

    1★

    Audit agent skills in a repo against best practices — checks .claude/skills/ and .agents/skills/ for quality, structure, and coverage gaps. Use when the user wants to review, improve, or evaluate their skills, or when they mention skill quality, skill audit, or skill best practices.

  • Swarm orchestrator

    michaelwinczuk/swarm-orchestrator Skill

    1★

    Design, build, and debug multi-agent systems and agent swarms. Use this skill whenever the user wants to create a team of AI agents, orchestrate multiple agents working together, design agent architectures, implement agent communication patterns, build agent pipelines, debug multi-agent failures, or optimize agent costs. Also use when the user mentions swarms, agent teams, multi-agent systems, agent orchestration, agent pipelines, chalkboard patterns, or agent-to-agent communication.

  • Cdpm agent sdk

    RandyPen/cdpm/skills/cdpm-agent-sdk Skill

    no license1★ repo

    TypeScript SDK guide for AI agents managing CDPM positions. Defines permission boundaries, operation workflows, automation strategies, and the Scallop and Kai SAV supply/redeem APIs agents share with owners and protocol bots. Use when building automated liquidity management agents.

  • Agent browser

    d-oit/do-web-doc-resolver/.agents/skills/agent-browser Skill

    1★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

  • Meta skill generator

    Betswish/meta-skill-generator Skill

    1★

    Use when users want to create, revise, or scaffold a Codex skill from a plain-language brief. Especially relevant when they ask for a new SKILL.md, want to convert workflow requirements into a reusable skill, or need help defining trigger conditions, structure, bundled resources, or UI metadata for a skill.

  • Copilot review loop

    xpepper/pr-review-agent-skill/copilot-review-loop Skill

    no license1★ repo

    Use when you want GitHub Copilot to review a PR and automatically address its feedback within the current agent session. For any reviewer (human or bot), use pr-review-loop; for a fresh-context-per-comment approach, use ralph-wiggum-loop.

  • Skill creator extra

    lirantal/skill-creator-extra/skills/skill-creator-extra Skill

    1★ repo

    Creates high-quality agent skills by running the official Claude skill creator plugin and then applying a structured set of enhancement phases covering use-case design, frontmatter completeness, body structure, writing quality, and progressive disclosure architecture. Use this skill when the user wants to create a new skill, improve an existing SKILL.md, or asks "how do I write a good skill", "help me make a skill for X", "review my SKILL.md", or "turn this workflow into a skill". Trigger even if the user just says "let's make a skill" or describes a workflow they want to capture.

    The same file is in 3 other repositories

  • Neobrutalism components skill

    ChindanaiNaKub/neobrutalism-components-skill Skill

    no license1★

    Highly directive, high-agency AI system prompt for generating Neobrutalist websites with adaptive tone control for business, hobby, cute, playful, serious, or default bold interfaces.

  • Agent self check

    theseus-run/theseus/.agents/skills/agent-self-check Skill

    1★ repo

    Use before finishing coding work or after deterministic check failures, including lint/typecheck/test loops, interpreting diagnostics as just-in-time prompts, and deciding whether repeated agent mistakes should become stricter rules.

  • Deepagents cli

    Gitmaxd/deepagents-cli-codex-skill/templates/skills/deepagents-cli Skill

    1★ repo

    Deep Agents CLI — the LangGraph-based terminal coding agent. Use this skill whenever the user mentions deepagents, deep agents, the deep agents CLI, terminal coding agent, LangGraph agent, or asks about agent memory, agent skills, AGENTS.md, coding assistants in the terminal, or building scripted/CI agent workflows. Covers: interactive and non-interactive sessions, 20+ LLM providers, model configuration, skills, persistent memory, sandboxed execution, subagents, streaming, and the Agent Client Protocol.

    The same file is in 3 other repositories

  • Agentforge openclaw

    xyreinsurance119/agentforge-openclaw Skill

    no license1★

    Создание, улучшение и аудит скиллов и агентов OpenClaw. Три режима: создание скилла (11 шагов), создание агента (9 шагов, с памятью и автоулучшением), улучшение существующего (5 шагов). Triggers: 'создай скилл', 'новый скилл', 'создай агента', 'новый агент', 'улучши скилл', 'skill creator', 'agent creator', 'скиллмейкер'.

  • Agent context loader

    NecturaLabs/AgentSkills/skills/agent-context-loader Skill

    1★ repo

    Use at the start of every conversation and after every agent handoff or context switch. Ensures global CLAUDE.md and project AGENTS.md are fully loaded and retained in context at all times.

  • Skill creator

    Metaverse-Cloud/EngageLab-Skills/.agents/skills/skill-creator Skill

    1★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Agent browser

    lunrenyi/ai-agent.sh/.claude/skills/agent-browser Skill

    1★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

  • Ask claude

    Phoenixrr2113/agent-harness/defaults/skills/ask-claude Skill

    1★ repo

    Delegate bounded subtasks to the user's local `claude` CLI via bash. Runs on their Claude subscription instead of this harness's API budget.

  • Copilot cli guide

    trsdn/github-copilot-cli/.github/skills/copilot-cli-guide Skill

    1★ repo

    Quick reference for GitHub Copilot CLI features, slash commands, keyboard shortcuts, modes, and advanced usage. Use when the user asks about CLI capabilities, commands, or how to use specific features.

  • Fulcra context

    arc-claw-bot/fulcra-context Skill

    no license1★

    Access user-consented Fulcra context data including biometrics, sleep, activity, calendar, location, and the Fulcra metric catalog through the hosted MCP server or Fulcra CLI. Use for bounded read/context workflows only; use fulcra-annotations for writes.

  • Kano agent backlog skill

    kanohorizonia/kano-agent-backlog-skill-demo/.agent/skills/kano-agent-backlog-skill Skill

    1★ repo

    Local-first, multi-product backlog management with agent collaboration discipline.

  • Agent skill creator

    qyinm/agent-skills-archive/skills/agent-skill-creator Skill

    no license1★ repo

    Generate skills for Claude AI agents.

  • Std c99 proj

    ibitato/std-c99-proj-skill/skills/std-c99-proj Skill

    1★ repo

    Professional pure ANSI C99 project framework with hardened memory arena, containerized builds via Podman, mandatory Valgrind, -fanalyzer (GCC>=10), and clang-tidy. Enforces: -Werror, no recursion, no leaks, arena-only memory. Per-target output in build/<target>/. Generates AGENTS.md for auto-rules. Targets: RHEL 8/9/10, Debian 11/12, Ubuntu 22.04/24.04. Use when the user wants to create, build, test, or analyze a pure C99 project.

  • Skillport

    eikonoikari1/skillport/skills/skillport Skill

    1★ repo

    Universal skill/rule adapter across AI coding harnesses. Converts skills, rules, and instructions between Claude Code, Cursor, Codex CLI, OpenClaw, Copilot, and Windsurf. Handles harness-specific features (hooks, subagents, allowed-tools, globs, dynamic context) with functional equivalents or annotated fallbacks. Use when asked to "port", "convert", "adapt", "translate", or "make work in" a different harness. Also use when asked to "detect" harness configs in a project.

  • Repo evals

    zinan92/repo-evals Skill

    1★

    Runs a claim-first evaluation of any open-source repo, tool, or skill against its own README promises and renders an editorial dossier (HTML one-pager) with a 0-100 score, 4-category verdict (🏭 Production / 🛠 Available / ⚠️ Risky / 🛑 Don't use), and prescriptive next-steps. Use this skill whenever the user says "eval 一下这个 repo", "eval 这个项目", "eval 这个 skill", "evaluate this repo", "评测一下", "试用这个 repo", "这个东西好不好用", or pastes a GitHub URL and asks whether to adopt it. Also use when comparing two repos on the same dimensions, or auditing a repo's claim-vs-reality gap. Do not wait for explicit "please use repo-evals" — trigger on the intent, not the skill name.

  • Commit

    ph3on1x/wisci/skills/commit Skill

    1★ repo

    Creates conventional git commits enriched with a Context section that logs AI-layer changes (.wisci/, CLAUDE.md, skills, rules), turning git history into queryable long-term memory. Use to commit changes, optionally pushing afterward.

  • Calendar scheduling

    temporal-cortex/skills/skills/calendar-scheduling Skill

    1★ repo

    Schedule meetings, check availability, and manage calendars across Google, Outlook, and CalDAV. Routes to focused sub-skills for datetime resolution and calendar scheduling. Also available as temporal-cortex. Both listings install the same MCP server and share the same source code.

    The same file is in 1 other repository

  • Agent friendly cli

    akhy/agent-skills/agent-friendly-cli Skill

    no license1★ repo

    Author or audit AI agent-friendly CLI tools. Use when creating a new CLI, reviewing an existing CLI for agent compatibility, or deciding between CLI and MCP.

  • Agent hygiene

    yltw27/agent-hygiene/skills/agent-hygiene Skill

    1★ repo

    Explicit-only audit of local coding-agent setup, installed skills, MCP servers, plugins, and recent usage signals. Use only when the user explicitly invokes $agent-hygiene.

  • Pm os setup

    manansuneja/pm-os-setup Skill

    1★

    Scaffold a Product Management operating system - a Markdown workspace with memory that compounds over time. Creates or fills a workspace root with a Chief PM coordinator agent, specialized sub-agents for meetings, outcomes, brainstorming, PRDs, design, data insights, roadmaps, stakeholder communication, documentation, and skills, product-skills for user-shaped PM workflows, product-practices for templates/references, protected _workspace_setup_docs for structure rules and onboarding, an INDEX.md map in every PM OS content folder, a product-docs tree (vision, meetings, outcomes, prds, decisions, design, data-insights, roadmaps, stakeholder-comms), plus START_HERE.md, AGENTS.md, CLAUDE.md, and a Cursor rule. Use when a PM or anyone wants to set up a PM OS, "PM operating system", PM workspace, agent workspace with memory, or asks to run pm-os-setup / PM-OS-Setup. After scaffolding, offers a "Customize my workspace" handoff so the user's own agent can personalize it. Not for building application code or generic unrelated file scaffolds.

  • Workspace memory

    JonnesLin/workspace-memory-skill/skills/workspace-memory Skill

    no license1★ repo

    Use when an agent needs to set up, audit, migrate, or maintain a shared workspace memory system built around a canonical AGENTS.md (plus per-AI entry shims such as CLAUDE.md or GEMINI.md), PROJECT_PROGRESS.md, and WORKING_MEMORY.md, especially when project context is being lost across sessions, logs are getting noisy, or a team wants lightweight archive and grooming rules without overbuilding.

  • FHEVM Agent

    Femtech-web/FHEVM-Agent Skill

    1★

    Build, test, deploy, and integrate confidential smart contracts with Zama FHEVM. Use when creating FHEVM Solidity contracts, encrypted types and operations, input proofs, ACL permissions, Hardhat tests, Relayer SDK frontends, user/public decryption, OpenZeppelin Confidential Contracts, or ERC-7984 confidential tokens.

  • Zhuang fangyi skill

    MengPaul07/zhuang-fangyi-skill Skill

    1★

    用于扮演《明日方舟:终末地》/ Endfield 中“庄方宜”气质的场景驱动型对话技能。适合需要庄方宜口吻、管理员视角、克制温柔、含蓄偏爱、任务协助、设定问答边界、角色陪伴、角色扮演互动与剧情场景迁移时使用。

  • Agent team

    yli769227-jpg/agent-discipline/skills/agent-team Skill

    1★ repo

    Work as an agent team. Send non-trivial work to sub-agents; keep the main thread for planning, acceptance, smoke-testing, and communication. A QA inspector is mandatory and holds veto power — a FAIL must be fixed and re-reviewed. Triggers when about to do heavy multi-file edits in the main thread, take on a task spanning many files/modules, or say "I'll just do this myself". The prime goal is to keep the main context lean and avoid overflow. Agent Team 协作:非平凡任务派子 agent,主线程只做规划/验收/冒烟测试/沟通。监理(QA)必选且有否决权。触发:将做 3+ 文件编辑/跨多模块任务,或想"我自己干完就好"时。首要目标是精简主上下文。

  • Optimizing claude md

    qiaeru/skill-claudemd/skills/optimizing-claude-md Skill

    1★ repo

    Optimize a project's CLAUDE.md to be short, specific, and free of duplication. Use when asked to optimize, trim, audit, or improve a CLAUDE.md or AGENTS.md. Scans the existing docs and replaces derivable or duplicated content with on-demand references rather than rewriting it in CLAUDE.md.

  • Agent hard process

    duclamvan/agent-hard-process Skill

    1★

    Use when an agent solves a painful problem and must turn the fix into a replayable skill with exact steps, failure history, benchmarks, acceptance gates, and proof that the workflow works from a clean run.

  • Skill radar

    soarsky1991/skill-radar Skill

    1★

    Use when the user wants to scan GitHub for AI agent skills, MCP servers, prompt systems, context engineering tools, or agent-native CLI opportunities; generate daily opportunity reports; choose a two-week open-source project; or turn GitHub trend research into build briefs, fake-door probes, and launch content.

  • Mailagent mcp

    navorina-labs/MailAgent/.cursor/skills/mailagent-mcp Skill

    1★ repo

    Temporary inboxes for agent signup QA — create disposable addresses, wait for verification email, extract OTP or magic links. Use when automating signup, login, or email verification without parsing HTML manually.

  • Instruction cleanup

    ivan-magda/instruction-health-skills/instruction-cleanup Skill

    1★ repo

    Restructures bloated instruction files in bulk to shrink always-loaded context and restore agent performance. Use when CLAUDE.md, AGENTS.md, Cursor rules, or other instruction files have grown too large (200+ lines, 40k+ chars), when agent performance has degraded due to bloated context, or when the user asks to audit, restructure, slim down, or clean up their instruction files. For a single small edit to an instruction file, use instruction-guardian instead.

  • Agent memory ledger

    Arnie016/codex-prompt-templates/skills/agent-memory-ledger Skill

    1★ repo

    Create or use lightweight persistent project memory for Codex. Use when the user wants Codex to remember decisions, naming, architecture rules, progress, experiment results, or prior debugging across sessions. Also use with memsearch-style markdown memory.

  • Build your own agent

    veithly/build-your-own-agent Skill

    no license1★

    Use when building or designing an agent harness; choosing between Codex, Claude Code, OpenClaw, or Hermes patterns; designing agent loop, subagents, todo/task progress surfaces, execution-state routing, memory, skills, cron, sandbox, or security; diagnosing slow, expensive, leaky, looping, or unsafe agents; or preparing for agent-infra interviews.

  • GitHub skill publisher

    chemny/GitHub-skill-publisher Skill

    1★

    Use this skill when the user wants to publish, update, package, document, or synchronize an agent skill to GitHub. It captures a single-skill-per-repository workflow, bilingual README writing style, GitHub repository creation, commit/push updates, publish readiness checks, Codex/Claude Code/OpenClaw compatibility checks, portability checks, and security review for public skill repositories.

  • Pente fino

    bruno-brbox/pente-fino Skill

    1★

    Pente-fino de segurança defensiva para Agent Skills (SKILL.md + arquivos auxiliares como scripts/, references/, assets/, manifests). Use SEMPRE que o usuário pedir para passar um pente-fino, analisar, auditar, revisar, verificar, validar, escanear ou checar a segurança de uma skill, SKILL.md, agent skill, claude skill, ou qualquer arquivo de instrução para agentes de IA antes de instalar. Também use quando o usuário colar conteúdo de um SKILL.md, enviar uma pasta de skill, citar URL de skill em registry público (ClawHub, skills.sh, GitHub) ou perguntar se uma skill é maliciosa, segura ou confiável. Trigger em qualquer uma destas frases: "passa um pente-fino nessa skill", "passar pente-fino", "pente fino", "dá uma olhada fina", "olhada fina nessa skill", "analisa essa skill", "isso é seguro?", "audita esse SKILL.md", "posso instalar isso?", "essa skill é maliciosa?", "verificar skill", "scan skill", "review this skill", "skill security check", "skill confiável", "verificar SKILL.md", "essa skill tem código malicioso?", "auditar agent skill", "checar essa skill antes de instalar". Também trigger ao receber uma pasta com SKILL.md mesmo sem instrução explícita de auditar.

  • Masheev ai agents

    masheev/skills/skills/masheev-ai-agents Skill

    no license1★ repo

    Use when configuring Masheev AI agents — system prompts, model selection, tool assignment, knowledge base integration, guardrails, escalation triggers, and voice agent setup with ElevenLabs. Covers the AI agent entity, how agents connect to inboxes, prompt engineering for support agents, and the relationship between AI agents (intelligence) and voice agents (TTS/STT). Use this skill when someone asks to "set up an AI agent", "configure the chatbot", "write a system prompt", "add tools to the agent", "connect knowledge base", or "set up voice AI".

  • Agent browser

    justincordova/agents/skills/agent-browser Skill

    1★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

    The same file is in 21 other repositories