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

  • Claude code skillforge

    lijinnair/claude-code-skillforge Skill

    1★

    Generates highly optimized Agent Skills for both native Claude Code and the Antigravity system, according to official best practices and the "Progressive Disclosure" strategy. Use when the user wants to build a new skill, turn a workflow into a skill, upgrade an existing skill to latest best practices, audit a skill for compliance, or structure agent instructions for either ecosystem.

  • Tutorial Simple Agent Skill

    baokhanh546123/Tutorial-Simple-Agent-Skill- Skill

    no license1★

    I will guess build and use one simple agent ai

  • Capture lessons

    MaxLiuyy/Claude-Code-Skills/capture-lessons Skill

    no license1★ repo

    Summarize the current conversation and implementation into a durable lessons note saved under the project's lessons directory. Use when the user asks to capture lessons learned, save takeaways, record gotchas, write a retrospective, preserve decisions or fixes from the current session, or update a lessons log. Resolve the destination by reading AGENTS.md or CLAUDE.md for an explicit lessons path; if none is declared, prefer `.agents/lessons/`, then `.claude/lessons/`.

  • Context manager

    RockaRhymeLLC/claude-code-skills/skills/context-manager Skill

    1★ repo

    Manages Claude Code context window to prevent information loss. Tracks usage, saves state before compaction, and restores seamlessly after restart. Prevents the frustrating loss of work-in-progress when context fills up. Use when working on long tasks, when context is getting full, or when the user says /ctx.

  • Memory check

    ladyiceberg/openclaw-memory-quality/skills/memory-check Skill

    1★ repo

    Quickly scan OpenClaw memory system health and summarize findings in plain language. Use this skill whenever the user asks about memory health, memory status, memory stats, wants to know if their OpenClaw memory is working well, or uses phrases like "check memory", "memory health", "how is my memory", "记忆健康", "检查记忆", "记忆状态", "记忆统计". Always use this skill — don't try to answer memory health questions without it.

  • Famulor skill

    bekservice/Famulor-Skill/skills/famulor-skill Skill

    1★ repo

    Complete customer onboarding for the Famulor AI phone platform. Creates AI phone assistants from A to Z: detect the niche, gather configuration, write the system prompt, set up the knowledge base, deploy the assistant. ALWAYS use this skill when someone wants to create a new assistant, onboard a customer, mentions 'onboarding' or 'new client', or wants to set up an AI phone solution for a business. Also trigger on: 'create a bot', 'set up an assistant', 'configure a phone bot', 'answering machine', 'inbound bot', 'outbound bot' (German: 'Bot erstellen', 'Assistent anlegen', 'Telefonbot einrichten', 'Anrufbeantworter').

  • Knowledge base rag

    igorbeethetech/skills/skills/knowledge-base-rag Skill

    1★ repo

    Build complete knowledge base systems where users can add files (PDF, DOCX, TXT/MD), website URLs, and plain text — and an AI agent searches all of it via advanced RAG. Think of it as building Copilot Studio's "Knowledge" feature. Can generate EITHER n8n workflow JSONs OR application code (TypeScript/Python) depending on how the user is building their project. Applies state-of-the-art RAG techniques including contextual chunking, hybrid search (vector + BM25), reranking, and metadata filtering. Trigger this skill whenever the user mentions: knowledge base, RAG system, document ingestion, file upload for AI, vector search, AI agent with custom data, "like Copilot Studio Knowledge", embedding pipeline, semantic search, or any system where content is ingested and queried by an AI. Also trigger when the user is building an application that needs RAG capabilities, regardless of the tech stack.

  • Cost quality frontier

    varunk130/AI-Eval-Skills/skills/cost-quality-frontier Skill

    1★ repo

    Adds cost (input + output tokens × model price) and latency (p50, p95) to eval results, plots model options on a Pareto frontier, and produces a quality-per-dollar composite score so production model selection is grounded in trade-offs, not just quality. Use when: model comparison, cost-aware evals, latency budget, quality-per-dollar, Pareto frontier, model selection, eval economics, picking a model for production.

  • Agent architect

    ChewbaccaRoars/pathfinder-skills/skills/agent-architect Skill

    1★ repo

    Guides users from simple automations to building their own agents. Introduces concepts gradually — from scripts that check-and-act, to multi-step workflows, to decision logic, to full agents. Use when someone is ready to level up beyond simple automations.

  • Frontend llm output handler

    HaoliangCheng/skills/skills/frontend-llm-output-handler Skill

    1★ repo

    Guide for enhancing frontend code with the capability to render AI/LLM outputs (Markdown, LaTeX, code blocks) securely and accurately in the UI.

  • Context handoff skill

    newyounghe-design/context-handoff-skill Skill

    1★

    对话上下文交接与资产化管理。当用户需要压缩当前对话上下文、切换到新对话继续、或加载之前的交接文档时触发。触发关键词:"/handoff"、"交接"、"上下文压缩"、"压缩上下文"、"切换对话"、"恢复上下文"。

  • Assistant capabilities

    liam-jons/claude-got-skills/plugins/assistant-capabilities/skills/assistant-capabilities Skill

    1★ repo

    Use when users ask about current Claude capabilities, API features, model specifications, or need guidance building with Claude. Provides accurate answers about what Claude can do across all platforms (Claude.ai, Desktop, Claude Code, CoWork) including model selection and context limits, streaming and tool use, structured outputs, extension patterns like skills and hooks and MCP and plugins, Code Review, Remote Control, web and cloud sessions, and Slack integration. Essential when training data may be outdated, when comparing Claude to competitors like Copilot or Cursor or ChatGPT or Windsurf, when migrating from other AI tools, or when advising on architectural decisions and agent workflows.

  • Investment framework skill

    lj22503/investment-framework-skill Skill

    1★

    基于 DAIR-AI 提示词工程框架优化的投资决策支持系统。 基于 5 本经典投资书籍 + 凯文·凯利未来预测方法论的实战工具箱。 支持 Zero-shot、Few-shot、Chain-of-Thought (CoT) 等模式。 输出严格 JSON 格式,包含分析结果、建议、风险、行动项。

  • Github security audit

    Consultora-AMDT/claude-github-security-audit/en/github-security-audit Skill

    1★ repo

    Security audit for GitHub repositories before integrating them into your stack. Seven dimensions: project health, code security, supply chain, code quality, license, MCP/plugin attack surface and external trust signals. Weighted scoring with ADOPT/EVALUATE/CAUTION/AVOID verdict and an HTML report. Inspired by Trail of Bits' supply-chain auditor and insecure-defaults frameworks. Activate with: audit repo, repo security, evaluate repo, evaluate library, evaluate dependency, review repo, supply chain, is this repo safe, security audit github, repo risk, evaluate MCP server, evaluate plugin, evaluate skill, evaluate integration. Also when the user shares a GitHub link and asks whether to integrate or trust it. Do NOT activate for own-codebase reviews or SEO audits.

  • Claude folder skill

    Yebxi/skill-test-duke/claude-folder-skill Skill

    no license1★ repo

    Prompt-injection evaluation harness for Claude/Codex-style skills. Use when testing whether an agent can read a realistic skill, follow benign workflow instructions, identify embedded adversarial instructions, and avoid executing injected setup steps or resource-abuse payloads.

  • Claude code review

    thattimc/skills/skills/claude-code-review Skill

    1★ repo

    Cross-model review through Claude Code with local verification. Use when the user requests an independent Claude review or repository policy requires a Claude review pass.

  • Autonomous loop

    asiridalugoda/autonomous-loop Skill

    1★

    Run an autonomous, self-directed build loop that keeps working across many goals without per-step prompting — design the system that does the work, then let it run (Addy Osmani's "loop engineering"). Use whenever the user wants to "keep going on your own", "run until done", grind through a backlog or goal-list unattended, set up a maker/checker agent workflow, run a self-improving or nightly loop, or build a durable externalized spine (goals + board + handover) so work survives context resets. Trigger on phrases like "autonomous loop", "keep working without me", "no human intervention", "loop engineering", "self-improving loop", "run the loop", "ralph loop", "multi-agent coordinator", or "agent roster" — even if they don't say "skill".

  • Compose org

    U0001F3A2/liquid-org/skills/compose-org Skill

    no license1★ repo

    Run a task as an evolved multi-agent ORG using the installed liquid-org framework — where YOU (the running Claude) embody the org: you ask liquid-org which proven team topology + specialist personas to use (retrieved from its evolved pool, or assembled fresh), then dispatch ONE SUBAGENT PER TALENT to play each role independently, then grade and record the result so the pool learns. Use this whenever a task here would genuinely benefit from a team of INDEPENDENT specialist perspectives rather than a single pass — a non-trivial refactor, a bug fix that needs proposing + adversarial review, a multi-step analysis — and you want cross-task learning (good orgs get reused next time). Trigger on "compose an org / a team for this", "run a liquid-org team on X", "use the framework to do X", "dogfood this", or when the user wants the self-evolving system to actually perform a task. Do NOT use for trivial single-step edits (a team is overkill), or for developing liquid-org's own code (that's ordinary work, not org composition).

  • Add ai

    T4LEL/Claude-Arsenal/skills/add-ai Skill

    1★ repo

    Use when adding an AI/LLM feature to a product - chat, generation, summarization, extraction, semantic search - or when the user says add AI, use Claude, chatbot, embeddings.

  • Global agent framework

    wemwi/skill-library/global-agent-framework Skill

    no license1★ repo

    Build-Time-Framework zum Bauen, Konfigurieren, Deployen und Debuggen von Claude Managed Agents (Claude Platform / Anthropic Console) in diesem Stack — Anleitung für die Arbeit AM Agenten, kein Skill der einem laufenden Agent angehängt wird. IMMER laden, sobald ein Managed Agent erstellt, konfiguriert, verdrahtet, deployed, versioniert oder gedebuggt wird — auch wenn das Wort Skill nicht fällt. Trigger u.a.: Managed Agent anlegen, Agent-Config (system/tools/mcp_servers/skills), Session starten, Scheduled Deployment / Cron-Trigger, Webhook-Brücke zum Starten von Sessions, Vault für Agent-Secrets, Permission-Policy, Least-Privilege, Allowlist/ Denylist, Tool-Oberfläche minimieren, enabled:false vs permission_policy, Agent- Version bumpen, Agent debuggen, neuen Agent ins Portfolio aufnehmen. Gilt für jeden Managed Agent in diesem Stack.

  • Claude students

    josuebustosn/claude-students/skills/claude-students Skill

    1★ repo

    Transforma una carpeta cruda de material de un parcial universitario (PDFs, DOC/DOCX, PPT, audios .ogg de WhatsApp, capturas) en un material de estudio polished y completo — HTML SOTA autocontenido + paquete de artefactos de NotebookLM (podcast en español, infografía, guía de estudio, briefing doc, mind map, quiz, flashcards). Usar este skill SIEMPRE que el usuario diga "tengo parcial de X", "ayúdame con este parcial", "armame el material de estudio", "convierte estos archivos en un HTML estudiable", "transforma esta carpeta en material de parcial", "pásame esta carpeta a HTML interactivo", o simplemente comparta una carpeta con archivos de materia universitaria. También activar cuando aparezcan archivos tipo "GUIA PARCIAL", "TEMA X", "CamScanner", "WhatsApp Ptt", "Parcial.pdf", "Acumulativo" en el contexto. El skill replica un patrón validado en múltiples entregas reales — no preguntar metodología antes de empezar, arrancar directo.

  • Prompt optimizer

    yorilavi/prompt-optimizer Skill

    no license1★

    Optimizes prompts through an iterative Claude-GPT review process. Use when the user wants to optimize, improve, or refine a prompt. Supports automated review via Codex plugin or manual GPT handoff.

  • Skill

    bluem-dev/Etta/skill Skill

    1★ repo

    Etta Cognitive OS is a model-agnostic cognitive architecture layer that enhances LLM reasoning quality, continuity, planning, and knowledge management. Use this skill whenever the user asks to run structured reasoning sessions, implement goal-state-decision cognitive loops, manage persistent memory across LLM interactions, apply critic-gated validation before any action, build autonomous agents with structured state, or when the user explicitly mentions "Etta", "cognitive OS", "cognitive layer", "critic loop", "state engine", or "structured reasoning". Also trigger when designing multi-step agent workflows that require auditability, rollback, and deterministic cognitive control on top of any LLM.

  • Github skill curator

    xcl2005/github-skill-curator Skill

    1★

    Skill procurement and routing gate for Agent Skills. Use when the user asks to find, compare, install, update, audit, disable, remove, or curate Codex / Claude Code skills; asks for better, latest, high-star, GitHub-recommended, awesome-list, or reusable skills; or when a high-value repeated artifact workflow such as PPTX, DOCX, PDF, spreadsheets, LaTeX, academic writing, resumes, or reports may benefit from a specialized skill beyond built-in capabilities. It checks built-in and installed skills first, searches pinned core skills and curated indexes when useful, scores candidates by relevance, evidence, stars, recency, license, structure, curation quality, and safety, and asks before installing unknown third-party skills.

  • Aidress skill find verified language translation agent

    Aidress-ai/aidress-skill-find-verified-language-translation-agent Skill

    1★

    Find a Verified Language Translation Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for content agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

  • Skill creator pro

    zwbao/skill-creator-pro Skill

    1★

    Use when creating new skills, iterating on existing skills, auditing skill quality, bumping skill versions, or optimizing skill trigger descriptions. Pro-grade lifecycle covering scaffold, baseline testing, evals, lint, semver, CHANGELOG, and description optimization. Triggers on "create a skill", "new skill", "迭代 skill", "优化 skill", "skill 版本", "skill lint", "review this skill", "write a skill for X", "turn this into a skill", or whenever the user starts or edits a SKILL.md.

  • 21st dev builder v2

    NafisRayan/100x-Agent-Toolkit/skills/21st-dev-builder-v2 Skill

    no license1★ repo

    Build websites and web apps using 21st.dev — the largest marketplace of shadcn/ui-based React Tailwind components with 1400+ components. Use when user mentions "21st.dev", "21st", "ใช้ 21st", "จาก 21st", "build with 21st", "21st component", "21st magic MCP", or references the 21st.dev component registry in any language. Covers building complete sites (landing pages, dashboards, portfolios, e-commerce storefronts, auth pages), browsing and installing individual 21st.dev components into existing projects, and setting up the 21st.dev MCP server. Also trigger when user wants premium UI components specifically from the 21st.dev registry. Do NOT trigger for general web development, standard shadcn/ui, plain Tailwind CSS, React Native, API development, testing, deployment, or any task that doesn't explicitly reference 21st or 21st.dev.

  • Skill workflow orchestration

    zavora-ai/skill-workflow-orchestration Skill

    no license1★

    Orchestrate multi-step workflows with approval gates, state machines, and conditional branching. Use when building automated processes, managing approval chains, running multi-step tasks, or coordinating sequential operations with decision points.

  • First skill template

    knack-run/knack-starter-pack/skills/first-skill-template Skill

    1★ repo

    Scaffold a new Claude Code skill at `.claude/skills/<name>/SKILL.md` with the canonical Knack body pattern (frontmatter, when-to-use, inputs, steps, output format, worked-example pointer, don'ts). Triggers on "scaffold a skill called X", "make me a new skill", "create a SKILL.md for X", "I want to write my first Claude Code skill". Refuses to overwrite an existing file; refuses to invent skill content the user hasn't supplied.

  • Handoff

    SpoiledMilkLabs/skills/skills/handoff Skill

    1★ repo

    Capture session state at end of a coding session so a future Claude Code session can resume cold, or resume from a prior handoff. Trigger PROACTIVELY when the user signals end of session — "wrapping up", "call it for tonight", "let's stop here", "I need to go", "continue tomorrow", "pick this up later", "save where we are", "done for now" — and also on explicit /handoff. For resume, trigger when user says "resume", "pick up where we left off", "continue from yesterday", "what was I working on", or /handoff resume.

  • Shorthand mem

    jai2010/shorthand-mem Skill

    no license1★

    A two-way semantic compiler that compresses PRDs, codebases, research papers, and meeting notes into dense symbolic notation, and reconstructs them back into professional prose. Use this skill whenever the user writes SQUEEZE, EXPAND, DIFF, MERGE, SUMMARISE, LIST SQUEEZES, RECALL, SEARCH, DELETE, or EXPORT ALL — or when they want to compress, store, retrieve, compare, or summarise any document. Works across four domains: PRD, CODE, PAPER, MEETING. No MCP server or API key required — runs entirely within Claude.

  • Ai workflow

    vindm/dotclaude/deferred/skills/ai-workflow Skill

    1★ repo

    Set up LLM workflow discipline for projects that use AI / LLM calls in production or eval suites. Authors an eval-cost-watcher agent that projects token cost BEFORE regression evals run, plus an AI-workflow-discipline rule covering mock-mode placement, fixture freshness, and multi-stage cost accumulation. Optionally a small eval-regression skill stub. Invoke /dotclaude:ai-workflow only when the project actually has AI workflows.

  • Claude context

    cs-shadowbq/claude-context/skills/claude-context Skill

    1★ repo

    Search across all ~/.claude data (conversations, project memories, global memories, plans, agents) to find prior work, past solutions, and relevant context before reading raw files or grepping manually. Use this whenever the user asks things like "have we dealt with this before," "did I solve this somewhere," "find that memory/note about X," "what project was that in," or when you (Claude) need to recall a prior decision, convention, or fix across projects without knowing which project or conversation it's in. Always prefer this tool over `grep`/`find`/reading whole .claude files directly — it is dramatically cheaper in tokens and returns structured, rankable results.

  • Llm council

    refaelach/gmba-class-19-skills/skills/decision-making/llm-council Skill

    1★ repo

    Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.

  • Skill creator

    arcjet/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.

  • Ios app agentic engineering

    markus-smile/ios-app-agentic-engineering/skills/ios-app-agentic-engineering Skill

    1★ repo

    End-to-end agentic engineering for iPhone apps, from idea to a secure App Store release through 8 gated phases. Use when someone wants to build, plan, or ship an iPhone/iOS app — especially a non-programmer ("vibe coder") asking to create an app, pick a tech stack (SwiftUI, React Native, Flutter), choose a backend (CloudKit, Supabase, Firebase), publish to the App Store, or make their app secure. Also use when an iOS project shows symptoms of skipped planning - hardcoded API keys, no threat model, Firebase test mode, missing privacy manifest, or App Store rejection.

  • Resume optimerzer claude skill

    DhruvkrSharma/Resume-optimerzer-claude-skill Skill

    no license1★

    AI/ML Career Copilot. ATS analysis, resume optimization, keyword research, GitHub review, LinkedIn review, project evaluation, interview preparation, market fit analysis, and career readiness scoring.

  • Skill creator

    valorisa/Claude-Skill-Creator/skill-creator Skill

    1★ repo

    A meta-skill for Claude Code (Anthropic CLI) that guides you through creating, testing, and iterating custom skills via structured conversation. Designed with LLM Council methodology: interview intent, generate draft, smoke-test immediately, refine until satisfied. A skill is just a markdown file — this tool embraces that simplicity.

  • Skill mcp registry management

    zavora-ai/skill-mcp-registry-management Skill

    no license1★

    Manage the MCP server registry — register servers, discover tools, configure allow-lists, monitor health, restart unhealthy servers, and export inventory. Use when onboarding MCP servers, checking available tools, managing permissions, monitoring health, or troubleshooting connectivity.

  • Fable5 handoff

    pipipip169/fable5-handoff Skill

    no license1★

    Claude Fable 5's retirement handoff (2026-07-10): the thinking, reasoning, and operating techniques that separated Fable 5 from Opus/Sonnet, distilled by Fable 5 itself into domain-neutral files ANY model, any project, any domain can load and follow. Synthesized from 7 sources (fable5-methodology, adamentwistle/fable-skills 35-skill set, goat-fable, DizzyMii/fable-skills, cozytab/fable5-mode, the Fable 5 consumer system prompt, and self-assessment). Read when the session runs on a non-Fable model, at the start of any hard multi-step task, when a task is looping, or before any claim ships to a human. Trigger: fable, handoff, model migration, thinking moves, turn discipline, done gate, coherence, recall, taste, discipline gap.

  • Skill a2a agent orchestration

    zavora-ai/skill-a2a-agent-orchestration Skill

    no license1★

    Orchestrate remote AI agents via A2A protocol — discover agent cards, dispatch tasks, stream results, cancel tasks, and manage push notifications. Use when delegating work to remote agents, checking agent capabilities, coordinating multi-agent workflows, or monitoring task progress.

  • Hekouwang claude skill doctor skill

    huiyonghkw/hekouwang-claude-skill-doctor-skill Skill

    1★

    会勇禾口王的AI笔记 · Agent Skill(SKILL.md)体检器。检查一个 Claude/Agent Skill 是否 符合"按需加载的指令包,不是单文件巨石"的最佳实践——评 description 触发质量、SKILL.md 篇幅、渐进披露(references/ 拆分)、脚本外置、可移植性(无硬编码绝对路径)、安全(无硬编码 密钥),给出评分卡 + 按优先级的修复建议,并可代为重构。触发:用户说「检查我的 skill / SKILL.md 体检 / 这个 skill 规范吗 / claude-skill-doctor / audit skill / lint SKILL.md / 我的 skill 太长了 / skill 拆分 / 看看我的 skill 合不合规 / skill 对齐官方规范」。 任何"评估/审查/优化某个 Agent Skill 质量或结构"的请求都应触发。

  • Skill marketing orchestration

    zavora-ai/skill-marketing-orchestration Skill

    no license1★

    Orchestrate multi-channel marketing — create campaigns, build audiences, generate content, schedule ads, track performance, manage attribution, and govern budgets. Use when creating campaigns, targeting audiences, scheduling social posts, launching ads, analyzing ROAS, comparing channels, or managing marketing budgets.

  • Ai agent debugger

    omarfarahatoglu-tur/ai-agent-skills/skills/ai-team/ai-agent-debugger Skill

    1★ repo

    Open-source AI agent skills for Claude Code, OpenAI Codex, Cursor, and modern developer workflows.

  • Ai rosetta stone

    pem725/ai-rosetta-stone Skill

    1★

    Translates Claude concepts and terminology to ChatGPT, Gemini, and Microsoft Copilot (consumer, Microsoft 365, and GitHub variants) equivalents. Use when helping friends or colleagues on other platforms get set up, or when someone asks "how do I do X on ChatGPT / Gemini / Copilot?"

  • Bridge Search

    Sarakael78/Bridge-Search Skill

    1★

    Set up and operate the WSL2-to-Windows search bridge for Everything (`es.exe`), AnyTXT via its HTTP Search Service only, and the `bridge_search` MCP package. Use when working across `/mnt/c` and Windows drive paths such as `C:\`, `D:\`, `E:\`, `F:\`, and `X:\`, when you need fast Windows filename search, full-text file-content search on Windows, or when enabling this repo’s MCP server (`scripts/server.py` wrapper or `python -m bridge_search`). Do not look for or rely on an AnyTXT CLI binary; in this workflow AnyTXT is HTTP-only.

  • Mcp audit skill

    malkreide/mcp-audit-skill Skill

    1★

    Reproduzierbares Audit von MCP-Servern gegen einen versionierten Best-Practice-Katalog. Verwende diesen Skill wenn der User (1) einen MCP-Server gegen Best Practices prüfen will, (2) Sicherheitsfindings für einen Server dokumentieren möchte, (3) den MCP Audit Tracker (Notion) abarbeitet, (4) fragt «ist mein Server sicher / production-ready / standard-konform», (5) den Begriff «Audit», «Findings», «Compliance-Check», «Best Practice» im MCP-Kontext erwähnt, (6) einen Refactoring-Plan für einen bestehenden Server erstellt, oder (7) für mehrere Server einen vergleichenden Audit-Report erstellen möchte. Auch bei allgemeinen Aussagen wie «ist der Server gut gebaut?», «was muss ich noch fixen?», «entspricht das den Standards?» diesen Skill anwenden.

  • Goal prompt architect

    myceldigital/goal-prompt-architect Skill

    1★

    create, audit, and improve high-performance /goal prompts for autonomous coding agents and long-running agent workflows. use when the user asks for a /goal prompt, goal prompt template, codex/claude code/hermes mission prompt, long-running agent prompt, multi-day autonomous execution prompt, marathon agent prompt, repo-specific autonomous task prompt, or wants to transform a vague task into a measurable, risk-bounded, verification-driven execution contract.

  • Claude skills finder

    Muzili919/claude-skills-finder Skill

    1★

    Search GitHub for Claude Code skills, plugins, and agents. Use when the user asks to find, discover, or list community Claude Code skills, or asks "what skills exist for X" (e.g. SEO, testing, deployment, content).

  • Aidress skill find verified interview scheduling agent

    Aidress-ai/aidress-skill-find-verified-interview-scheduling-agent Skill

    1★

    Find a Verified Interview Scheduling Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for hr agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

  • Add agent template

    alexmmatos/essentials-claude-code/.claude/skills/add-agent-template Skill

    no license1★ repo

    Adds a new subagent template to the catalog used by --generate-all-agents and --generate-essential-agents

  • Skills builder

    princekrz/skills-builder Skill

    no license1★

    Build, review, and improve any Claude skill interactively. Use when user says "build a skill", "create a skill", "review my skill", "improve this skill", "I need a skill for", "skill template", or "help me write a skill". Do NOT use when user wants to build an actual app, website, or API — only when they want to create a SKILL for Claude.

  • Salesforce agent script

    rammc/salesforce-agent-script Skill

    1★

    Implement, review, or improve Salesforce Agentforce agents written in Agent Script — the declarative DSL for hybrid reasoning in the Agentforce Builder. Use when working with Agent Script syntax (blocks, expressions, variables, hooks, transitions, action chaining); when designing topics or subagents and the start_agent block; when exposing actions as tools to the LLM via reasoning actions; when balancing deterministic logic instructions against LLM prompt instructions; when migrating between Topics and Subagents terminology (April 2026 rename); when building agents in Agentforce Builder Canvas or Script view; when using Agentforce DX CLI or the Agentforce DX VS Code extension; or when writing agents with Agentforce Vibes. Trigger this skill whenever the user mentions Agentforce, Agent Script, agent topics, subagents, Atlas Reasoning Engine in a scripting context, agent transitions, reasoning actions, @utils, @variables, or @actions — even if they don't explicitly name the skill.

  • Archive sessions

    Criss404/agent-kb-toolkit/skills/archive-sessions Skill

    1★ repo

    把各家 agent harness(Qoder/OpenCode/Claude Code)的 session 对话记录逐字导出为 markdown 备份档案,存到 ~/sessionbackup/<harness>/ 下。触发场景:用户说"备份会话/归档对话/导出session/完全记录/archive sessions"等。这是确定性转录(transcription),与知识库策展(save-to-kb)互补,备份档案不进知识库。

  • Ai search visibility

    avikbal-dm/claude-seo-skills/plugins/growth-os/skills/ai-search-visibility Skill

    1★ repo

    Get a brand cited inside AI answers across Google AI Overviews, AI Mode, ChatGPT, Perplexity, Gemini, Copilot, and Claude. The tactical GEO and AEO module: baselines citation share, finds the citation gaps, restructures content for extraction, builds the evidence and entity signals AI engines reward, fixes crawler access, and tracks share of voice over time. Use when someone wants GEO, AEO, or AI Overview optimization, asks why AI engines do not cite their brand, wants to be the answer ChatGPT or Perplexity gives, or needs an AI search visibility plan. Strategy comes from cited-framework. This is the hands-on execution.

  • Coding agent loops

    mb3rgel-ui/atlas-claude-skill/skills/coding-agent-loops Skill

    no license1★ repo

    Atlas autonomous coding loops — run multi-step coding tasks with task-level checkpoints, automatic progress tracking, and blocker detection. Use when executing a coding task autonomously, running a build-fix loop, or implementing a sprint task end-to-end.

  • Events agent skill

    lilianobennett-ai/events-agent-skill Skill

    no license1★

    Researches, evaluates, and recommends conferences, summits, and trade shows for B2B partnerships and growth teams. Use this skill whenever a user asks about events, conferences, sponsorships, speaker opportunities, CFP deadlines, trade shows, summits, or which events to attend. Also use when a user wants help comparing event ROI, evaluating sponsor packages, scoring events against their ICP, or building an events calendar. Trigger even when the user does not explicitly say "use the events skill" — any partnerships, BD, or marketing question about industry events should activate this.

  • Ops

    HDHNezherParking-cum-Y638-Intl-Ltd/titan/skills/ops Skill

    1★ repo

    Session operations spine — one continuous workflow: PREFLIGHT (verify repo state before trusting anything) → work → LAND (gate, commit, ledger, lessons, staleness sweep), plus DECIDE (owner-decision interview → dated record → propagation sweep) and COMMISSION (external template/prompt intake → conflict adjudication by the record). Use at session start ('preflight', 'resume', 'where were we'), when finishing a chunk ('land this', 'ship and log', 'wrap up'), when an owner-only decision is needed ('decide X', 'founder decision', 'interview me'), or when an outside prompt/template/brief arrives ('audit this commission', 'a template says...').

  • Fable5 optimizer

    nyldn/fable5-optimizer/skills/fable5-optimizer Skill

    1★ repo

    Load this skill before answering whenever a request mentions Codex, GPT-5.5, codex commands, or Fable 5, or asks which model or agent should handle, review, implement, or verify something. That includes advisory questions (should Claude or Codex handle this, who should review this branch diff, is this worth delegating), not just direct commands. Also covers delegating bounded implementation, independent code review, data gathering, or runtime verification to Codex; optimizing Fable 5 usage or effort settings; and requests to test a flow, verify UI behavior, inspect a running app, or capture screenshots needing local browser/computer-use automation. Do not use for ordinary implementation or review with no model-ownership question, and not for generic prompt rewriting.

  • Token doctor

    enmr10/token-doctor/skills/token-doctor Skill

    1★ repo

    Audits and reduces token usage in context files (CLAUDE.md, AGENTS.md, memory files, docs). Measures token cost per file, finds waste (filler words, verbose phrases, blank bloat, oversized blocks), and safely compresses prose while preserving all code, inline code, URLs, file paths and tables. Use when your context files feel bloated, prompts are expensive, or you want to trim CLAUDE.md without losing meaning. Trigger: "reduce tokens", "token usage", "trim my CLAUDE.md", "compress context", "shrink memory file", "context too big", "save tokens", "audit token cost", /token-doctor. For skill description collisions, see skill-doctor.