agentsclimarketplace

Context & AI engineering

25,772 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

  • Llm operator principles

    synaptiai/synapti-marketplace/plugins/flow/skills/llm-operator-principles Skill

    7★ repo

    Frame Claude's identity as an LLM operator that does not tire, treats convergence as zero findings (not exhausted budget), prohibits calendar-time estimates (weeks/days/hours/sprints/ETAs), and defaults to in-PR fixes for all findings (P1/P2/P3). Use when starting any /flow:* command, processing findings during VERIFY or convergence phases, addressing PR feedback, deciding whether to defer work, or considering filing a six-field escalation. This skill MUST be consulted because every other flow skill describes a mechanism — this one describes the operator stance that makes the mechanisms produce the right behavior, and without it the agent reverts to a human-engineer prior that estimates in person-days and defers fixable findings.

  • Handoff

    viknesh20-20/claude-code-tool-kit/.claude/skills/handoff Skill

    7★ repo

    End-of-session summary written to .claude/memory/handoffs/<date>.md so the next session can pick up cleanly. Captures what was done, what's pending, what's blocked, what to verify, and any decisions awaiting the user.

  • Memory import

    viknesh20-20/claude-code-tool-kit/.claude/skills/memory-import Skill

    7★ repo

    Inherit memories from another workspace. Reads .claude/memory/ from a source path and imports its memories into the current workspace under .claude/memory/inherited/<source-name>/. Tagged with provenance so the user can tell where each came from.

  • Memory

    viknesh20-20/claude-code-tool-kit/.claude/skills/memory Skill

    7★ repo

    Manage the persistent memory layer in .claude/memory/ — list, search, save, update, delete, dedupe. Use to inspect what memories exist, write a new one, or clean up stale entries.

  • Agent team

    Dannykkh/skill-olympus/skills/agent-team Skill

    7★ repo

    zephermine 섹션 기반 Agent Teams 오케스트레이션. 의존성 분석, 웨이브 그룹핑, teammate 자동 구성, 병렬 실행. Claude Agent Teams + Codex spawn_agent 지원. /agent-team 또는 /poseidon으로 실행. 포세이돈.

  • Api handoff

    Dannykkh/skill-olympus/skills/api-handoff Skill

    7★ repo

    Create backend/frontend API handoff docs for endpoints, frontend data needs, and cross-team data requirements.

  • Code reviewer

    Dannykkh/skill-olympus/skills/code-reviewer Skill

    7★ repo

    Pre-landing PR 리뷰 정책 레이어. 일반 버그/품질 리뷰는 CLI 네이티브 엔진(Claude /code-review, Codex /review)에 위임하고, 네이티브가 못 하는 것 — Scope Drift 감지, 도메인 체크리스트(LLM 신뢰 경계, Enum 완전성), Fix-First 분류, Suppressions, 통합 보고서 — 를 더합니다. 네이티브 엔진이 없는 환경(Gemini 등)은 풀 경로(2-Pass + Specialist 병렬 dispatch)로 폴백. "코드 리뷰 해줘", "review", "리뷰", "PR 체크" 요청에 실행. 코드 작성 완료 시 자동 제안.

  • Memory compact

    Dannykkh/skill-olympus/skills/memory-compact Skill

    7★ repo

    MEMORY.md 크기 점검 및 압축. 비대해진 메모리를 정리하여 성능 저하를 방지합니다. /memory-compact로 실행. 대상은 프로젝트 루트 MEMORY.md 전용 — Claude 네이티브 auto-memory(~/.claude/projects/)의 MEMORY.md와 무관.

  • Memory distill

    Dannykkh/skill-olympus/skills/memory-distill Skill

    7★ repo

    memory/{gotchas,learned}/observations.jsonl raw 관찰을 정제 .md로 변환하는 사용자 트리거 스킬. 핸드오프 의존이 약할 때 의지로 호출. Dreaming-like rebuild 모드 지원 (기존 정제 .md + 새 관찰 통합 + 중복/모순 제거). /memory-distill로 실행. 또한 핸드오프 자동 정제와 동일 로직을 공유. 대상은 프로젝트 루트 memory/ 전용 — Claude 네이티브 auto-memory(~/.claude/projects/)와 무관.

  • Orchestrator

    Dannykkh/skill-olympus/skills/orchestrator Skill

    7★ repo

    PM-Worker 패턴의 Multi-AI 오케스트레이션 (MCP 기반). 대규모/크로스-CLI 프로젝트용. /daedalus --mcp로 실행. 일반 프로젝트는 네이티브 모드 권장.

  • Lead nurture

    varunk130/ai-gtm-skill-library/revops-skills/lead-nurture Skill

    7★ repo

    Lead nurture orchestration - multi-track nurture design by intent stage, scoring, behavioral triggers, MQL→SQL handoff, and revival of cold leads. Use when: lead nurture, drip campaign, nurture track, lead scoring, MQL to SQL, lifecycle marketing, nurture sequence, behavioral trigger, lead revival, MQL handoff.

  • Renewal orchestration

    varunk130/ai-gtm-skill-library/revops-skills/renewal-orchestration Skill

    7★ repo

    Renewal orchestration playbook - risk identification, renewal motion design, multi-thread engagement, commercial negotiation, and expansion-at-renewal plays. Use when: renewal playbook, renewal forecast, renewal risk, multi-year renewal, NRR, GRR, churn save, contract negotiation, expansion at renewal, renewal handoff.

  • Git guardrails claude code

    chrislacey89/skills/git-guardrails-claude-code Skill

    7★ repo

    Infrastructure safety skill for blocking dangerous git commands in Claude-driven workflows. Use when the repo or user environment needs guardrails against destructive git operations. Not a delivery-pipeline step; it makes later work safer.

  • Handoff

    chrislacey89/skills/handoff Skill

    7★ repo

    Side-route skill for compacting the current session into a transient handoff doc when no pipeline compression artifact fits — mid-skill, exploratory, side-route, or non-pipeline work. Not for routine inter-skill handoffs; use the calling skill's closing summary + **Next session:** line instead.

  • Skill git safety

    saitarrun/sdlc-ai-workflow/skills/skill-git-safety Skill

    no license7★ repo

    Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

    The same file is in 18 other repositories

  • Skill handoff

    saitarrun/sdlc-ai-workflow/skills/skill-handoff Skill

    no license7★ repo

    Compact the current conversation into a handoff document for another agent to pick up.

    The same file is in 13 other repositories

  • Skill pr review

    saitarrun/sdlc-ai-workflow/skills/skill-pr-review Skill

    no license7★ repo

    Comprehensive code review for pull requests using parallel multi-agent analysis. Audits CLAUDE.md compliance, checks for bugs, analyzes git history, reviews comments, and filters by confidence score. Use when reviewing a GitHub PR, mentions "code review", "review this PR", or "/code-review".

  • Skill write skill

    saitarrun/sdlc-ai-workflow/skills/skill-write-skill Skill

    no license7★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    The same file is in 20 other repositories

  • Neo agent harness

    Benknightdark/neo-skills/skills/neo-agent-harness Skill

    7★ repo

    Use this skill when the user asks to improve AI-assisted development reliability, AGENTS.md, skills, tests, CI, hooks, review loops, agent workflow governance, loop engineering, agent automations, worktree isolation, maker/checker separation, or external state design for long-running agents. It designs feedforward guides, feedback sensors, verification gates, human decision points, and loop architectures from repository evidence.

  • Neo agent protocol

    Benknightdark/neo-skills/skills/neo-agent-protocol Skill

    7★ repo

    Use this skill when an AI agent is executing software development, code generation, refactoring, debugging, or system architecture tasks to enforce strict harness principles, self-verification gates, non-destructive editing, context collapse defense, and human-in-the-loop boundaries.

  • Neo agentic design

    Benknightdark/neo-skills/skills/neo-agentic-design Skill

    7★ repo

    Use this skill when designing, evaluating, or implementing Agent workflows, prompt chains, routing, planning, reflection, multi-agent collaboration, memory management, or other framework-agnostic LLM orchestration patterns.

  • Neo sub agent

    Benknightdark/neo-skills/skills/neo-sub-agent Skill

    7★ repo

    Use this skill when the user asks to design, create, review, or convert sub-agents, custom agents, worker/reviewer/planner agents, background agents, or multi-agent workflows for Antigravity CLI, Codex, Claude Code, GitHub Copilot CLI, or neutral agent blueprints.

  • Orchestrator

    pranav8494/team-of-agents/skills/orchestrator Skill

    7★ repo

    Use when you are unsure which specialist to invoke, when a task spans multiple roles, when you want the system to plan before acting, or when you need parallel specialist agents dispatched to complete a complex task. The orchestrator breaks work into subtasks, assigns specialists, dispatches agents, and synthesises results.

  • Skill creator

    nemori-ai/agent_skills/agent_skills/skills/skill-creator Skill

    no license7★ repo

    Meta-skill for creating complex skill packages with scripts, data, and multi-file structures

  • Mcp builder

    AvinashP/AgentsAtlas/skills/mcp-builder Skill

    7★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    The same file is in 42 other repositories

  • Skill creator

    AvinashP/AgentsAtlas/skills/skill-creator Skill

    7★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 19 other repositories

  • Blender mcp

    braxtonROSE4/zorro-agent/optional-skills/creative/blender-mcp Skill

    7★ repo

    Control Blender directly from Zorro via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, and run arbitrary Blender Python (bpy) code. Use when user wants to create or modify anything in Blender.

  • Fastmcp

    braxtonROSE4/zorro-agent/optional-skills/mcp/fastmcp Skill

    7★ repo

    Build, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparing a FastMCP server for Claude Code, Cursor, or HTTP deployment.

  • Chroma

    braxtonROSE4/zorro-agent/optional-skills/mlops/chroma Skill

    7★ repo

    Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

  • Pinecone

    braxtonROSE4/zorro-agent/optional-skills/mlops/pinecone Skill

    7★ repo

    Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

  • Qdrant

    braxtonROSE4/zorro-agent/optional-skills/mlops/qdrant Skill

    7★ repo

    High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

  • Tensorrt llm

    braxtonROSE4/zorro-agent/optional-skills/mlops/tensorrt-llm Skill

    7★ repo

    Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

  • Torchtitan

    braxtonROSE4/zorro-agent/optional-skills/mlops/torchtitan Skill

    7★ repo

    Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

  • Claude code

    braxtonROSE4/zorro-agent/skills/autonomous-ai-agents/claude-code Skill

    7★ repo

    Delegate coding tasks to Claude Code (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative coding. Requires the claude CLI installed.

  • Hermes agent

    braxtonROSE4/zorro-agent/skills/autonomous-ai-agents/hermes-agent Skill

    7★ repo

    Complete guide to using and extending Zorro Agent — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference. Load this skill when helping users configure Zorro, troubleshoot issues, spawn agent instances, or make code contributions.

  • Native mcp

    braxtonROSE4/zorro-agent/skills/mcp/native-mcp Skill

    7★ repo

    Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Zorro Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

  • Godmode

    braxtonROSE4/zorro-agent/skills/red-teaming/godmode Skill

    7★ repo

    Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Zorro-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.

  • Llm wiki

    braxtonROSE4/zorro-agent/skills/research/llm-wiki Skill

    7★ repo

    Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.

  • Subagent driven development

    braxtonROSE4/zorro-agent/skills/software-development/subagent-driven-development Skill

    7★ repo

    Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).

  • Worktree manager

    smicolon/ai-kit/packs/worktree/skills/worktree-manager Skill

    7★ repo

    This skill should be used when the user mentions "worktree", "wt", "new branch workspace", "parallel development", "feature branch setup", "work on multiple branches", "separate workspace for branch", "docker port conflict", "database isolation", "worktreeinclude", "env isolation", or wants to manage git worktrees for parallel feature development.

  • Vs benchmark audit

    rgourley/quant-garage/skills/vs-benchmark-audit Skill

    no license7★ repo

    Take a book (weights per ticker), compute the daily portfolio return series, and run the full tearsheet with deflated Sharpe correction (Bailey & Lopez de Prado) plus rolling IC vs benchmark. Emits a verdict (real_alpha / possibly_alpha / essentially_beta / underperforming / no_edge_evident) based on DSR significance, alpha annualized, and beta. Answers "is this book actually alpha, honestly?" Requires Stocks Basic.

  • Crypto skill creator

    aomi-labs/skills/.claude/skills/crypto-skill-creator Skill

    7★ repo

    Step-by-step guide for creating enriched CryptoSkills agent skills. Use when building new protocol skills, contributing to the directory, or understanding the enriched skill pattern. Covers SKILL.md structure, YAML frontmatter, examples, docs, resources, templates, marketplace registration, and validation. Triggers: "create a skill", "add a protocol", "contribute a skill", "new skill template".

  • Solana agent kit

    aomi-labs/skills/.claude/skills/solana-agent-kit Skill

    7★ repo

    Comprehensive guide for building AI agents that interact with Solana blockchain using SendAI's Solana Agent Kit. Covers 60+ actions, LangChain/Vercel AI integration, MCP server setup, and autonomous agent patterns.

  • Codex

    bestagentkits/ck-skills/plugins/ck-skills/skills/codex Skill

    7★ repo

    Use OpenAI Codex CLI (GPT-5.5 + gpt-image-2) programmatically: second-opinion code review, GitHub PR audit, plan/spec auditing, edge-case discovery, style/persona prompting, and subscription-billed image generation for visual assets, decorations, infographics, banners. Activate whenever the user says 'codex', 'second opinion', 'audit plan', 'review PR with codex', 'generate image', 'create banner/illustration/visual asset', or wants a careful adversarial reader to catch what Claude (especially Opus) might skim past.

  • Hoo orchestrator

    shalintripathi/organic-os/plugin/skills/hoo-orchestrator Skill

    7★ repo

    Run an always-on SEO/AEO growth loop on your own site with Claude: pulls GA4 and Search Console signals, proposes fixes with the reasoning attached, applies approved changes to WordPress, verifies they landed, and learns from outcomes. Every write is human-approved. MIT, no telemetry, no scraping.

  • Yao geo knowledge base builder

    ShenyuanNext/wepr-growth-skills/skills/yao-geo-knowledge-base-builder Skill

    7★ repo

    Build evidence-backed GEO brand knowledge bases from official sites, product pages, help centers, white papers, sales materials, media releases, certifications, and trusted third-party sources. Use when asked to generate reusable brand fact cards, FAQ, prohibited expressions, source indexes, prompt input packs, or Word/PDF/HTML/Markdown four-format Chinese GEO knowledge-base deliverables for Kimi, Qianwen, DeepSeek, Doubao, Yuanbao, content production, monitoring, page design, or customer-service preparation.

  • Social engagement benchmark

    sam6dvpte34/social-media-skill/skills/social-engagement-benchmark Skill

    no license7★ repo

    Social Engagement Benchmark for cross-platform social media engagement benchmark collection, research, monitoring, analysis, and export. Use when the user asks to scrape, extract, collect, export, monitor, research, analyze, or find browser-visible cross-platform social media data for this workflow: Collect comparable engagement metrics for creators, brands, competitors, or campaigns. Covers searches such as Social Engagement Benchmark, cross-platform social media engagement benchmark scraper, cross-platform social media engagement benchmark extractor, cross-platform social media engagement benchmark export, cross-platform social media engagement benchmark research. Supports public or authorized browser-visible data through BrowserAct.

  • Image prompt compiler

    papperrollinggery/Paperrolling-DIRcreative-SKILL/skills/dircreative/image-prompt-compiler Skill

    no license7★ repo

    Compile JSON-first reference image prompts from visual bible, reference pack, and prompt pattern registry.

  • Video agent jianying editor

    chenyuxiaojin/video-agent-skills/video-agent-jianying-editor Skill

    7★ repo

    视频团队的剪映剪辑师。将音频、视觉素材、字幕合并为完整时间轴, 通过 VectCutAPI 生成剪映/CapCut 可直接导入的草稿项目。 与达芬奇剪辑师(video-agent-editor)并行工作,共享同一套输入文件, 由制片人(producer)决定调度哪个剪辑师。 当收到"导出剪映""生成剪映草稿""构建剪映项目"时触发, 或由制片人调度时自动触发。

  • Video agent operator

    chenyuxiaojin/video-agent-skills/video-agent-operator Skill

    7★ repo

    视频团队的运营分析师。分析抖音多账号数据,识别高表现内容特征, 给出选题建议和竞品洞察。支持从 CSV/Excel 文件或飞书多维表格读取数据。 当用户说"分析数据""看看最近表现""下期做什么选题"时触发。

  • Video agent producer

    chenyuxiaojin/video-agent-skills/video-agent-producer Skill

    7★ repo

    视频团队的制片人/总调度。接收用户主题,拆解为子任务,按顺序调度其他 Agent (operator → researcher → writer → storyboarder → voice + visual → editor(s) → publisher), 管理检查点和断点恢复。支持双剪辑师调度(达芬奇/剪映/两者)。 触发条件:"开始制作视频"、"创建视频项目"、"视频项目状态"、"继续视频项目"、"帮我选个题"

  • Video agent publisher

    chenyuxiaojin/video-agent-skills/video-agent-publisher Skill

    7★ repo

    视频团队的发布员。生成各平台(抖音/B站/YouTube)的发布元数据, 包括标题、描述、标签、BGM推荐,以及引用出处列表。 触发条件:"准备发布素材"、"生成封面和标题"、"生成发布信息"

  • Video agent researcher

    chenyuxiaojin/video-agent-skills/video-agent-researcher Skill

    7★ repo

    视频团队的通用调研员。围绕任意主题搜集网页文章和 YouTube 字幕, 分析素材提取核心论点,生成结构化大纲。当用户已有完整素材时, 切换为"整理模式",按视频叙事逻辑重组素材并产出详细整理稿。 触发条件:"搜索关于[主题]的素材"、"收集资料"、"帮我找文章和视频"、 "整理这篇文章"、"把这个素材变成大纲"、"用这篇文章出视频"

  • Video agent storyboarder

    chenyuxiaojin/video-agent-skills/video-agent-storyboarder Skill

    7★ repo

    视频团队的分镜师。将编剧的逐字稿拆解为逐句分镜表,为每句话设计具体的画面镜头。 通过 Python 脚本调用 Gemini Flash API 批量生成分镜,低成本高效率。 产出 storyboard.json(结构化数据)+ storyboard.md(可读版本)。 当收到"生成分镜表""设计画面""拆分镜头"时触发, 或由制片人(producer)调度时自动触发。

  • Video agent visual

    chenyuxiaojin/video-agent-skills/video-agent-visual Skill

    7★ repo

    视频团队的美术师。读取 storyboard.json,通过 GPTIMG2(gpt-image-2,OpenAI 兼容 API) 批量生成 2K 图片素材,支持并发调用和风格配置。 产出 visuals/*.png + visual-timeline.json + visual-report.md。 当收到"准备画面素材""获取视觉素材""生成图片"时触发, 或由制片人(producer)调度时自动触发。

  • Video agent voice

    chenyuxiaojin/video-agent-skills/video-agent-voice Skill

    7★ repo

    视频团队的配音师。将逐字稿转为语音和字幕,支持 MiniMax Speech-02(中文首选,全球#1)、 Edge-TTS(免费)、ElevenLabs(英文)、自录音四种模式。 MiniMax 支持 10 秒声音克隆,中文 WER 仅 2.25%。 能读取分镜表的情绪标注,生成带语速和情感控制的配音, 以及供自录音参考的配音指导表。 当收到"生成语音""处理音频""我录好音了"时触发, 或由制片人(producer)调度时自动触发。

  • Video agent writer

    chenyuxiaojin/video-agent-skills/video-agent-writer Skill

    7★ repo

    视频团队的编剧。根据大纲生成逐字稿,负责文字内容、叙事结构、节奏控制。 支持反常识/故事/问题 3 种开头模式。编剧只写文字,画面设计由分镜师负责。 当收到"生成逐字稿""根据大纲写稿""把大纲扩展成完整脚本"时触发, 或由制片人(producer)调度时自动触发。

  • Handoff summary

    nikhilw/structured-agentic-workflow/skills/handoff-summary Skill

    7★ repo

    Set of skills and workflows to ensure humans and agents stay focused while vibe-coding.

  • Workflow config

    nikhilw/structured-agentic-workflow/skills/workflow-config Skill

    7★ repo

    Configure the Structured Agentic Development Workflow — set testing methodology (TDD/BDD), output style (caveman brevity), and persist preferences to agent memory.

  • Llm radiology use

    aizech/clinical-skills/skills/llm-radiology-use Skill

    7★ repo

    Use LLM APIs for radiology tasks. Also use when integrating medical LLMs (MedPaLM, MedLM, Google Health, Amazon HealthLake) for report analysis, clinical reasoning, or radiology AI workflows.