Context & AI engineering
25,729 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
Just-Agent/just-product-factor/skills/5-factor-evals Skill
1★ repoReusable Factor Skills for Agent-native product optimization
Just-Agent/just-product-factor/skills/7-factor-mcp Skill
1★ repoReusable Factor Skills for Agent-native product optimization
Just-Agent/just-product-factor/skills/9-factor-rag Skill
1★ repoReusable Factor Skills for Agent-native product optimization
stella/skillguard/fixtures/evasive/encoded-eval Skill
1★ repoLocal-first security scanner and policy gate for Agent Skills
stella/skillguard/fixtures/malicious/install-hook Skill
1★ repoLocal-first security scanner and policy gate for Agent Skills
s-frantz/agent-memory-trellis/skills/handoff Skill
1★ repoSession continuity — orients from or writes project-state.md depending on session phase: picks up context at the start of a session, saves it at the end.
ming-14/PTY-Agent Skill
no license1★Interactive CLI program proxy via pseudo-terminal (PTY). Use when: (1) must maintain ongoing dialog with interactive programs (REPLs, debuggers, Servers) — send input and wait for specific prompts; (2) process may block, crash, or pop up GUI windows — need real-time state detection; (3) simulating user interaction tests; (4) download large files. DO NOT use for: non-interactive scripts, web/HTTP API calls, GUI interfaces. If a plain script suffices, do not use this tool.
rtwsvj/skill-switch/tests/fixtures/skills-malicious/tamper-claude-settings Skill
1★ repoA skill that rewrites the agent config to grant itself permissions. Malicious fixture for audit tests; never install.
rtwsvj/skill-switch/tests/fixtures/skills-portability/claude-flavored Skill
1★ repoUse when testing portability warnings for Claude-specific fields.
matt-bat/agent-skill-foundry/packs/minimal Skill
no license1★ repoUse for low-complexity Agent work that needs concise responses, dependency-correct sequencing, and safe deterministic command execution without heavier governance.
ed1son99/skills/skills/agent-tools/tools-langchain-agent Skill
1★ repoLangChain/LangGraph Agent 脚手架
ed1son99/skills/skills/agent-tools/tools-multi-agent-optimize Skill
1★ repo多 Agent 优化应用栈
ed1son99/skills/skills/agent-tools/tools-multi-agent-review Skill
1★ repo多 Agent 综合代码审查
ed1son99/skills/skills/agent-tools/tools-prompt-optimize Skill
1★ repoAI Prompt 优化
ed1son99/skills/skills/architecture-planning/context-engineering Skill
1★ repo上下文工程 — 优化 Agent 上下文配置
ed1son99/skills/skills/autonomous-ai-agents/ai-pipeline-orchestrator Skill
1★ repoOrchestrate multi-AI pipelines: Hermes coordinates Claude (brain/reviewer) and Codex (executor/writer) in a chained workflow
ed1son99/skills/skills/autonomous-ai-agents/claude-code Skill
1★ repoDelegate coding to Claude Code CLI (features, PRs).
ed1son99/skills/skills/autonomous-ai-agents/hermes-agent Skill
1★ repoConfigure, extend, or contribute to Hermes Agent.
ed1son99/skills/skills/claude-config/claude-api Skill
1★ repoClaude API 参考 — 模型 ID、定价、参数、流式、工具使用、MCP
ed1son99/skills/skills/claude-config/using-agent-skills Skill
1★ repoAgent Skill 发现与调用 — 元技能,管理所有其他 skill 的发现和调用
ed1son99/skills/skills/creative/agent-reach Skill
1★ repo全网调研 — 13 平台多后端路由搜索
ed1son99/skills/skills/creative/claude-design Skill
1★ repoDesign one-off HTML artifacts (landing, deck, prototype).
ed1son99/skills/skills/creative/touchdesigner-mcp Skill
1★ repoControl a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
ed1son99/skills/skills/devops/kanban-orchestrator Skill
1★ repoDecomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
ed1son99/skills/skills/devops/kanban-worker Skill
1★ repoPitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
ed1son99/skills/skills/mlops/evaluating-llms-harness Skill
1★ repolm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
ed1son99/skills/skills/plugin-performance/performance-benchmark Skill
1★ repo负载测试与性能基准 — 智能场景生成
ed1son99/skills/skills/research/llm-wiki Skill
1★ repoKarpathy's LLM Wiki: build/query interlinked markdown KB.
ed1son99/skills/skills/software-development/hermes-agent-skill-authoring Skill
1★ repoAuthor in-repo SKILL.md: frontmatter, validator, structure, and writing-quality principles.
ed1son99/skills/skills/super-claude/sc-agent Skill
1★ repoSuperClaude Agent 管理
ed1son99/skills/skills/workflow-automation/workflow-create-prompt Skill
1★ repo创建优化的 XML 结构化 Prompt
ed1son99/skills/skills/workflow-automation/workflow-handoff-create Skill
1★ repo创建任务交接文档
ed1son99/skills/skills/workflow-automation/workflow-prompt-run Skill
1★ repo并行或顺序执行多个 Prompt
Ghosteken/agent-harness/archive/skills-community/acceptance-orchestrator Skill
1★ repoUse when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/agent-framework-azure-ai-py Skill
1★ repoBuild persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
The same file is in 7 other repositories
Ghosteken/agent-harness/archive/skills-community/agent-manager-skill Skill
1★ repoManage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The same file is in 7 other repositories
Ghosteken/agent-harness/archive/skills-community/agent-memory-mcp Skill
1★ repoA hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
The same file is in 7 other repositories
Ghosteken/agent-harness/archive/skills-community/agent-memory-systems Skill
1★ repoMemory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.
The same file is in 7 other repositories
Agent orchestration improve agent
Ghosteken/agent-harness/archive/skills-community/agent-orchestration-improve-agent Skill
1★ repoSystematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
The same file is in 7 other repositories
Agent orchestration multi agent optimize
Ghosteken/agent-harness/archive/skills-community/agent-orchestration-multi-agent-optimize Skill
1★ repoOptimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
The same file is in 7 other repositories
Ghosteken/agent-harness/archive/skills-community/agent-orchestrator Skill
1★ repoMeta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/agent-tool-builder Skill
1★ repoTools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
The same file is in 7 other repositories
Ghosteken/agent-harness/archive/skills-community/agentic-actions-auditor Skill
1★ repoAudits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.
The same file is in 6 other repositories
Ghosteken/agent-harness/archive/skills-community/agents-md Skill
1★ repoThis skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/ai-dev-jobs-mcp Skill
1★ repoSearch 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/ai-engineer Skill
1★ repoBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
The same file is in 6 other repositories
Ghosteken/agent-harness/archive/skills-community/ai-ml Skill
1★ repoAI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
Ghosteken/agent-harness/archive/skills-community/ai-seo Skill
1★ repoOptimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems. Use when improving AI visibility, answer engine optimization, or citation readiness.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/antigravity-agent-manager Skill
1★ repoConfigure and orchestrate parallel agents using the standalone Antigravity 2.0 Agent Manager and Antigravity IDE.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/apple-notes-search Skill
1★ repoSemantic + keyword search and connection-discovery across the user's own Apple Notes via the apple-notes MCP server. Use when the user wants to find, recall, or synthesize something from their notes, or surface non-obvious bridges/related notes. macOS, on-device.
Ghosteken/agent-harness/archive/skills-community/clarvia-aeo-check Skill
1★ repoScore any MCP server, API, or CLI for agent-readiness using Clarvia AEO (Agent Experience Optimization). Search 15,400+ indexed tools before adding them to your workflow.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/claude-ally-health Skill
1★ repoA health assistant skill for medical information analysis, symptom tracking, and wellness guidance.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/claude-api Skill
1★ repoBuild apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/claude-code-expert Skill
1★ repoEspecialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/claude-code-guide Skill
1★ repoTo provide a comprehensive reference for configuring and using Claude Code (the agentic coding tool) to its full potential. This skill synthesizes best practices, configuration templates, and advanced usage patterns.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/claude-d3js-skill Skill
1★ repoThis skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.
The same file is in 6 other repositories
Claude in chrome troubleshooting
Ghosteken/agent-harness/archive/skills-community/claude-in-chrome-troubleshooting Skill
1★ repoDiagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/claude-monitor Skill
1★ repoMonitor de performance do Claude Code e sistema local. Diagnostica lentidao, mede CPU/RAM/disco, verifica API latency e gera relatorios de saude do sistema.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/claude-scientific-skills Skill
1★ repoScientific research and analysis skills
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/claude-settings-audit Skill
1★ repoAnalyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects tech stack, build tools, and monorepo structure.
The same file is in 5 other repositories