Context & AI engineering
25,745 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
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/agent-evaluation Skill
5★ repoTesting and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks
The same file is in 7 other repositories
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/agent-governance Skill
5★ repoPatterns for adding safety, trust, and policy enforcement to AI agent systems -- control which tools agents can call, what content they process, and maintain accountability through audit trails.
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/agent-memory-architecture Skill
5★ repoThis skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to context-compression, and token-efficiency tactics to context-optimization.
The same file is in 1 other repository
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/agent-supply-chain Skill
5★ repoGenerate and verify integrity manifests for AI agent plugins and tools -- detect tampering, enforce version pinning, and establish supply chain provenance (the SLSA/Sigstore gap for agent ecosystems).
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/agent-tool-design Skill
5★ repo284 curated plugins for AI assistants across 16 categories: security, Azure, documentation, code quality, cloud infrastructure, and more. Works with GitHub Copilot. Drop into .github/skills/local/ and go.
The same file is in 1 other repository
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/agentic-actions-auditor Skill
5★ 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
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/agentic-eval Skill
5★ repo284 curated plugins for AI assistants across 16 categories: security, Azure, documentation, code quality, cloud infrastructure, and more. Works with GitHub Copilot. Drop into .github/skills/local/ and go.
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/ai-agent-design Skill
5★ repoDesign autonomous AI agents that reason, plan, and execute tasks
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/copilot-sdk Skill
5★ repo284 curated plugins for AI assistants across 16 categories: security, Azure, documentation, code quality, cloud infrastructure, and more. Works with GitHub Copilot. Drop into .github/skills/local/ and go.
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/foundry-agent-platform Skill
5★ repoMicrosoft Foundry agent deployment, orchestration, and cloud-native AI service patterns
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/llm-model-selection Skill
5★ repoChoosing the right model for the task — power vs. cost vs. speed.
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/make-skill-template Skill
5★ repoCreate new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional scripts/references/assets folders.
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/mcp-builder Skill
5★ repoBuild MCP servers for LLM tool integration — Python (FastMCP), Node/TypeScript (MCP SDK), or C#/.NET (Microsoft MCP SDK)
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/mcp-development Skill
5★ repoDomain: AI Infrastructure
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/multi-agent-architect Skill
5★ repoDesign and optimize production-grade multi-agent systems with LangGraph, LangChain, and DeepAgents for complex AI workflows.
The same file is in 4 other repositories
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/multi-agent-orchestration Skill
5★ repoCoordinate multiple AI agents for complex tasks — decomposition, delegation, and synthesis
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/multi-agent-patterns Skill
5★ repoThis skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on whether multiple agents are justified.
The same file is in 1 other repository
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/prompt-builder Skill
5★ repoCreate and validate .prompt.md files that pass brain-qa on first attempt
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/prompt-engineering Skill
5★ repoCraft effective prompts that get the best results from language models.
fabioc-aloha/Alex_Skill_Mall/plugins/ai-agents/rag-architecture Skill
5★ repo284 curated plugins for AI assistants across 16 categories: security, Azure, documentation, code quality, cloud infrastructure, and more. Works with GitHub Copilot. Drop into .github/skills/local/ and go.
fabioc-aloha/Alex_Skill_Mall/plugins/architecture-patterns/saga-orchestration Skill
5★ repoImplement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building event-driven saga coordinators for travel booking systems that must roll back hotel, flight, and car rental reservations atomically, or debugging stuck saga states in production where compensation steps never complete.
Workflow orchestration patterns
fabioc-aloha/Alex_Skill_Mall/plugins/architecture-patterns/workflow-orchestration-patterns Skill
5★ repoDesign durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
fabioc-aloha/Alex_Skill_Mall/plugins/cloud-infrastructure/entra-agent-id Skill
5★ repo284 curated plugins for AI assistants across 16 categories: security, Azure, documentation, code quality, cloud infrastructure, and more. Works with GitHub Copilot. Drop into .github/skills/local/ and go.
fabioc-aloha/Alex_Skill_Mall/plugins/code-quality/repository-readiness-eval Skill
5★ repoEvaluate a repository's readiness for AI-assisted development across 4 axes: code understanding, dependency restore, build success, and test execution. Use when onboarding to a new repo, assessing CI readiness, or validating that an AI agent can work effectively in a codebase.
fabioc-aloha/Alex_Skill_Mall/plugins/data-analytics/biome-powerbi-query Skill
5★ repoExecute read-only DAX queries against Power BI semantic models via the Power BI MCP server -- metadata discovery with INFO.VIEW functions and data retrieval with EVALUATE.
fabioc-aloha/Alex_Skill_Mall/plugins/data-analytics/flint-chart-plugin/skills/flint-chart Skill
5★ repoUse when the user wants to visualize data — from 'which chart should I use?' to 'render this'. Helps pick the right chart from the analytical question (comparison / trend / distribution / relationship / proportion / flow / KPI), then authors a ChartAssemblyInput and renders via the flint-chart-mcp server (Vega-Lite / ECharts / Chart.js). Transform data before Flint; style tweaks after Flint.
fabioc-aloha/Alex_Skill_Mall/plugins/data-analytics/prompt-2-data Skill
5★ repo284 curated plugins for AI assistants across 16 categories: security, Azure, documentation, code quality, cloud infrastructure, and more. Works with GitHub Copilot. Drop into .github/skills/local/ and go.
fabioc-aloha/Alex_Skill_Mall/plugins/data-analytics/semantic-overlap-detection Skill
5★ repoAnalyze a semantic model (via MCP or TMDL) to find columns whose value domains overlap, classify ambiguity types, generate proposed descriptions/rules/exclusions, and produce a review Excel for domain experts. Use when a semantic model has columns whose values overlap across tables or hierarchies, when Copilot picks the wrong column for ambiguous queries, when preparing a model for Prep data for AI, or when auditing a model for attribute collisions before connecting a data agent.
fabioc-aloha/Alex_Skill_Mall/plugins/devops-process/copilot-usage-metrics Skill
5★ repoRetrieve and display GitHub Copilot usage metrics for organizations and enterprises using the GitHub CLI and REST API.
fabioc-aloha/Alex_Skill_Mall/plugins/image-generation/gpt-image-2 Skill
5★ repo面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用:(A) Garden 本地模式,通过 OpenAI 兼容接口直接出图并落盘;(B) Host-Native 模式,把本 Skill 当作提示词工程指引,把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图;(C) Advisor 模式,宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板,覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。
The same file is in 2 other repositories
fabioc-aloha/Alex_Skill_Mall/plugins/media-graphics/image-embedding-size-limits Skill
5★ repoImage embedding size limits in markdown — base64 bloats 33%, use file references for images over 50KB
fabioc-aloha/Alex_Skill_Mall/plugins/media-graphics/image-storage-embedding-split Skill
5★ repoStoring images at embed size loses the original:
fabioc-aloha/Alex_Skill_Mall/plugins/reasoning-metacognition/anti-hallucination Skill
5★ repoRecognize and prevent confabulation — when you don't know, say so.
fabioc-aloha/Alex_Skill_Mall/plugins/supervisor-fleet/ai-memory-setup Skill
5★ repoDetect, create, and manage the AI-Memory fleet communication channel. Fires on bootstrap, session start (announcements), and feedback writes.
fabioc-aloha/Alex_Skill_Mall/plugins/supervisor-fleet/on-call-handoff-patterns Skill
5★ repoEffective patterns for on-call shift transitions, ensuring continuity, context transfer, and reliable incident response across shifts.
The same file is in 6 other repositories
fabioc-aloha/Alex_Skill_Mall/plugins/supervisor-fleet/subagent-orchestrator Skill
5★ repoCoordinate quota-aware parallel subagents for large, multi-file Antigravity tasks.
The same file is in 4 other repositories
akunzai/agent-skills/skills/mem-promote Skill
5★ repoInteractively promote verified [Candidate] daily-log notes into durable long-term memory (global ~/.agents/AGENTS.md, or project AGENTS.md / CLAUDE.md), and prune those long-term files. Use when reviewing candidates for promotion or consolidating durable conventions.
akunzai/agent-skills/skills/mem-recall Skill
5★ repoSearch short-term memory on demand — project .memories/ and ~/.agents/memories/ for handoffs, candidates, and prior task state not already loaded by AGENTS.md / CLAUDE.md.
akunzai/agent-skills/skills/mem-setup Skill
5★ repoWire each installed coding agent's native global memory file to one canonical ~/.agents/AGENTS.md, so Claude Code, Codex, OpenCode, Antigravity/Gemini, and pi all read the same durable cross-agent memory. Use to set up or refresh global memory bridging across agents.
tea-x-random/unity-game-skills/skills/unity-mcp-bridge Skill
5★ repoDrive a live Unity Editor through CoplayDev MCP for Unity from GPT/Codex, Claude Code, or another MCP client. Use for real Editor actions: scenes, GameObjects, components, prefabs, materials, scripts, Play Mode, tests, console, asset import and builds. Covers HTTP setup, tool groups, editor readiness, domain-reload reconnects, no_unity_session recovery, headless iOS builds, and device-only debug HUDs. This is the execution layer beneath unity-game-director and other unity skills; use the documented headless CLI fallback when MCP is unavailable.
tea-x-random/unity-game-skills/skills/unity-mcp-skill Skill
5★ repoOrchestrate Unity Editor via MCP (Model Context Protocol) tools and resources. Use when working with Unity projects through MCP for Unity - creating/modifying GameObjects, editing scripts, managing scenes, running tests, or any Unity Editor automation. Provides best practices, tool schemas, and workflow patterns for effective Unity-MCP integration.
Kbediako/evergreen-codex-skills/skills/native-agent-deliberation Skill
5★ repoFrame consequential or ambiguous decisions through distinct evidence-backed viewpoints, tradeoffs, and dissent. Use for brainstorming among competing strategies, architecture choices, risk review, or a decision whose assumptions should be challenged before execution.
Kbediako/evergreen-codex-skills/skills/native-agent-evals Skill
5★ repoEvaluate or audit Codex native Multi-Agent V2 behavior with small reproducible probes and structural rollout evidence. Use for V2 surface checks, direct-tool lifecycle behavior, bounded fanout, interruption semantics, resume behavior, or skill-invocation evidence.
Kbediako/evergreen-codex-skills/skills/native-agent-skill-validation Skill
5★ repoEvergreen, generally useful Codex skills designed to stay valuable as models improve.
Kbediako/evergreen-codex-skills/skills/native-subagents-first Skill
5★ repoEvergreen, generally useful Codex skills designed to stay valuable as models improve.
soia-team/soia-open-skills/skills/soia-meta-skill-release Skill
5★ repo域仓正式发版(dev→main、tag、Release、notes、CHANGELOG)与发布收尾:市场 pin 刷新、客户端更新、旧名清理、WorkBuddy 专家安装、dev 快照试装。触发:「正式发版」「发布技能」「更新插件」「技能发布收尾」「装到 WorkBuddy」「试装 dev」
khasky/awesome-agent-skills/skills/awesome-humanize-en Skill
5★ repoUse when: the user asks you to check, rewrite, humanize, or de-slop English text that shows signs of AI generation (ChatGPT, Claude, Gemini, Grok, DeepSeek, GPT-5, Qwen, Llama, any LLM). Trigger for requests like: 'humanize this', 'make it sound human / natural', 'remove the AI voice', 'this reads like a chatbot', 'AI detector for English', 'check for AI', 'de-slop', 'reduce AI-isms', remove clichés / filler / corporate jargon / emoji bullet lists 🚀 / gratuitous em-dashes / sycophantic tone / fabricated sources. Also when visible copy-paste chatbot markers are present: `:contentReference`, `?utm_source=chatgpt.com`, `oai_citation`, `grok_card://`, `vertexaisearch`, `turn0search`, `[cite_start]`, `[cite: 8]`. Do NOT use: text that is not in English, source code / scripts (even about NLP), legal documents (officialese is the genre), literary prose / poetry / résumés (there the em-dash, rhythm and compression are an authorial device).
cynco-labs/ai-accounting-skills/accounting-engagement/skills/statutory-handoff Skill
5★ repoHand locked figures to tax/statutory filing workflows. Use when SSM, filing pack, or tax handoff.
cynco-labs/ai-accounting-skills/finalisation-accounting/skills/statutory-handoff Skill
5★ repoHand locked figures to tax/statutory filing workflows. Use when SSM, filing pack, or tax handoff.
skillsaiagent/aiskills/skills/ai-agent-browser Skill
no license5★ repo业务诊断助手适合市场营销、运营、产品、销售在用户提出“这件事该怎么做”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
Ai creator commercial value benchmark
skillsaiagent/aiskills/skills/ai-creator-commercial-value-benchmark Skill
no license5★ repo业务诊断助手适合运营、市场营销、内容媒体、电商在用户提出“这件事该怎么做”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
skillsaiagent/aiskills/skills/ai-gpt-image-2 Skill
no license5★ repo视觉质量诊断助手适合市场营销、运营、内容媒体、电商在用户提出“这张图够发布吗”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
The same file is in 1 other repository
Ai knowledge base launch quality check
skillsaiagent/aiskills/skills/ai-knowledge-base-launch-quality-check Skill
no license5★ repo文案诊断助手适合technical、管理者、software、知识库在用户提出“这段文案能打动人吗”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
skillsaiagent/aiskills/skills/ai-visual-prompt-review Skill
no license5★ repo视觉质量诊断助手适合设计、运营、市场营销、内容创作者在用户提出“这张图够发布吗”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
The same file is in 1 other repository
rikitrader/glaw/seats/glaw-mc-cfo-agent Skill
no license5★ repoMission Control CFO Agent — autonomous financial intelligence agent for Example Holdings. Reads/writes Google Sheets as source of truth, calls CFO Dashboard API for live KPIs, and applies roofer-accounting domain expertise for analysis, forecasting, fraud detection, and board reporting. Designed to run as an MC agent session. Use when: "cfo agent", "financial agent", "mc cfo", "agent financials", "update financials", "pull from sheets", "push to dashboard", "cfo report", "agent accounting", "mc accounting"
rikitrader/glaw/seats/glaw-sec-enforcement-swarm Skill
no license5★ repoElite SEC enforcement & securities-investigation virtual division: an 11-seat swarm (SEC Enforcement Attorney, SEC Investigator, Forensic Accountant, Market Manipulation Analyst, Insider Trading Analyst, FCPA Investigator, Whistleblower Analyst, Litigation Support Specialist, Expert Witness Report Generator, Wells Notice Response Generator, 10-K/10-Q Risk Analyzer) that run solo or coordinated. Routes a matter to the right seat(s), runs an adversarial RED/BLUE pass, and ships court/SEC-ready deliverables with a full audit trail and ZERO fabricated data. Use for: "SEC investigation", "respond to a Wells Notice", "build a securities-fraud case", "10b-5 / Rule 10b5-1", "pump and dump", "spoofing / layering / wash trades", "market manipulation", "insider trading", "MNPI / tipper-tippee", "FCPA / foreign bribery / books and records", "whistleblower tip / Form TCR", "expert witness report / Rule 26 / Daubert", "analyze 10-K / 10-Q risk", "revenue recognition fraud", "did this company commit securities fraud".
rikitrader/glaw/seats/glaw-valuation-409a-architect Skill
no license5★ repoGLAW 409A valuation orchestrator for audit-ready DRAFT work-product. Validates intake, runs DCF, market comps, VC method, PWERM, latest priced-round anchor, liquidation waterfall with conversion test, OPM/Black-Scholes allocation, round backsolve, DLOM, common FMV, and strike-price math; writes results and audit logs; routes RED-team and Chief/appraiser sign-off gates. Use for full 409A orchestration, defensible draft valuations, priced-round cross-checks, and audit-trail report generation.
initxy/initxy-skills/skills/self/handoff Skill
5★ repoCompress the current conversation and work progress into a handoff note. Use for handoff, handover, resuming, summarizing progress, or letting a later session continue.
Kong/ai-marketplace/plugins/kong-konnect/skills/kong-skill-authoring Skill
5★ repoCreate or refactor a skill in this repo. Use when deciding extend-versus-create, classifying domain/tool/router ownership, tightening a description, or reviewing a skill package against repo policy. Not for the product workflow itself.
Kong/ai-marketplace/plugins/kong-konnect/skills/konnect-ai-gateway Skill
5★ repoOperate Konnect AI Gateway request flow, provider/model routing, AI Proxy behavior, prompt/response controls, and LLM analytics. Use when the issue is inside AI Gateway, not generic prompt engineering, provider SDK debugging, or non-AI Gateway rollout.