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
onfire7777/universal-ai-skills-library/skills/claude-native-theme-factory Skill
14★ repoToolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
Claude native web artifacts builder
onfire7777/universal-ai-skills-library/skills/claude-native-web-artifacts-builder Skill
14★ repoSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
onfire7777/universal-ai-skills-library/skills/claude-native-webapp-testing Skill
14★ repoToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
onfire7777/universal-ai-skills-library/skills/claude-native-xlsx Skill
14★ repoUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
onfire7777/universal-ai-skills-library/skills/compress Skill
14★ repoCompress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress FILEPATH or "compress memory file"
Conducting memory forensics with volatility
onfire7777/universal-ai-skills-library/skills/conducting-memory-forensics-with-volatility Skill
14★ repoPerforms memory forensics analysis using Volatility 3 to extract evidence of malware execution, process injection, network connections, and credential theft from RAM dumps captured during incident response. Covers memory acquisition, process analysis, DLL inspection, and malware detection. Activates for requests involving memory forensics, RAM analysis, Volatility framework, memory dump investigation, volatile evidence analysis, or live memory acquisition.
onfire7777/universal-ai-skills-library/skills/context-engineering-advisor Skill
14★ repoDiagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
Deploying edr agent with crowdstrike
onfire7777/universal-ai-skills-library/skills/deploying-edr-agent-with-crowdstrike Skill
14★ repoDeploys and configures CrowdStrike Falcon EDR agents across enterprise endpoints to enable real-time threat detection, behavioral analysis, and automated response. Use when onboarding endpoints to EDR coverage, configuring detection policies, or integrating Falcon telemetry with SIEM platforms. Activates for requests involving CrowdStrike deployment, Falcon sensor installation, EDR policy configuration, or endpoint detection and response.
onfire7777/universal-ai-skills-library/skills/design-hook Skill
14★ repoDesign a Uniswap V4 hook architecture without code generation. Use when user wants to plan a hook, understand which callbacks to use, or review an architecture before building. Returns a design document, not code.
onfire7777/universal-ai-skills-library/skills/dispatching-parallel-agents Skill
14★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
onfire7777/universal-ai-skills-library/skills/dmux-workflows Skill
14★ repoMulti-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
onfire7777/universal-ai-skills-library/skills/embedding-fusion-strategy Skill
14★ repoUse when designing embedding strategies that fuse semantic and structural information for knowledge graphs. Invoke when user mentions node embeddings, structural embeddings, semantic embeddings, contrastive alignment, embedding fusion, vector representations for graphs, or combining text and graph signals. Provides embedding selection, fusion design, and implementation guidance.
onfire7777/universal-ai-skills-library/skills/eval-harness Skill
14★ repoFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
The same file is in 1 other repository
onfire7777/universal-ai-skills-library/skills/everything-claude-code Skill
14★ repoDevelopment conventions and patterns for everything-claude-code. JavaScript project with conventional commits.
onfire7777/universal-ai-skills-library/skills/five-agent-captain-merge-gate Skill
14★ repoUse before the five-agent-dev-team Captain Integrator merges, rebases, labels ready-to-merge, pushes main, or advances main build state.
onfire7777/universal-ai-skills-library/skills/five-agent-ci-debug Skill
14★ repoUse when five-agent-dev-team GitHub Actions, Gitleaks, Docker, audit, lint, test, or formatting checks fail.
onfire7777/universal-ai-skills-library/skills/five-agent-pr-handoff Skill
14★ repoUse when a five-agent-dev-team automation opens, updates, labels, or hands off a pull request.
onfire7777/universal-ai-skills-library/skills/five-agent-preflight-check Skill
14★ repoUse before any five-agent-dev-team automation mutates files, opens PRs, updates branches, or performs Captain integration.
onfire7777/universal-ai-skills-library/skills/five-agent-security-review Skill
14★ repoUse for five-agent-dev-team secret handling, workflow permissions, Docker safety, dependency audit, local binding, and supply-chain review.
onfire7777/universal-ai-skills-library/skills/five-agent-state-update Skill
14★ repoUse when updating five-agent-dev-team swarm state, ledger entries, blockers, or next-stage handoffs.
onfire7777/universal-ai-skills-library/skills/frame Skill
14★ repoA bridge agent that leverages the Figma MCP Server to extract and structure design context, delivering it to implementation agents. Used when bridging Figma designs to code, managing Code Connect, or extracting design system rules.
onfire7777/universal-ai-skills-library/skills/gbrain Skill
14★ repoUse when the user asks for GBrain, personal knowledge brain setup, brain-first retrieval, local PGLite brain, hybrid RAG search, gbrain import/query/sync/embed, GBrain skills, Minions, durable agent jobs, soul-audit, brain maintenance, or integrating GBrain with gstack, Hermes, OpenClaw, Claude Code, or Codex.
onfire7777/universal-ai-skills-library/skills/git-guardrails-claude-code Skill
14★ repoSet 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
onfire7777/universal-ai-skills-library/skills/gpt-tasteskill Skill
14★ repoElite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
onfire7777/universal-ai-skills-library/skills/graphrag-evaluation Skill
14★ repoUse when evaluating GraphRAG system quality across knowledge graph completeness, retrieval relevance, answer correctness, and reasoning verification. Invoke when user mentions evaluate GraphRAG, quality metrics, benchmark, hallucination reduction, answer correctness, multi-step reasoning evaluation, test my GraphRAG, or measure RAG performance. Provides evaluation frameworks, metric selection, and testing protocols.
onfire7777/universal-ai-skills-library/skills/gstack Skill
14★ repoUse when the user explicitly asks for gstack, Garry Tan's AI engineering stack, gstack methodology skills, gstack browser/PDF tooling, gstack office hours, gstack review, gstack QA, gstack ship, gstack security review, or gstack integration with Claude Code, Codex, OpenCode, Hermes, OpenClaw, Kiro, Cursor, or GBrain.
onfire7777/universal-ai-skills-library/skills/hone Skill
14★ repoAI CLI configuration auditing and optimization agent. Collects official best practices for Codex CLI (~/.codex/), Gemini CLI (~/.gemini/), and Claude Code (~/.claude/) from the web, analyzes config.toml/settings.json/CLAUDE.md/GEMINI.md/AGENTS.md/permissions/commands/hooks/rules/MCP/extensions, and proposes improvements in Before/After diff format. Does not edit configurations directly.
Html ppt obsidian claude gradient
onfire7777/universal-ai-skills-library/skills/html-ppt-obsidian-claude-gradient Skill
14★ repoCreate GitHub-dark gradient decks for developer workflows, agents, MCP systems, and technical tutorials.
onfire7777/universal-ai-skills-library/skills/lightpanda-browser/references Skill
14★ repoLightpanda browser, drop-in replacement for Chrome and Openclaw default browser - faster and lighter for tasks without graphical rendering like data retrieval. Use it via MCP server, CLI fetch, or CDP with Playwright/Puppeteer.
onfire7777/universal-ai-skills-library/skills/llm-security Skill
14★ repoSecurity guidelines for LLM applications based on OWASP Top 10 for LLM 2025. Use when building LLM apps, reviewing AI security, implementing RAG systems, or asking about LLM vulnerabilities like 'prompt injection' or 'check LLM security'. IMPORTANT: Always consult this skill when building chatbots, AI agents, RAG pipelines, tool-using LLMs, agentic systems, or any application that calls an LLM API (OpenAI, Anthropic, Gemini, etc.) — even if the user doesn't explicitly mention security. Also use when users import 'openai', 'anthropic', 'langchain', 'llamaindex', or similar LLM libraries.
onfire7777/universal-ai-skills-library/skills/master-skill-orchestrator Skill
14★ repoThe master conductor for all 630+ installed skills. Activates automatically on every task to determine which skills to apply, in what order, and how to combine them. Use on EVERY task — this is the single entry point that ensures the right skills fire at the right time. Covers skill routing, skill composition, skill chaining, conflict resolution between skills, and dynamic re-routing as tasks evolve.
onfire7777/universal-ai-skills-library/skills/mcp-builder Skill
14★ repoGuide 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).
onfire7777/universal-ai-skills-library/skills/mcp-server-patterns Skill
14★ repoBuild MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
The same file is in 1 other repository
onfire7777/universal-ai-skills-library/skills/memory-retrieval-learning Skill
14★ repoUse when long-term knowledge retention is needed (weeks to months), studying for exams or certifications, learning new job skills or technology, mastering substantial material that requires systematic review, combating forgetting through spaced repetition and retrieval practice, or when user mentions studying, memorizing, learning plans, spaced repetition, flashcards, active recall, or durable learning.
onfire7777/universal-ai-skills-library/skills/meta-prompt-engineering Skill
14★ repoUse when prompts produce inconsistent or unreliable outputs, need explicit structure and constraints, require safety guardrails or quality checks, involve multi-step reasoning that needs decomposition, need domain expertise encoding, or when user mentions improving prompts, prompt templates, structured prompts, prompt optimization, reliable AI outputs, or prompt patterns.
onfire7777/universal-ai-skills-library/skills/model-selector Skill
14★ repoSet and manage the preferred backbone LLM for compatible AI-agent workflows. Supports manual model selection, automatic best-model selection based on task type, and a cached/refreshable leaderboard of the latest frontier models from OpenRouter. Toggle on/off via chat commands. Use when the user says "model-selector", "set model", "change model", "best model", "auto model", "switch model", "model-selector on", "model-selector off", "list models", "show models", "model status", "recommend model", "refresh models", or asks which AI model to use for a task.
onfire7777/universal-ai-skills-library/skills/multi-model-code-auditor Skill
14★ repoRun a comprehensive security, privacy, and bug audit on any codebase using the absolute best frontier AI models via OpenRouter API. Dynamically discovers the latest models, uses model-specific elite prompt engineering, merges findings by consensus, implements fixes, and runs a verification re-audit. Use when the user requests a code audit, security review, vulnerability scan, bug audit, or asks to review code with multiple AI models.
onfire7777/universal-ai-skills-library/skills/n8n-mcp-tools-expert Skill
14★ repoExpert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
onfire7777/universal-ai-skills-library/skills/nexus Skill
14★ repoOrchestrator overseeing specialist AI agent teams. Decomposes requests, designs minimal agent chains, and in AUTORUN mode internally executes each agent role to automatically progress to the final output. Used when multi-agent collaboration is required.
onfire7777/universal-ai-skills-library/skills/notebooklm-mcp-cli Skill
14★ repoUse when working with Google NotebookLM through jacob-bd/notebooklm-mcp-cli: listing or creating notebooks, adding sources, querying notebooks, generating audio or studio artifacts, revising slides, downloading artifacts, sharing notebooks, syncing Drive sources, running cross-notebook queries, configuring the NotebookLM MCP server, or diagnosing NotebookLM CLI authentication. Prefer this over generic Google or MCP skills when the task is specifically about NotebookLM.
onfire7777/universal-ai-skills-library/skills/open-design-landing Skill
14★ repoProduce a world-class single-page editorial landing site in the Atelier Zero visual language (Monocle / Apartamento / Études editorial collage) — the same aesthetic Open Design uses for its own marketing surface. The agent fills a typed `inputs.json` from a brand brief, optionally generates 16 collage assets via gpt-image-2, then runs a pure-function composer that emits a self-contained HTML file; a separate path can mirror the Astro marketing site in `apps/landing-page/`. Drop-in scroll-reveal motion and a Headroom-style sticky nav are wired automatically.
onfire7777/universal-ai-skills-library/skills/oracle Skill
14★ repoSpecialist agent for AI/ML design and evaluation. Covers prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, and cost optimization.
onfire7777/universal-ai-skills-library/skills/prompt-engineer Skill
14★ repoCreate a highly optimized prompt for an AI agent based on user input. Use when the user asks to improve, rewrite, or optimize a prompt, or when they want to learn how to write better prompts for agentic AI workflows. Requires OPENROUTER_API_KEY and/or OPENAI_API_KEY environment variables.
onfire7777/universal-ai-skills-library/skills/prompt-engineering Skill
14★ repoExpert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.
onfire7777/universal-ai-skills-library/skills/rally Skill
14★ repoMulti-session parallel orchestration adapter for Claude Code Agent Teams API. Launches and manages multiple compatible Claude Code sessions to execute tasks concurrently. Use only when that adapter is available and parallel work is required.
Retrieval search orchestration
onfire7777/universal-ai-skills-library/skills/retrieval-search-orchestration Skill
14★ repoUse when designing retrieval strategies for querying knowledge graphs in RAG systems. Invoke when user mentions retrieval strategy, search orchestration, global-first retrieval, local-first retrieval, U-shaped retrieval, query decomposition, multi-hop reasoning, provenance tracking, or citation in GraphRAG. Provides retrieval pattern selection, query rewriting, and provenance design.
onfire7777/universal-ai-skills-library/skills/setup-matt-pocock-skills Skill
14★ repoSets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
The same file is in 15 other repositories
onfire7777/universal-ai-skills-library/skills/sigil Skill
14★ repoA meta-tooling agent that analyzes a project's codebase, tech stack, and conventions to dynamically generate portable project skills. Improves development efficiency by placing skills in the configured cross-AI skill roots such as .claude/skills/, .agent/skills/, and OpenSkills-compatible locations.
onfire7777/universal-ai-skills-library/skills/skill-creator Skill
14★ repoGuide for creating or updating portable AI skills via specialized knowledge, workflows, scripts, references, or tool integrations. For any skill modification or improvement request, read this skill first and follow its update workflow.
onfire7777/universal-ai-skills-library/skills/skill-security-auditor Skill
14★ repoSecurity audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this skill safe", "scan skill for security", "check skill before install", "skill security check", "skill vulnerability scan".
onfire7777/universal-ai-skills-library/skills/subagent-driven-development Skill
14★ repoUse when executing implementation plans with independent tasks in the current session
onfire7777/universal-ai-skills-library/skills/ultimate-skill-creator Skill
14★ repoThe definitive end-to-end pipeline for creating the highest quality portable AI skills. Orchestrates six individual skills in sequence — each run fully, separately, and in its entirety — to produce elite, production-grade skills. Use when the user explicitly requests the full pipeline, says "ultimate skill", "ultimate skill creator", "ultimate skill creation", "best skill", "best skill creator", "full pipeline", "full skill pipeline", or specifically asks for maximum quality skill creation with all optimization stages. For simple skill creation without the full pipeline, use skill-creator instead.
onfire7777/universal-ai-skills-library/skills/universal-ai-config Skill
14★ repoConfigure and audit the local universal AI skills setup across Codex, ChatGPT, Claude, Claude Code, Claude Cowork, Cursor, Gemini, OpenCode, OpenSkills, Hermes Agent, OpenClaw, Cline, Continue, GitHub Copilot, Kiro, OpenHands, hosted provider compatibility surfaces, plugin manifests, optional MCP bridges, and global instruction files. Use when the user asks to organize, consolidate, optimize, rename, or repair the cross-AI skill router configuration.
onfire7777/universal-ai-skills-library/skills/write-a-skill Skill
14★ repoCreate 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
d3x293/code-crew/skills/execution-orchestrator Skill
13★ repoSmart hybrid execution engine that dispatches agents in parallel or sequential order based on task dependencies. Manages the Agent tool calls, result collection, conflict detection, and integration review.
litestar-org/litestar-skills/plugins/litestar/skills/litestar-mcp Skill
13★ repoAuto-activate for litestar_mcp, LitestarMCP, MCP, MCPConfig, mcp.app, mcp.run(), @mcp.tool/resource/prompt, MCPAuthConfig, MCPAuthBackend, mcp_tool=, mcp_resource=, Streamable HTTP, stdio, or OIDC MCP endpoints. Not for non-Litestar MCP.
litestar-org/litestar-skills/skills/litestar-mcp Skill
13★ repoAuto-activate for litestar_mcp, LitestarMCP, MCP, MCPConfig, mcp.app, mcp.run(), @mcp.tool/resource/prompt, MCPAuthConfig, MCPAuthBackend, mcp_tool=, mcp_resource=, Streamable HTTP, stdio, or OIDC MCP endpoints. Not for non-Litestar MCP servers or clients — use the official MCP Python SDK instead.
timwukp/agent-skills-best-practice/skills/skills/claude-api Skill
13★ 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 2 other repositories
timwukp/agent-skills-best-practice/skills/skills/gitlab-ci-kiro-pipeline Skill
13★ repoBuild, extend, or debug GitLab CI/CD pipelines (.gitlab-ci.yml) that run Kiro CLI in headless mode for AI-powered merge-request review, security scanning, test-failure analysis, config-drift detection, code-duplication sync checks, and change-impact/risk analysis — including integrating the customer's MCP servers (SonarQube SAST, Jira, internal tools) into CI jobs. Use this skill whenever the user mentions GitLab CI, .gitlab-ci.yml, GitLab pipelines, merge-request automation, AI code review in CI, Kiro CLI in CI/CD, kiro-cli headless or non-interactive mode, MCP servers in pipelines, or wants agentic/LLM checks in a pipeline — even if they don't say "Kiro" or "GitLab CI" explicitly (e.g. "add an AI reviewer to my MRs", "hook SonarQube into the AI review", "make the pipeline catch config drift").
timwukp/agent-skills-best-practice/skills/skills/mcp-builder Skill
13★ repoGuide 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