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
Ghosteken/agent-harness/archive/skills-community/pipecat-friday-agent Skill
1★ repoBuild a low-latency, Iron Man-inspired tactical voice assistant (F.R.I.D.A.Y.) using Pipecat, Gemini, and OpenAI.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/project-development Skill
1★ repoThis skill covers the principles for identifying tasks suited to LLM processing, designing effective project architectures, and iterating rapidly using agent-assisted development.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/prompt-caching Skill
1★ repoCaching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation)
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/prompt-engineer Skill
1★ repoTransforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/prompt-engineering-patterns Skill
1★ repoMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/prompt-engineering Skill
1★ 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.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/prompt-library Skill
1★ repoA comprehensive collection of battle-tested prompts inspired by [awesome-chatgpt-prompts](https://github.com/f/awesome-chatgpt-prompts) and community best practices.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/protect-mcp-governance Skill
1★ repoAgent governance skill for MCP tool calls — Cedar policy authoring, shadow-to-enforce rollout, and Ed25519 receipt verification.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/saga-orchestration Skill
1★ repoPatterns for managing distributed transactions and long-running business processes.
The same file is in 5 other repositories
Ghosteken/agent-harness/archive/skills-community/sendblue/sendblue-notify Skill
1★ repoText the user's phone when a long-running task, agent turn, or scheduled job finishes — via @sendblue/cli for outbound, optionally wired to a Claude Code Stop hook for automatic fire.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/skill-creator-ms Skill
1★ repoGuide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.
The same file is in 3 other repositories
Ghosteken/agent-harness/archive/skills-community/skill-creator Skill
1★ repoTo create new CLI skills following Anthropic's official best practices with zero manual configuration. This skill automates brainstorming, template application, validation, and installation processes while maintaining progressive disclosure patterns and writing style standards.
The same file is in 2 other repositories
Ghosteken/agent-harness/archive/skills-community/skill-improver Skill
1★ repoIteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards. Use when improving a skill with multiple quality issues, iterating on a new skill until it meets standards, or automated fix-review cycles instead of manual editing.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/skill-optimizer Skill
1★ repoDiagnose and optimize Agent Skills (SKILL.md) with real session data and research-backed static analysis. Works with Claude Code, Codex, and any Agent Skills-compatible agent.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/social-orchestrator Skill
1★ repoOrquestrador unificado de canais sociais — coordena Instagram, Telegram e WhatsApp em um unico fluxo de trabalho. Publicacao cross-channel, metricas unificadas, reutilizacao de conteudo por formato, agendamento sincronizado e gestao centralizada de campanhas em todos os canais simultaneamente.
Ghosteken/agent-harness/archive/skills-community/tdd-orchestrator Skill
1★ repoMaster TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices.
The same file is in 3 other repositories
Ghosteken/agent-harness/archive/skills-community/tool-use-guardian Skill
1★ repoFREE — Intelligent tool-call reliability wrapper. Monitors, retries, fixes, and learns from tool failures. Auto-recovers from truncated JSON, timeouts, rate limits, and mid-chain failures.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/varlock-claude-skill Skill
1★ repoSecure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits
The same file is in 3 other repositories
Ghosteken/agent-harness/archive/skills-community/vector-database-engineer Skill
1★ repoExpert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar
The same file is in 4 other repositories
Workflow orchestration patterns
Ghosteken/agent-harness/archive/skills-community/workflow-orchestration-patterns Skill
1★ repoMaster workflow orchestration architecture with Temporal, covering fundamental design decisions, resilience patterns, and best practices for building reliable distributed systems.
The same file is in 4 other repositories
Ghosteken/agent-harness/archive/skills-community/x402-express-wrapper Skill
1★ repoWrapper oficial de M2MCent (Node.js) para inyectar muros de pago x402 en APIs o servidores Model Context Protocol (MCP). Usar al construir nuevos servicios que requieran monetización máquina a máquina.
The same file is in 4 other repositories
Ghosteken/agent-harness/skills/agent-evaluation Skill
1★ repoTesting and benchmarking LLM agents including behavioral testing,
Ghosteken/agent-harness/skills/agent-squad Skill
1★ repoMain agent orchestrator that coordinates a specialized squad of agents
The same file is in 23 other repositories
Ghosteken/agent-harness/skills/ai-agent-development Skill
1★ repoAI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.
Ghosteken/agent-harness/skills/ai-agents-architect Skill
1★ repoExpert in designing and building autonomous AI agents. Masters tool
Ghosteken/agent-harness/skills/ai-engineering-toolkit Skill
1★ repo6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
The same file is in 5 other repositories
Ghosteken/agent-harness/skills/autonomous-agent-patterns Skill
1★ repoDesign patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI Codex](https://github.com/openai/codex).
Ghosteken/agent-harness/skills/browser-testing-with-devtools Skill
1★ repoTests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
The same file is in 37 other repositories
Ghosteken/agent-harness/skills/context-engineering Skill
1★ repoOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
The same file is in 12 other repositories
Ghosteken/agent-harness/skills/embedding-strategies Skill
1★ repoGuide to selecting and optimizing embedding models for vector search applications.
The same file is in 7 other repositories
Ghosteken/agent-harness/skills/llm-app-patterns Skill
1★ repoProduction-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best practices.
The same file is in 5 other repositories
Ghosteken/agent-harness/skills/llm-evaluation Skill
1★ repoMaster comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.
The same file is in 5 other repositories
Ghosteken/agent-harness/skills/llm-ops Skill
1★ repoLLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.
The same file is in 4 other repositories
Ghosteken/agent-harness/skills/multi-agent-brainstorming Skill
1★ repoSimulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation.
The same file is in 4 other repositories
Ghosteken/agent-harness/skills/rag-engineer Skill
1★ repoExpert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.
Ghosteken/agent-harness/skills/rag-implementation Skill
1★ repoRAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.
Ghosteken/agent-harness/skills/subagent-driven-development Skill
1★ repoUse when executing implementation plans with independent tasks in the current session
Ghosteken/agent-harness/skills/using-agent-harness Skill
1★ repoIntent router and pre-flight checker for agent-harness — checks for a matching skill before any response, then maps what the user describes to the right agent persona and skill. Use when starting any task to determine which agent and skill should handle it.
thiagoxikota/ai-collective-content-lab/.claude/skills/prompt-de-imagem Skill
1★ repoAjuda a escrever um bom prompt de imagem antes de gerar (sujeito, estilo, luz, camera, enquadramento, aspect ratio). Use quando a pessoa disser "me ajuda com o prompt", "melhora esse prompt de imagem", "como descrever pra IA", "esse prompt ta bom?", "help me with the prompt", "improve this image prompt".
loursCreatif/ours-stack/memory-palace Skill
1★ repoCarte en relief oblique (style Google Maps 3D) — cliquer bâtiments et zones pour ancrer concepts (method of loci). Drill-down site → intérieur, panneau latéral. Pas de déplacement FPS. Reads brief.md, notes.md, research.md, report.md. Outputs memory-palace.json + HTML (Three.js vendored). Triggers: "memory palace", "palais de mémoire", "relief map", "carte oblique", /memory-palace. No new research.
VoldemortGin/AI-Coding-Skill-Bible/java-project-standard Skill
1★ repoEnforce a strict, model-agnostic, AI-navigable Java project standard: the Java compiler plus `-Werror` + `-Xlint:all` as the baseline, **Error Prone** (bug-pattern checks as errors, the clippy/detekt analog) and **NullAway** (JSpecify `@Nullable`, null-safety at compile time — the Kotlin null-safety / Swift optional analog) as the static guarantee, **Spotless** with google-java-format as the format gate, sealed error hierarchies + exhaustive `switch` (no silent failures), **TDD with a JaCoCo coverage floor in the gate**, Jackson at boundaries with lightweight record compact-constructor validation, a Gradle multi-module module-per-domain structure, a zero-SDK zero-framework `:domain` module behind provider interface seams with a default `MockProvider`, a manual composition root (no DI framework), a version catalog pinning every version, a CLAUDE.md in every module, and scaffold/conformance scripts. Use whenever starting or scaffolding a Java project; setting up Gradle / settings.gradle.kts / libs.versions.toml / Error Prone / NullAway / Spotless / JaCoCo / CI; deciding module structure; adding an LLM / embedding / vector-store dependency; wiring providers or adapters; or checking that an existing Java project conforms. Apply it even when the user only says "start a Java project", "set up the structure", "add an LLM", or "wire up CI" without naming the standard. This skill governs the Java host's internals; it is complementary to polyglot-core-standard, which governs the cross-language seam (a Rust core + a JNI/JNA/Panama-FFM bridge — Java has no official UniFFI support).
VoldemortGin/AI-Coding-Skill-Bible/rust-project-standard Skill
1★ repoEnforce a strict, model-agnostic, AI-navigable Rust project standard: a Cargo workspace with crate-per-domain deep structure, #![forbid(unsafe_code)] + strict clippy workspace lints + a one-command zero-warning gate (fmt + clippy -D warnings + doc + test + cargo-deny), serde + newtypes at boundaries, trait-based provider seams with a zero-SDK domain crate and a default MockProvider, tracing, figment, include_str! + minijinja prompts, and a CLAUDE.md in every crate. Use whenever starting or scaffolding a Rust project, crate, or workspace; setting up Cargo.toml / clippy / rustfmt / CI; deciding crate or module structure; adding an LLM / embedding / vector-store dependency; wiring providers or adapters; setting up cargo-deny or supply-chain/license checks; or checking an existing Rust project conforms. Apply even when the user only says "start a Rust project", "structure this crate", "add an LLM", or "wire up CI" without naming the standard.
VoldemortGin/AI-Coding-Skill-Bible/swift-project-standard Skill
1★ repoEnforce a strict, model-agnostic, AI-navigable Swift project standard: Swift 6 language mode + complete strict concurrency + warnings-as-errors as a one-command zero-warning gate, the escape hatches (`!` force-unwrap / `try!` / `as!` / `@unchecked Sendable` / implicitly-unwrapped optionals) shut, `Codable` + newtypes at boundaries (parse don't validate), an SPM package with target-per-domain deep structure, a zero-SDK `Domain` target behind provider protocol seams with a default `MockProvider`, `os.Logger` with privacy interpolation, a strongly-typed `AppConfig`, a swift-format + SwiftLint double gate, a CLAUDE.md in every target, and scaffold/conformance scripts. Use whenever starting or scaffolding a Swift or SwiftUI project; setting up Package.swift / SwiftLint / swift-format / CI; deciding module or target structure; adding an LLM / embedding / vector-store dependency; wiring providers or adapters; or checking that an existing Swift project conforms. Apply it even when the user only says "start a Swift project", "set up the structure", "add an LLM", or "wire up CI" without naming the standard.
monikazapisek/design-engineering-playbook/agents/agent-agile-master/skills/change-agent Skill
1★ repoChange management and facilitation — Kotter 8 steps, ORID structured conversation, Information Radiators. Dual mode: personal change narrative and organizational transformation.
monikazapisek/design-engineering-playbook/skills/figjam-storymap-llm Skill
1★ repoUse when you need to parse or audit a FigJam User Story Map (Jeff Patton methodology) into LLM-readable Markdown or JSON — after a Story Mapping workshop, before publishing a Story Map template, or when feeding a Story Map to a coding agent (Cursor, Claude Code, Copilot).
monikazapisek/design-engineering-playbook/skills/legible-agent-output Skill
1★ repoForce every user-facing string from an AI agent into plain language a non-technical human can read. Rewrites task titles, status messages, error messages, and action previews, replacing opaque codes and framework jargon with descriptions a non-technical PM can understand.
Senderkit mcp messaging operations
senderkit/senderkit-skills/skills/senderkit-mcp-messaging-operations Skill
1★ repoSend and operate transactional messages — email, SMS, push, or web-push — at runtime through the connected SenderKit MCP server. Use whenever the SenderKit MCP tools (senderkit_*) are available and a user wants to actually send a message (a test or live send, a welcome/OTP/notification message), check delivery or message status, debug a failed or stuck send, look up/draft/regenerate templates, filter recent messages, check scheduled sends, or cancel a scheduled or queued message — rather than editing application code (that is the senderkit-integration skill).
yiyaw-lab/agent-armor/frontier Skill
1★ repoBring your work to the frontier — across any SURFACE (design, model/LLM stack, agent architecture, infra, content...). For a surface it audits where you have fallen behind the live 2026 standard (benchmarked against that surface's frontier exemplars) and, on approval, provisions the current frontier toolchain. The external standard-SETTER; harmonize is the internal-consistency enforcer it pipelines into. Surfaces + their benchmarks live in ~/.claude/frontier/surfaces.md. Modes: audit | plan | apply | refresh, scoped with a <surface>.
yiyaw-lab/agent-armor/mirror Skill
1★ repoSync a skill from ~/.claude/commands/<x>.md to the public skills repo (yiyaw-lab/agent-armor; local clone ~/code/claude-code-skills) as <x>/SKILL.md — disclosure+secrets gate first, README bookkeeping (badge count, playbook diagram, catalog row) handled, then a PR with CI green; merge only on explicit approval. Curated: only named skills, never a bulk export. Modes: <skill-name> | sweep | audit.
yiyaw-lab/agent-armor/prompt Skill
1★ repoPersonal prompt library + prompt compiler. Save frequently used prompts as parameterized templates, invoke them by name, or refine a draft prompt into a more effective, token-lean version — informed by TASTE.md so the refined prompt asks for what the user will actually accept, not just what they typed. Modes: <name> | save | list | refine.
vasu-devs/Forge/skills/eval Skill
1★ repoMeasure non-deterministic behavior — LLM features, agents, prompts, or a skill itself — with repeatable evals instead of one-shot checks. Use when building or tuning AI/LLM functionality (ranking, extraction, generation, agent loops), when a feature could pass once by luck, or when validating that a prompt or skill actually changes behavior.
Razaib-khan/ForgeWeave/src/forgeweave/templates/claude/.claude/skills/memory-manager Skill
1★ repoHandles local persistence of research outputs, intermediate reasoning, and reusable knowledge chunks
Razaib-khan/ForgeWeave/src/forgeweave/templates/claude/.claude/skills/playwright-mcp Skill
1★ repoComplete guide for using Playwright MCP to automate browsers inside AI agent workflows. Use this skill whenever the agent needs to: navigate web pages, fill forms, click elements, take screenshots, mock API responses, manage cookies/localStorage, save auth state, generate Playwright test code, record video/traces, export PDFs, or handle any browser interaction. Triggers on phrases like "open browser", "automate this flow", "test this page", "fill this form", "screenshot this site", "mock the API", "save login state", "generate playwright test", "browser automation", "interact with the site", or any task requiring real browser control. Even if the user mentions just a URL and a goal, this skill applies.
Razaib-khan/ForgeWeave/src/forgeweave/templates/claude/.claude/skills/skill-authoring Skill
1★ repoCreate or revise a ForgeWeave skill — from identifying the repeatable job to writing the bundle and validating it with eval checks.
Razaib-khan/ForgeWeave/src/forgeweave/templates/claude/.claude/skills/skill-builder Skill
1★ repoComplete guide for designing, writing, testing, iterating, and packaging Claude Skills (SKILL.md files). Use this skill whenever someone wants to: create a new skill from scratch, improve or update an existing skill, understand the skill format, write a SKILL.md, build a skill folder with scripts and references, evaluate whether a skill is well-written, package a skill for distribution, optimize a skill's trigger description, or understand best practices for Agent Skills. Triggers include phrases like "build a skill", "write a SKILL.md", "make a skill for", "improve this skill", "skill format", "create an agent skill", "how do I write a skill", or any request to teach Claude a domain-specific capability through the skills system.
Razaib-khan/ForgeWeave/src/forgeweave/templates/claude/.claude/skills/workflow-orchestrator Skill
1★ repoCoordinates multi-skill execution pipelines (e.g., research → plan → build → test)
Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/agent-spawner Skill
1★ repoCreates and configures subagents dynamically with defined roles, constraints, and tool permissions
Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/memory-manager Skill
1★ repoHandles local persistence of research outputs, intermediate reasoning, and reusable knowledge chunks
Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/playwright-mcp Skill
1★ repoComplete guide for using Playwright MCP to automate browsers inside AI agent workflows. Use this skill whenever the agent needs to: navigate web pages, fill forms, click elements, take screenshots, mock API responses, manage cookies/localStorage, save auth state, generate Playwright test code, record video/traces, export PDFs, or handle any browser interaction. Triggers on phrases like "open browser", "automate this flow", "test this page", "fill this form", "screenshot this site", "mock the API", "save login state", "generate playwright test", "browser automation", "interact with the site", or any task requiring real browser control. Even if the user mentions just a URL and a goal, this skill applies.
Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/skill-authoring Skill
1★ repoCreate or revise a ForgeWeave skill — from identifying the repeatable job to writing the bundle and validating it with eval checks.