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
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/memory-safety-patterns Skill
2★ repoCross-language patterns for memory-safe programming including RAII, ownership, smart pointers, and resource management.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/memory-systems Skill
2★ repoDesign short-term, long-term, and graph-based memory architectures. Use when building agents that must persist across sessions, needing to maintain entity consistency across conversations, or implementing reasoning over accumulated knowledge.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/multi-agent-brainstorming Skill
2★ repoSimulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/multi-agent-patterns Skill
2★ repoThis skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/multi-agent-task-orchestrator Skill
2★ repoRoute tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/n8n-mcp-tools-expert Skill
2★ 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.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/not-human-search-mcp Skill
2★ repoSearch AI-ready websites, inspect indexed site details, verify MCP endpoints, and discover tools and APIs using the Not Human Search MCP server
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/on-call-handoff-patterns Skill
2★ repoEffective patterns for on-call shift transitions, ensuring continuity, context transfer, and reliable incident response across shifts.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/parallel-agents Skill
2★ repoMulti-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
Performance testing review multi agent review
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/performance-testing-review-multi-agent-review Skill
2★ repoReviews performance test results and system bottlenecks with multiple analytical perspectives before recommending optimization work.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/pipecat-friday-agent Skill
2★ repoBuild a low-latency, Iron Man-inspired tactical voice assistant (F.R.I.D.A.Y.) using Pipecat, Gemini, and OpenAI.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/project-development Skill
2★ repoThis skill covers the principles for identifying tasks suited to LLM processing, designing effective project architectures, and iterating rapidly using agent-assisted development.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/prompt-caching Skill
2★ repoCaching strategies for LLM prompts including Anthropic prompt
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/prompt-engineer Skill
2★ repoTransforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/prompt-engineering-patterns Skill
2★ repoMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/prompt-engineering Skill
2★ 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.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/prompt-library Skill
2★ repoA comprehensive collection of battle-tested prompts inspired by [awesome-chatgpt-prompts](https://github.com/f/awesome-chatgpt-prompts) and community best practices.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/protect-mcp-governance Skill
2★ repoAgent governance skill for MCP tool calls — Cedar policy authoring, shadow-to-enforce rollout, and Ed25519 receipt verification.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/rag-engineer Skill
2★ repoExpert in building Retrieval-Augmented Generation systems. Masters
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/rag-implementation Skill
2★ repoRAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/saga-orchestration Skill
2★ repoPatterns for managing distributed transactions and long-running business processes.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/skill-creator-ms Skill
2★ 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.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/skill-creator Skill
2★ 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.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/skill-improver Skill
2★ 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.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/skill-optimizer Skill
2★ 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.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/social-orchestrator Skill
2★ 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.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/subagent-driven-development Skill
2★ repoUse when executing implementation plans with independent tasks in the current session
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/tdd-orchestrator Skill
2★ repoMaster TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/tool-use-guardian Skill
2★ 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.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/varlock-claude-skill Skill
2★ repoSecure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/vector-database-engineer Skill
2★ repoExpert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar
Workflow orchestration patterns
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/workflow-orchestration-patterns Skill
2★ repoMaster workflow orchestration architecture with Temporal, covering fundamental design decisions, resilience patterns, and best practices for building reliable distributed systems.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/x-twitter-scraper Skill
2★ repoX (Twitter) data platform skill — tweet search, user lookup, follower extraction, engagement metrics, giveaway draws, monitoring, webhooks, 19 extraction tools, MCP server.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/x402-express-wrapper Skill
2★ 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.
celeryhq/simplified-ai/skills/simplified-cli Skill
2★ repoEntry point for the Simplified CLI (`smp MODULE COMMAND`) — covers Project Manager, Media (image/video AI), Assets API (brand kits, projects, assets), Social Media, and the MCP server (`smp serve`). Trigger on any request to use the `smp` CLI, manage Simplified PM boards/tasks, generate or process images/videos, manage brand kits or assets, schedule social media posts, or expose Simplified as MCP tools to Claude Desktop / Cursor / Cline.
gokulb20/crewm8-cfo-skills/skills/cfo-orchestrator Skill
2★ repoRoutes CFO and financial operations requests to specialized sub-skills based on user intent matching, task classification, and multi-skill chain assembly. Use when the user mentions startup CFO tasks, financial operations, reporting, fundraising questions, cash management, financial planning, strategic advisory, or asks about running any CFO-related workflow.
olzn/skills/skills/handoff Skill
2★ repoCompact the current conversation into a handoff document another session or agent can resume from. Use when wrapping up with unfinished work, when context is getting long, or when the user says "hand this off", "write a handoff", or "save state for the next session". Produces a single Markdown file at a durable, harness-agnostic path and reports it. Does NOT continue the work itself; it only captures state so a fresh session can.
IrfanSadiqRahat/constellation/agents/agent-orchestrator Skill
no license2★ repoMulti-agent coordination, tool routing, planner/worker patterns.
IrfanSadiqRahat/constellation/agents/eval-engineer Skill
no license2★ repoLLM-as-judge, holdout sets, regression suites, error analysis.
IrfanSadiqRahat/constellation/agents/hallucination-auditor Skill
no license2★ repoGrounded-claim detection, citation enforcement, abstention rules.
IrfanSadiqRahat/constellation/agents/prompt-engineer Skill
no license2★ repoSystem prompts, few-shot, chain-of-thought, structured output design.
IrfanSadiqRahat/constellation/agents/rag-architect Skill
no license2★ repoChunking, embedding, retrieval, re-ranking, eval-driven RAG tuning.
IrfanSadiqRahat/constellation/agents/vector-search-engineer Skill
no license2★ repoPinecone/Qdrant/pgvector, HNSW tuning, hybrid search, filters.
IrfanSadiqRahat/constellation/methodology/handoff-protocol Skill
no license2★ repoPass typed artifacts between roles with explicit contracts. The connective tissue of multi-agent pipelines.
IrfanSadiqRahat/constellation/methodology/memory-protocol Skill
no license2★ repoPersistent role-scoped memory across sessions. The agent that worked on your codebase yesterday knows things today.
IrfanSadiqRahat/constellation/methodology/pipeline-orchestration Skill
no license2★ repoRun a team formation's multi-stage pipeline end-to-end with role switching, handoffs, validation, and rollback.
IrfanSadiqRahat/constellation/methodology/subagent-dispatch Skill
no license2★ repoDispatch fresh subagents per task with typed artifact handoff and two-stage review.
Advise memory personalization skills
the-long-ride/skill-master/skills/advise-memory-personalization-skills Skill
2★ repoUse when a human wants to design, evaluate, or improve AI agent skills for persistent memory, user preferences, project context, personalization, recall, forgetting, or long-running relationship context
the-long-ride/skill-master/skills/advise-research-rag-skills Skill
2★ repoUse when a human wants to design, evaluate, or improve AI agent skills for web research, retrieval augmented generation, citations, source synthesis, knowledge bases, search workflows, or evidence-grounded answers
Advise tool integration skills
the-long-ride/skill-master/skills/advise-tool-integration-skills Skill
2★ repoUse when a human wants to design, evaluate, or improve AI agent skills for APIs, MCP servers, SaaS connectors, authentication flows, schemas, tool calling, external systems, or integration-heavy workflows
the-long-ride/skill-master/skills/universal-skill-governance Skill
2★ repoUse when creating, reviewing, or publishing AI-agent skills that must run consistently across local agents and web LLM chat interfaces.
Skryx-L-A/project-kit/skills/llm-app Skill
2★ repoBuild/set up an LLM-powered PRODUCT — a chatbot, RAG-over-documents app, agent app, or fine-tune — from the user's grilled answers. Project-kit sub-skill loaded by new-project routing whenever someone wants to build an AI app, a chatbot, RAG, "chat with my docs", an LLM agent product, or fine-tune a model. Chains claude-api + Supabase pgvector + skill-creator evals, and bakes in grounded citations, an eval set, and hallucination/jailbreak/PII guardrails.
Skryx-L-A/project-kit/skills/new-project Skill
2★ repoStand up a brand-new project folder end-to-end — grill the plan to a full Definition of Ready, then auto-scaffold the perfect file/memory structure, project-specific sub-agents, and tooling for it. Use WHENEVER the user wants to start/create/set up a new project, a new project folder, a new repo, a new app/site/tool/business/research/anything — even if they only say "neues Projekt", "new project", "let's build X", "I want to start X", or "set up a folder for X". Run automatically at the very start of any new effort; the user should never have to point at this folder. Routes to type-specific sub-skills (build-business, website, api-backend, data-ml, quant-strategy, game-mod, game-dev, llm-app, hardware-embedded, creative-media, simulation, ecommerce-store, research-decision, content-writing, oss-library, browser-extension, bot-automation, saas, cli-tool, desktop-app, mobile-app, ai-agent-mcp) and a generic fallback.
Vironnimo/vbot/tests/e2e/fixtures/mixed-project/.claude/skills/claude-e2e-skill Skill
2★ repoDeterministic Claude Project Skill fixture.
grimaldost/craft-collection/plugins/humblepowers/skills/skill-authoring Skill
2★ repoAuthor and revise Claude Code skills with calibrated trigger descriptions and eval-gated quality — the description is a trigger surface that competes on fit, not an advertisement that competes on volume. Use when creating a new skill, when an existing skill over- or under-triggers and the description needs rework, when adding negative space ("not for X — that is Y") or example trigger phrasings, when deciding whether a skill body is rigid (bright-line constraints) or flexible (judgment-delegating guidance), or when porting a skill from an imperative register to a neutral one. Covers the calibration doctrine — dense concrete triggers, explicit non-triggers naming the owning sibling, plain-declarative bright lines, descriptive failure-mode catalogs without identity pressure, and the shipping requirement of a trigger dataset with sealed holdout plus a correct-usage rubric for rigid skills. The register linter mechanically enforces the detectable subset of the register rules (banners, caps runs, a fixed phrase list); review holds the rest. Not for measuring an existing skill's behavior (that is evaluate-skill) and not for deciding which installed skill to use on a task (that is choosing-tools).
grimaldost/craft-collection/plugins/session-workflow/skills/compaction-survival Skill
2★ repoMaintain a persisted, re-readable control anchor so a long autonomous run survives context compaction without losing the plot — one file holding the mission, a plan pointer, a live cursor (done / in progress / next action), invariants, last-known-good state, and exact resume steps, updated after each step and re-read at the start of each turn. Use when starting or driving a multi-hour or multi-phase autonomous task, a self-driving loop, or any unattended run that will cross one or more automatic compactions or context-window resets; on asks like "make sure compaction doesn't lose the work", "keep state across auto-compact", "persist the current state so a reset doesn't disrupt this", "this is a long autonomous run", or "resume cleanly after a reset". The anchor is intra-actor state recovery — the same actor re-reading its own working state across a discontinuity. Not for handing work to a fresh context or a teammate (that is context-handoff's inter-actor brief), not for post-hoc capture of what a finished session learned (that is journaling-sessions), and not for tracking a short task that fits comfortably in one context window. The /anchor command is the one-off snapshot entry point; when the running session lacks the plugin surface entirely (stale snapshot, harness without the skill menu), references/cold-start.md has the by-hand recipe.
grimaldost/craft-collection/plugins/session-workflow/skills/context-handoff Skill
2★ repoAuthor a paste-ready, self-contained brief that hands work to a fresh context — a new Claude Code session, a spawned task, a teammate, or an issue ticket. Use whenever current work must be packaged so a receiver with zero shared context can take it cold — "package this up for a fresh session", "bundle this for another agent", "write a standalone brief / a self-contained handoff", "spin this off", "hand this off", "offload this", "branch off", "new session for this", "author a persisted backlog / worklist doc for a future session", "subtask", "fork", "spinoff" — when curating a context slice to continue or delegate work elsewhere, or running "/context-handoff". Three modes — SUBTASK (bounded brief, an artifact comes back), FORK (continues independently, nothing returns), and BACKLOG (a persisted repo doc a future session opens to pick up any item). For in-session parallel work where results flow back automatically, prefer the Task tool / subagents — this skill is for handoffs that cross a boundary the harness won't bridge (a fresh session, a human, a ticket).
grimaldost/craft-collection/plugins/session-workflow/skills/evaluate-skill Skill
2★ repoUse when you want to behaviorally evaluate a Claude Code skill — measure whether it auto-activates on the prompts it should and stays quiet on near-misses (trigger recall and specificity), whether its output actually satisfies its own discipline (correct-usage), and whether it beats the no-skill baseline (with/without) — producing a scorecard with confidence intervals. Triggers on "evaluate this skill", "test my skill", "does my skill fire", "measure or benchmark skill performance", "is my description triggering", "build an eval for this skill", or running "/evaluate-skill". Claude Code only — it spawns many headless `claude -p` runs, so it is cost-gated; show the plan first. Not for a one-off manual spot-check, for judging a skill's design qualitatively (that is a fresh-eyes panel, not a behavioral eval), or for listing which skills are installed (that is toolkit-awareness).
grimaldost/craft-collection/plugins/session-workflow/skills/llm-signature Skill
2★ repoSign agent-assisted work with a machine-generated provenance signature: an Assisted-By git trailer naming the exact model that wrote and orchestrated the change, and an Agent-Stack trailer naming the harness and plugin versions it ran on. Use when committing or writing a PR body in a project that adopts the signature, when asked to sign a commit with the model / add model attribution or an LLM signature, when asked which model or tool stack produced a change, or when replacing Co-Authored-By AI boilerplate with provenance trailers. The signature is rendered by a script from live sources, never typed from memory, and the model is listed only in Assisted-By — never as a commit co-author. Not for human authorship credit (real co-authors keep their Co-Authored-By lines).
grimaldost/craft-collection/plugins/session-workflow/skills/tool-feedback Skill
2★ repoWrite a per-session dogfooding feedback report for each registered in-development tool the session exercised — what worked, friction, misses with the phase that should have caught them, vacuous gates, and severity-tagged proposed changes with stable finding IDs — saved into that tool's own feedback directory. Use when the user asks for feedback on their tools ("write the feedback reports", "tooling feedback", "dogfood report", "capture the friction with keel / convoy") — a direct imperative naming one tool ("write a dogfooding feedback report for keel") is this skill too, since writing that report IS the skill; route it here rather than drafting the report freehand — and offer once, unprompted, when a session that exercised a registered tool is winding down. Registered tools come from a feedback-targets table the user supplies (e.g. in CLAUDE.md) — never hunt the filesystem for targets. Design-only or authoring-only use of a tool still counts as use. Not for feedback on code or PRs (that is code review), not for capturing general session knowledge into a memory store (that is journaling-sessions), and not for product feedback to a third-party vendor.