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
northseadl/skillwisp/skills/@muratcankoylan/memory-systems Skill
0★ repoThis skill should be used when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph", "track entities", or mentions memory architecture, temporal knowledge graphs, vector stores, entity memory, or cross-session persistence.
The same file is in 3 other repositories
northseadl/skillwisp/skills/@muratcankoylan/multi-agent-patterns Skill
0★ 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.
The same file is in 4 other repositories
northseadl/skillwisp/skills/@muratcankoylan/project-development Skill
0★ repoThis skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.
The same file is in 4 other repositories
northseadl/skillwisp/skills/@obra/dispatching-parallel-agents Skill
0★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 15 other repositories
northseadl/skillwisp/skills/@obra/subagent-driven-development Skill
0★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 7 other repositories
northseadl/skillwisp/skills/@openai/figma Skill
0★ repoUse the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
The same file is in 5 other repositories
iceflower/agent-skills/prompt-engineering Skill
0★ repoPrompt engineering best practices for LLM-powered applications including prompt design patterns, structured output, evaluation, safety, and cost optimization. Use when building or reviewing AI-powered features that interact with LLMs.
iceflower/agent-skills/spring-ai Skill
0★ repoSpring AI conventions and patterns for building AI-powered applications including ChatClient configuration, tool/function calling, prompt template management, vector store integration, RAG (Retrieval Augmented Generation), Advisors API, MCP (Model Context Protocol) integration, multi-model routing patterns, advanced RAG (query rewriting, hybrid search, reranking, agentic RAG), agent frameworks (Router Agent, Human-in-the-Loop, memory patterns), and model evaluation/token monitoring. Use when building or reviewing Spring AI applications, integrating LLMs with Spring Boot, implementing ChatClient, configuring tool calling, designing prompt templates, working with vector databases in Spring, or building advanced RAG pipelines and autonomous agent workflows.
taujiong/skills/skills/skill-creator-defaults Skill
no license0★ repoGuide to project-specific defaults for skill creation. Use when users want to create a new skill, edit an existing skill, write SKILL.md, or modify any files in .agents/skills. Also triggers when users mention create skill, new skill, write skill, edit skill, or .agents/skills.
Makiato1999/agentic-travel/.claude/skills/memory-query Skill
0★ repoUse this skill when the user asks about their own history, past trips, or saved preferences. Triggers when user asks "我去过哪些地方", "我上次去北京是什么时候", "我之前说过什么偏好", "我的旅行记录". This skill uses MemoryQueryAgent and requires a MemoryManager (user_id, session_id) to access long-term memory.
yaniv-golan/skill-packager-skill/skill-packager/skills/skill-packager Skill
0★ repoPackage AI agent skills into deployment formats — .zip, .skill, Claude plugin, Claude marketplace, Cursor plugin, Cursor marketplace, native Codex/ChatGPT plugin, ChatGPT/Manus zip, Codex CLI, NanoClaw marketplace, OpenClaw/ClawHub, Agent Skills standard (.agents/), or a universal repo with all formats + CI/CD. Use when the user says "package this skill", "deploy my skill", "create a plugin from this skill", "make this work on Cursor/ChatGPT/Codex/NanoClaw/OpenClaw", "set up a repo for my skill", or wants to distribute a SKILL.md to any platform.
prof-ramos/skills/skills/agent-workflows/skill-cleaner Skill
0★ repoAudit and trim AI agent skill prompt budget across OpenCode, Codex, and Claude Code. Use when trimming skill prompt budget, finding duplicate skills across roots, auditing enabled/disabled skill roots, inspecting token pressure from the pre-budget skill list, or deciding which skills, plugins, or personal repos to remove. Detects oversized descriptions nearing truncation, body-hash duplicates, unused skills with no recent usage trace, and budget exhaustion before descriptions are truncated or skills omitted.
ahostbr/LiteCLI/skills/compile-cli Skill
0★ repoTurn any MCP server or SKILL.md file into a standalone CLI using LiteCLI. Use when the user wants to compile an MCP server, skill file, or directory of skills into runnable CLI commands.
1natsu-vacation/agent-skills/.claude/skills/spec-drift-watch Skill
0★ reponpx skills add 1natsu-vacation/agent-skills
1natsu-vacation/agent-skills/skills/1natsu-document-harness-audit Skill
0★ repoセッションをまたいで存在する既存ハーネスドキュメント(CLAUDE.md, .claude/rules/, docs/, feature README, コード内コメント)とエージェントの永続メモリ(Claude Code auto-memory 等)を検査する。ドキュメントは陳腐化・蒸留不足・重複・不整合・参照切れ・欠落・用語と文体の規約違反を検出し、メモリは蒸留漏れ・ドキュメントとの食い違い・陳腐化を検出する。「ドキュメントを監査して」「整合性チェックして」「古いドキュメントがないか」「文体や用語がバラバラなので直したい」「メモリを整理して」「メモリの知識をdocsに反映して」「メモリとドキュメントがずれてる」等で使用する。現セッションで自分が実装した変更のドキュメント生成・更新は `1natsu-document-harness` を使い、このスキルではない。
The same file is in 1 other repository
koinod/skills/agent-fleet-status Skill
0★ repo55+ AI agent skills for sales, content, research, and fleet operations. Free lite editions. Full alpha at koino.capital
The same file is in 1 other repository
koinod/skills/elite-longterm-memory Skill
0★ repoUltimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
The same file is in 1 other repository
koinod/skills/proactive-agent Skill
0★ repoTransform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
The same file is in 1 other repository
gdm257/cc-plugins/plugins/codebase-memory/skills/codebase-memory Skill
no license0★ repoUse the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions, high fan-out, refactor candidates, code quality audit, graph query syntax, Cypher query examples, edge types, how to use search_graph.
badrusiddique/enggenie-skill/skills/memory-recall Skill
0★ repoUse when asking about previous sessions - cross-session context search via claude-mem with token-efficient 3-layer retrieval
jmlrt/skills/optimize-workspace-context Skill
0★ repoOptimize CLAUDE.md or AGENTS.md files for AI consumption. Focus on quality improvements — inconsistencies, duplicates, unnecessary content, content that should be moved elsewhere. Use when asked to optimize, review, or clean up an AI config file.
jmlrt/skills/review-claude-config Skill
0★ repoAudit the ecosystem of Claude config files — global CLAUDE.md, per-repo CLAUDE.md and CLAUDE.local.md, memory files, and skills — for redundancy, inconsistency, outdated facts, and misplaced content. Use when asked to "review CLAUDE.md", "audit claude config", "clean up claude files", or "check what should be global vs local".
jmlrt/skills/review-claude-settings Skill
0★ repoAudit Claude Code settings.json files — global (~/.claude/settings.json) and per-repo (.claude/settings.json, .claude/settings.local.json) — for permission consolidation, redundancy, and security risks. Use when asked to "review settings.json", "audit claude settings", "clean up permissions", "check what should be global vs repo", or "security review of settings".
coderbaba0/ai_agents_skills/git-guardrails-claude-code Skill
0★ 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
coderbaba0/ai_agents_skills/write-a-skill Skill
0★ 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
jovd83/Cypress-skill/documentation/session-state Skill
0★ repoUse when you need the legacy Cypress session-state entrypoint path; record session state in the canonical Cypress handover workflow.
jovd83/Cypress-skill/orchestrator Skill
0★ repoCentral entrypoint for broad or ambiguous Cypress requests. Use when Codex needs to classify the user's testing goal, choose the right Cypress subskill, and move from intent to implementation, planning, documentation, execution, or reporting without unnecessary menu-driven back-and-forth.
leoheart0125/sdd-skills/skills/sdd-knowledge-base Skill
no license0★ repoThe 'Brain' of the project: manages state (Context), accumulates knowledge (Patterns + Lessons), and evolves rules.
master5d/claude-personal-skills/skills/pencil Skill
no license0★ repoPencil design tool expert — working with .pen files using the Pencil MCP server and CLI. Use this skill whenever the user mentions Pencil, .pen files, design files, wants to create/edit/export designs, generate UI components in Pencil, read design tokens or variables, batch-modify design properties, or asks about design-to-code workflows. Also triggers for "open my design", "create a layout in Pencil", "export design", "pencil CLI", or any prompt that involves the pencil MCP tools (batch_design, batch_get, get_editor_state, etc.).
zhijunio/skills/skill-audit Skill
0★ repoAudit, design, categorize, distribute, and measure agent skills using lessons from Anthropic's Lessons from building Claude Code: How we use skills. Use when reviewing an existing skill, deciding whether a workflow deserves a skill, planning a skill library, turning team knowledge into skills, choosing skill categories, writing trigger descriptions, designing progressive disclosure, or planning skill marketplace and usage measurement.
zhijunio/skills/skill-creator Skill
0★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
fntune/skills/swarm-audit/skills/swarm-audit Skill
0★ repoThis skill should be used when the user asks to "audit the codebase", "review and fix codebase issues", "run a swarm audit", "security sweep", "type safety sweep", "codebase-wide review", or wants to spawn a multi-agent team to discover and fix issues across the codebase. Triggers on "swarm", "audit pipeline", "review pipeline", "team review", "parallel audit".
kpatryk/skills/skills/worktrunk Skill
0★ repoExpert guide for Worktrunk (the `wt` CLI), a git worktree manager designed for running AI agents in parallel. Invoke this skill whenever a user mentions worktrunk or wt commands (wt switch, wt list, wt merge, wt remove, wt hook, wt step, wt config), asks about git worktrees for AI agents or parallel development, wants to configure LLM commit messages, set up worktree lifecycle hooks, run multiple Claude or Codex agents simultaneously, use wt list CI status, configure the interactive picker, copy build caches between worktrees, or troubleshoot shell integration. Also use for questions about .config/wt.toml, ~/.config/worktrunk/config.toml, hash_port, sanitize filters, wt merge squash/rebase workflow, wt step copy-ignored, wt step prune, agent handoffs, dev servers per worktree, bare repository layouts, or any other worktrunk topic.
devcsde/oatda-openclaw-skills/skills/oatda-list-models Skill
no license0★ repoList and filter AI models from OATDA's unified gateway — ChatGPT/GPT-5, Claude Sonnet 4.5, Gemini 3, Grok 4, Qwen3, Kimi K2.7, GLM-5, and 100+ more across 10+ providers. Triggers when the user wants to see available models, pick the right LLM for a task, discover provider-specific parameters for image/video/audio generation, or filter by capability (chat/image/video/audio/vision) and provider. Ideal for model discovery, pricing comparison, and capability lookup before calling other OATDA skills.
devcsde/oatda-openclaw-skills/skills/oatda-text-completion Skill
no license0★ repoGenerate text, code, or chat completions using OATDA's unified LLM API gateway — like calling ChatGPT, Claude, Gemini, GPT-5, Claude Sonnet 4.5, Grok 4, or Qwen from a single endpoint. Triggers when the user wants to generate, write, summarize, translate, or complete text via OpenAI, Anthropic, Google, Deepseek, Mistral, xAI, Alibaba/Qwen, MiniMax, ZAI/GLM, Moonshot/Kimi, or Bytedance. Also use when comparing outputs across models or using aliases like "gpt-4o", "gpt-5", "claude", "gemini", "deepseek", "grok", "qwen", "mistral", "kimi".
devcsde/oatda-openclaw-skills/skills/oatda-vision-analysis Skill
no license0★ repoAnalyze images, photos, screenshots, or diagrams using vision-capable AI models (GPT-4o, GPT-5, Claude Sonnet 4.5, Claude Opus 4.5, Gemini 3, GLM-4.6V) through OATDA's unified AI gateway. Triggers when the user wants image analysis, OCR, photo understanding, chart reading, screenshot description, or computer-vision tasks via a single API key.
HyunKN/harness-kit/skills/subagent-workflow Skill
0★ repoUse when Codex sub-agents should be applied in a disciplined way for analysis, implementation, or review. Trigger when a task is large enough to benefit from role-split work but still needs one main agent to own integration.
markjoshwel/skills/skill-authoring-majo Skill
no license0★ repoCreate new Agent Skills from learned patterns and workflows. Use when you have developed a repeatable workflow, coding pattern, or expertise that should be reusable across projects and doesn't fit in AGENTS.md. Covers SKILL.md format, naming conventions, progressive disclosure, testing, and skill structure best practices.
thuongtruong109/soniclaw/.openclaw/workspace/skills/public/multi-model-orchestration Skill
no license0★ repoUse when a workflow should split work across different models by step, usually via sub-agents or delegated tasks. Best for tasks where cheap/fast steps and high-quality reasoning steps should use different models. Teaches how to structure main-agent, sub-agent, and tool-driven flows with explicit model choices.
ty13r/skillforge/.claude/skills/skill-creator Skill
no license0★ repoCreates production-quality Claude Agent Skill packages from a domain description. Generates SKILL.md, scripts, references, and domain-specific files following the golden template. Use when building, creating, or authoring a new skill, even if they just say "make a skill for X". NOT for editing existing skills or evolutions.
mkgp-dev/codex-skills/skills/.experimental/react-hook-form-with-zod Skill
0★ repoBest-practice guidance for building forms with React Hook Form in modern TypeScript React apps, with Zod integration when schema validation is useful. Use this skill whenever the user is writing or reviewing `useForm`, `register`, `useController`, `Controller`, `useFieldArray`, `useWatch`, `useFormState`, `FormProvider`, `useFormContext`, `defaultValues`, `setValue`, `reset`, `trigger`, `setError`, or accessible React Hook Form validation flows, including cases where Zod and `zodResolver` should be added or modernized.
ledjay/skills/pencil-mcp Skill
0★ repoControl Pencil.dev design tool via MCP to create, inspect, and export UI designs programmatically. Covers batch_design DSL, design tokens, components, and code sync. Use when working with .pen files, Pencil MCP, design systems, or mockups.
abijith-suresh/skills/skills/handoff Skill
0★ repoCompacts the current conversation into a handoff document for another agent or session to pick up. Use only when the user explicitly invokes the handoff skill. Do not trigger from ordinary requests to save files, commit changes, or open pull requests.
vijpatel7/favorite_skills_and_plugins/.agents/skills/mcp-builder Skill
0★ 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
vijpatel7/favorite_skills_and_plugins/.agents/skills/skill-creator Skill
0★ repoGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
The same file is in 19 other repositories
agykit/agykit/.agent/skills/skill-creator Skill
no license0★ repoGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
The same file is in 19 other repositories
hypertopos/hypertopos-skills/gds-explorer Skill
0★ repoGDS sphere exploration — orientation, population analysis, segmentation, and aggregate analysis. Use when user asks to "explore a sphere", "orient in a sphere", "show me what's in this sphere", "find archetypes", "cluster entities", "segment the population", "compare groups", "what patterns exist", or "give me an overview". Requires hypertopos MCP server.
hypertopos/hypertopos-skills/gds-fraud-investigator Skill
0★ repoAML/fraud detection and financial anomaly investigation via GDS geometric analysis — 3-phase process with 25 typology recipes. Use when user asks to "detect fraud", "screen for money laundering", "find suspicious accounts", "run AML scan", "investigate suspicious transactions", "typology detection", "passive scan for fraud", "detect insider trading", "find anomalous billing", "investigate suspicious transactions", or "financial crime detection". Use this skill for ANY financial anomaly investigation, not just AML. Requires hypertopos MCP server with a financial transaction sphere (account + pair + chain patterns).
hypertopos/hypertopos-skills/gds-investigator Skill
0★ repoAnomaly investigation, root-cause tracing, entity deep-dive, and incident reconstruction via GDS geometric analysis. Use when user asks to "investigate an anomaly", "trace root cause", "why is this entity anomalous", "deep-dive into entity", "what happened to entity X", "reconstruct incident", "compare entities", or "check if this is a false positive". Requires hypertopos MCP server.
hypertopos/hypertopos-skills/gds-monitor Skill
0★ repoGDS sphere health monitoring — drift detection, regime change tracking, alert response, and periodic health assessment. Use when user asks to "check sphere health", "monitor drift", "are there any alerts", "what changed since last time", "detect regime changes", "find emerging anomalies", "temporal health check", or "is the sphere healthy". Requires hypertopos MCP server with temporal data.
2sem/mobile-team-skills/plugins/mobile-team-skills/skills/aso-analysis Skill
no license0★ repoQuick App Store optimization (ASO) checklist and keyword analysis for WhereWeGo. Use on main agent for lightweight ASO checks. Escalate to marketer subagent for full strategy, campaign planning, or detailed competitive analysis.
2sem/mobile-team-skills/plugins/mobile-team-skills/skills/ios-design-spec Skill
no license0★ repoQuick HIG audit, SwiftUI component selection, and accessibility check for simple iOS UI questions. Use on main agent for lightweight design decisions. Escalate to designer subagent for full screen design, navigation architecture, or complex interaction design.
2sem/mobile-team-skills/plugins/mobile-team-skills/skills/ios-test-runner Skill
no license0★ repoBuild and run WhereWeGo iOS tests, report pass/fail results. Use on main agent for smoke tests after simple changes. Escalate to tester subagent for full coverage analysis, diagnosing complex failures, or writing new tests.
2sem/mobile-team-skills/skills/aso-analysis Skill
no license0★ repoQuick App Store optimization (ASO) checklist and keyword analysis for WhereWeGo. Use on main agent for lightweight ASO checks. Escalate to marketer subagent for full strategy, campaign planning, or detailed competitive analysis.
2sem/mobile-team-skills/skills/ios-design-spec Skill
no license0★ repoQuick HIG audit, SwiftUI component selection, and accessibility check for simple iOS UI questions. Use on main agent for lightweight design decisions. Escalate to designer subagent for full screen design, navigation architecture, or complex interaction design.
2sem/mobile-team-skills/skills/ios-test-runner Skill
no license0★ repoBuild and run WhereWeGo iOS tests, report pass/fail results. Use on main agent for smoke tests after simple changes. Escalate to tester subagent for full coverage analysis, diagnosing complex failures, or writing new tests.
Pratiyush/agent-catalog/skills/skill/skill-template Skill
0★ repoScaffold new Agent Skills with best-practice structure and frontmatter. Use when the user wants to create a new skill, bootstrap a skill directory, or generate SKILL.md boilerplate following the Agent Skills spec.
gotlougit/skills/making-feedback-loopable Skill
0★ repoScaffolds build/test/lint/runtime checks so agents get structured, self-locating feedback with file paths, line numbers, and error codes. Use when setting up a repo for AI-assisted development, when an agent is failing to debug due to weak diagnostics, or when asked to make a codebase more LLM-friendly.
timi-ty/agent-forge/skills/commit-agent-changes Skill
0★ repoIdentify the current agent's code changes, create a branch, group changes into logical commits, and open a PR. Use when the user says "commit my changes", "commit agent changes", "create a PR from this session", "push what you changed", or wants to turn the current agent's work into a pull request.
timi-ty/agent-forge/skills/playwright-pool Skill
0★ repoSet up and use the Playwright browser pool MCP server. Enables multiple agents to run isolated browser sessions simultaneously without contention. Works with both Cursor and Claude Code. TRIGGER on "set up playwright pool", "install playwright pool", "browser pool", or any browser automation task where session isolation is needed. Also triggered automatically by sync-skills after first install.