Context & AI engineering
25,841 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
jeremylongshore/claude-code-plugins-plus-skills/plugins/saas-packs/shopify-pack/skills/shopify-ai-toolkit-wrapper Skill
2,628★ repo'Integrate Shopify''s AI Toolkit MCP server with Claude Code for GraphQL validation,
jeremylongshore/claude-code-plugins-plus-skills/plugins/saas-packs/skill-databases/windsurf/skills/windsurf-cascade-context Skill
2,628★ repo'Manage Cascade context window and memory for complex projects. Activate when users mention
jeremylongshore/claude-code-plugins-plus-skills/plugins/saas-packs/skill-databases/windsurf/skills/windsurf-mcp-integration Skill
2,628★ repo'Manage integrate MCP servers with Windsurf for extended capabilities. Activate when users mention
jeremylongshore/claude-code-plugins-plus-skills/plugins/security/agent-safety-preflight/skills/agent-safety-preflight Skill
2,628★ repoGenerate a local repository risk receipt before Claude Code or other AI-agent edits. Use when the user asks to prepare a repository for agent changes, check for risky hooks or credential-writing automation, or run the /agent-preflight command. Trigger with "run agent preflight", "check this repo before agent edits", or "/agent-preflight".
jeremylongshore/claude-code-plugins-plus-skills/plugins/security/penetration-tester/skills/detecting-eval-exec-usage Skill
2,628★ repoScan a source tree for dynamic-code-execution APIs that an attacker can hijack: Python eval / exec / compile, JavaScript eval / Function() / setTimeout(string), Ruby eval / instance_eval / class_eval, Java ScriptEngine, PHP eval / assert($str), .NET Activator.CreateInstance / Reflection.Emit with dynamic input. Use when: pre-commit gate on any application that parses user-uploaded code (rule engines, formula evaluators, plugin systems), or post-bug-report when "we run user-supplied expressions." Threshold: any call to eval / exec / Function / similar where the argument is not a string literal. Trigger with: "scan eval", "find dynamic exec", "audit eval calls", "code injection patterns".
jeremylongshore/claude-code-plugins-plus-skills/plugins/security/severity1-marketplace/skills/prompt-improver Skill
2,628★ repo'Analyze and improve plugin prompts, skill definitions, and command instructions for clarity, safety, and effectiveness. Use when the user asks to "improve a prompt", "review a skill", "enhance instructions", "make this prompt better", "optimize this command", or "audit prompt quality".
jeremylongshore/claude-code-plugins-plus-skills/plugins/skill-enhancers/skill-creator/skills/agent-creator Skill
2,628★ repo'Create production-grade agent .md files aligned with the Anthropic 2026 spec (16-field schema).
jeremylongshore/claude-code-plugins-plus-skills/plugins/skill-enhancers/skill-creator/skills/skill-creator Skill
2,628★ repo'Create production-grade agent skills aligned with the 2026 AgentSkills.io spec and Anthropic
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/anth-core-workflow-a Skill
2,628★ repo'Build Claude tool use (function calling) workflows with the Messages API.
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/changelog-orchestrator Skill
2,628★ repoDraft changelog PRs by collecting GitHub/Slack/Git changes, formatting with templates, running quality gates, and preparing a branch/PR. Use when generating weekly/monthly release notes or when the user asks to create a changelog from recent merges. Trigger with "changelog weekly", "generate release notes", "draft changelog", "create changelog PR".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/clade-architecture-variants Skill
2,628★ repoBuild different types of Claude-powered applications \u2014 chatbots,\ \ RAG systems, Use when working with architecture-variants patterns. agents, content\ \ pipelines, and code generation tools. Trigger with "claude architecture", "\ anthropic rag", "build with claude", "claude agent pattern", "anthropic app\ \ design".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/clade-core-workflow-b Skill
2,628★ repo'Redirect to claude-embeddings-search for tool use (function calling)
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/clade-embeddings-search Skill
2,628★ repo'Implement tool use (function calling) with Claude to let it execute actions,
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/clade-migration-deep-dive Skill
2,628★ repoMigrate from OpenAI/GPT to Anthropic/Claude \u2014 API differences, \ Use when working with migration-deep-dive patterns. prompt adaptation, SDK swap,\ \ and feature mapping. Trigger with "migrate to claude", "openai to anthropic"\ , "switch from gpt to claude", "replace openai with anthropic".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/clade-reference-architecture Skill
2,628★ repoBuild Claude Code plugins \u2014 skills, agents, MCP servers, hooks,\ \ and slash commands. Use when working with reference-architecture patterns. \ The complete guide to extending Claude Code with the Anthropic plugin system. \ Trigger with "claude code plugin", "build a skill", "create mcp server", \ "anthropic plugin architecture", "claude code hooks".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/claude-reflect Skill
2,628★ repo'Execute self-learning system that captures corrections during sessions and syncs them to CLAUDE.md.
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/cursor-context-management Skill
2,628★ repo'Optimize context window usage in Cursor with @-mentions, context pills, and conversation strategy.
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/cursor-custom-prompts Skill
2,628★ repo'Create effective custom prompts for Cursor AI using project rules, prompt engineering patterns, and
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/detecting-eval-exec-usage Skill
2,628★ repoScan a source tree for dynamic-code-execution APIs that an attacker can hijack: Python eval / exec / compile, JavaScript eval / Function() / setTimeout(string), Ruby eval / instance_eval / class_eval, Java ScriptEngine, PHP eval / assert($str), .NET Activator.CreateInstance / Reflection.Emit with dynamic input. Use when: pre-commit gate on any application that parses user-uploaded code (rule engines, formula evaluators, plugin systems), or post-bug-report when "we run user-supplied expressions." Threshold: any call to eval / exec / Function / similar where the argument is not a string literal. Trigger with: "scan eval", "find dynamic exec", "audit eval calls", "code injection patterns".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/detecting-memory-leaks Skill
2,628★ repoDetect potential memory leaks and analyze memory usage patterns in code. Use when troubleshooting performance issues related to memory growth or identifying leak sources. Trigger with phrases like "detect memory leaks", "analyze memory usage", or "find memory issues".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/google-cloud-agent-sdk-master Skill
2,628★ repo'Execute automatic activation for all google cloud agent development kit (adk) Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/langchain-content-blocks Skill
2,628★ repoWorks correctly with LangChain 1.0's typed content blocks on AIMessage.content \ \u2014 text, tool_use, image, thinking, document \u2014 across Claude, GPT-4o, and \ Gemini, including multi-modal composition and tool-call iteration. Use when composing\ \ multi-modal messages, iterating tool_use blocks, handling Claude's thinking content,\ \ or unifying image inputs across providers. Trigger with "langchain content blocks"\ , "AIMessage.content", "tool_use block", "claude image input", "langchain\ \ multimodal", "thinking block replay", "claude citations".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/langchain-data-handling Skill
2,628★ repoLoad and chunk documents for LangChain 1.0 RAG pipelines correctly \u2014\ language-aware splitters, table-safe PDF loaders, Cloudflare-compatible web \ loaders, chunk-boundary strategies that survive real-world structure. Use when \ building a RAG pipeline, diagnosing why retrieval misquotes a table, or debugging\ \ a crawler returning blank content. Trigger with "langchain document loader"\ , "text splitter", "chunking strategy", "pdf loader", "markdown splitter"\ , "webbaseloader".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/langchain-deep-agents Skill
2,628★ repoBuild a LangGraph 1.0 Deep Agent \u2014 planner + subagents + virtual\ \ filesystem + reflection loop \u2014 without the state-growth and prompt-inheritance\ \ traps. Use when building a long-horizon agent that must plan, delegate subtasks,\ \ work against a scratchpad filesystem, and reflect on progress. Trigger with\ \ "langchain deep agent", "planner subagent", "virtual filesystem agent"\ , "reflection loop", "langgraph deep agent".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/langchain-eval-harness Skill
2,628★ repoBuild reproducible evaluation pipelines for LangChain 1.0 chains and\ \ LangGraph 1.0 agents \u2014 golden datasets, LangSmith evaluate(), ragas RAG\ \ metrics, deepeval LLM-as-judge, agent trajectory analysis, and CI gating on quality\ \ regressions. Use when setting up quality measurement for a new chain, diagnosing\ \ regression after a model switch, or building an evaluation gate for a pull request. \ Trigger with "langchain eval", "langsmith evaluate", "ragas", "llm-as-judge"\ , "agent trajectory eval", "eval regression gate".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/langchain-incident-runbook Skill
2,628★ repoTriage LangChain 1.0 / LangGraph 1.0 production incidents \u2014 LLM-specific\ \ SLOs, provider outage runbook, latency spike decision tree, cost-overrun response, \ agent loop containment. Use during an on-call page, in a post-mortem, or writing \ the team's first LLM runbook. Trigger with "langchain incident", "llm on-call"\ , "langchain slo", "langchain outage", "langchain cost spike", "langchain\ \ agent loop".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/langchain-model-inference Skill
2,628★ repo'Invoke Claude, GPT-4o, and Gemini through LangChain 1.0 without tripping on
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/langchain-prompt-engineering Skill
2,628★ repoManage LangChain 1.0 prompts like code \u2014 LangSmith prompt hub versioning, \ XML-tag conventions for Claude, few-shot example selection, discriminated-union \ extraction schemas, and A/B test wiring. Use when taking ad-hoc prompts into version\ \ control, migrating prompts from f-strings to ChatPromptTemplate, optimizing prompts\ \ for Claude vs GPT-4o vs Gemini, or A/B testing a prompt change. Trigger with\ \ "langchain prompt hub", "langsmith prompts", "prompt versioning", "claude\ \ xml prompt", "few-shot example selector", "prompt engineering".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/lindy-core-workflow-b Skill
2,628★ repo'Configure Lindy triggers, scheduling, multi-agent delegation, and automation.
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/memory-kit Skill
2,628★ repo'Persistent context management for Claude Code sessions. Save, load, update,
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/memory Skill
2,628★ repo'Execute extract and use project memories from previous sessions for context-aware assistance.
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/openrouter-function-calling Skill
2,628★ repo'Implement function/tool calling with OpenRouter models. Use when building agents, structured output, or tool-augmented LLM workflows. Triggers: ''openrouter function calling'', ''openrouter tools'', ''openrouter agent tools'', ''tool use openrouter''.
Orchestrating multi agent systems
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/orchestrating-multi-agent-systems Skill
2,628★ repo'Execute orchestrate multi-agent systems with handoffs, routing, and workflows across AI providers.
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/plane Skill
2,628★ repoPlane is a team behavior observatory — synthesize Plane API data into observations about how teams actually behave under pressure, not just ticket state. Five compound commands surface cycle velocity vs. plan, stale-ticket ownership churn, reviewer gate strength, stated-vs-actual priority drift, and cross-project workload concentration. Reads from the live mcp__plane MCP server when present; documentation-only otherwise. Use when investigating "why is this team's plan diverging from reality", auditing cycle health, finding orphan tickets, identifying review bottlenecks, or onboarding to a new project. Trigger with "/plane-cycle-velocity", "/plane-stale-tickets", "/plane-reviewer-gate-strength", "/plane-priority-drift", "/plane-cross-project-load", "audit Plane cycle", "team behavior plane", "how is my team behaving".
Podium call transcript pipeline
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/podium-call-transcript-pipeline Skill
2,628★ repoDurable, idempotent ingest pipeline for Podium call transcripts — the layer between Podium's transcript webhook and a downstream RAG/LLM queue. Survives minutes-to-hours transcript latency, partial-then-final overwrites, non-English callers, PII leakage to downstream consumers, queue-write failures, and speaker-diarization loss. Use when wiring Podium phone-call transcripts into an AI-assist queue, hardening an existing ingest against transcript drift, redacting PII before transcripts reach an LLM, or building the durable ack/replay layer that feeds podium-rag-context-bridge. Trigger with "podium call transcripts", "podium transcript webhook", "podium transcript ingest", "podium transcript pii redact", "podium transcript chunking", "podium transcript queue".
Podium conversation history export
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/podium-conversation-history-export Skill
2,628★ repoBulk-export Podium conversation, review, and contact history into a vector-store-ready corpus with cursor-paginated full crawls, CDC via updated_at watermarks, attachment URL refresh on expiry, windowed semantic chunking, and PII redaction before embedding. Use when standing up a RAG pipeline on a Podium org, building nightly incremental syncs, or hardening export jobs against attachment expiry. Trigger with "podium history export", "podium rag corpus", "podium cdc sync", "podium incremental export", "podium chunk for embedding".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/podium-rag-context-bridge Skill
2,628★ repoBridge a live Podium call transcript or webchat turn to an LLM by fetching relevant historical conversation context as a structured RAG bundle — vector search over embedded prior conversations + reranking + live Podium contact lookup, merged under a hard latency budget that keeps the call answerable in real time. Use when wiring a transcription-driven agent loop to an LLM that needs cross-channel customer memory, building the substrate that turns "transcript chunk" into "LLM-ready prompt with context", or hardening an existing RAG pipeline against staleness, reranking noise, PII leakage, token-budget overflow, and missed-the-call latency. Trigger with "podium rag", "podium llm context", "podium transcript to llm", "podium retrieval", "podium vector search", "podium real-time context", "podium agent grounding".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/prompt-improver Skill
2,628★ repo'Analyze and improve plugin prompts, skill definitions, and command instructions for clarity, safety, and effectiveness. Use when the user asks to "improve a prompt", "review a skill", "enhance instructions", "make this prompt better", "optimize this command", or "audit prompt quality".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/shopify-ai-toolkit-wrapper Skill
2,628★ repo'Integrate Shopify''s AI Toolkit MCP server with Claude Code for GraphQL validation,
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/skill-creator Skill
2,628★ repo'Create production-grade agent skills aligned with the 2026 AgentSkills.io spec and Anthropic
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/vertex-agent-builder Skill
2,628★ repoBuild and deploy generative AI agents on Vertex AI: Gemini model selection, RAG with grounded retrieval, function calling, multimodal extraction, evaluation, and Agent Engine deployment with operational guardrails (logs, alerts, cost controls). Use when designing, deploying, or operating Vertex AI agents on Google Cloud. Trigger with "build a Vertex agent", "deploy to Agent Engine", or "wire up RAG on Vertex AI".
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/windsurf-cascade-context Skill
2,628★ repo'Manage Cascade context window and memory for complex projects. Activate when users mention
jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/windsurf-mcp-integration Skill
2,628★ repo'Manage integrate MCP servers with Windsurf for extended capabilities. Activate when users mention
jeremylongshore/claude-code-plugins-plus-skills/skills/04-security-advanced/security-benchmark-runner Skill
2,628★ repo'Manage security benchmark runner operations. Auto-activating skill for Security Advanced.
jeremylongshore/claude-code-plugins-plus-skills/skills/05-frontend-dev/react-hook-creator Skill
2,628★ repo'Create react hook creator operations. Auto-activating skill for Frontend Development.
jeremylongshore/claude-code-plugins-plus-skills/skills/10-performance-testing/benchmark-suite-creator Skill
2,628★ repo'Create benchmark suite creator operations. Auto-activating skill for Performance Testing.
jeremylongshore/claude-code-plugins-plus-skills/skills/10-performance-testing/memory-profiler-setup Skill
2,628★ repo'Configure memory profiler setup operations. Auto-activating skill for Performance Testing.
jeremylongshore/claude-code-plugins-plus-skills/workspace/lab/schema-optimization Skill
2,628★ repoMulti-phase schema optimization workflow orchestrator. Creates session directories, spawns phase agents sequentially, validates outputs, aggregates results. Trigger: "run schema optimization", "optimize schema workflow", "execute schema phases"
amElnagdy/delegate-skills/skills/qoder-delegate Skill
2,607★ repoDelegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer.
aaron-he-zhu/aaron-marketing-skills/protocol/memory-management Skill
2,560★ repoUse when the user asks to "remember project context", review saved findings, initialize runtime memory, archive stale work, reconcile notes, or erase a subject; manages authorized HOT/WARM/COLD working memory across all disciplines while preserving registry event ownership and privacy controls. Not for changing canonical registry facts - route those through the owning registry. 项目记忆/跨会话
The same file is in 2 other repositories
cisco-ai-defense/skill-scanner/evals/test_skills/malicious/mcp-atlassian-cve-2026-27825 Skill
no license2,426★ repoSecurity Scanner for Agent Skills
cisco-ai-defense/skill-scanner/evals/test_skills/malicious/prompt-injection Skill
no license2,426★ repoA test skill with prompt injection patterns
bergside/awesome-design-skills/skills/claude Skill
2,314★ repoA research-journal aesthetic printed on warm stone — authoritative, editorial, almost achromatic. Pages live on warm ivory parchment (never pure white), with near-black slate as the dominant ink.
softaworks/agent-toolkit/dist/plugins/agent-md-refactor/skills/agent-md-refactor Skill
2,311★ repoRefactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
The same file is in 5 other repositories
Backend to frontend handoff docs
softaworks/agent-toolkit/dist/plugins/backend-to-frontend-handoff-docs/skills/backend-to-frontend-handoff-docs Skill
2,311★ repoCreate API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.
The same file is in 3 other repositories
softaworks/agent-toolkit/dist/plugins/command-creator/skills/command-creator Skill
2,311★ repoThis skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.
The same file is in 4 other repositories
softaworks/agent-toolkit/dist/plugins/session-handoff/skills/session-handoff Skill
2,311★ repoCreates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.
The same file is in 5 other repositories
softaworks/agent-toolkit/skills/agent-md-refactor Skill
2,311★ repoRefactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
The same file is in 5 other repositories
softaworks/agent-toolkit/skills/command-creator Skill
2,311★ repoThis skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.
The same file is in 4 other repositories
softaworks/agent-toolkit/skills/session-handoff Skill
2,311★ repoCreates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.
The same file is in 5 other repositories