Context & AI engineering
25,815 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
nimadorostkar/Claude-Skills-collection/skills/ai/llm-evaluation Skill
25★ repoUse when measuring the quality of an LLM feature. Covers building an evaluation set, choosing metrics, LLM-as-judge and its pitfalls, regression testing prompts, and evaluating in production.
nimadorostkar/Claude-Skills-collection/skills/ai/llm-integration Skill
25★ repoUse when integrating an LLM API into an application. Covers streaming, retries and rate limits, timeouts, caching, fallback across providers, and the production concerns that a tutorial integration ignores.
nimadorostkar/Claude-Skills-collection/skills/ai/mcp-server Skill
25★ repoUse when building a Model Context Protocol server. Covers tool, resource, and prompt design, transport choice, authentication, error handling, and testing an MCP server against a real client.
nimadorostkar/Claude-Skills-collection/skills/ai/prompt-engineering Skill
25★ repoUse when writing or improving prompts for a language model. Covers instruction structure, examples, reasoning elicitation, output formatting, and systematically diagnosing why a prompt fails.
nimadorostkar/Claude-Skills-collection/skills/ai/rag Skill
25★ repoUse when building retrieval-augmented generation. Covers chunking, embedding and hybrid search, reranking, grounding and citation, and diagnosing whether a bad answer is a retrieval failure or a generation failure.
ur-grue/autopunk-media-skills/.claude/skills/skill-creator Skill
25★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.
The same file is in 4 other repositories
mike007jd/game-superpowers/publish/clawhub/gsp-orchestrator Skill
25★ repoUse when a request needs routing across this Game Superpowers collection for build, audit, repair, or polish work.
mike007jd/game-superpowers/publish/clawhub/gsp-subagent-build-loop Skill
25★ repoUse when game implementation should default to a builder-reviewer-verifier loop instead of one monolithic pass.
mike007jd/game-superpowers/skills/gsp-orchestrator Skill
25★ repoUse when a request needs routing across this Game Superpowers collection for build, audit, repair, or polish work.
mike007jd/game-superpowers/skills/gsp-subagent-build-loop Skill
25★ repoUse when game implementation should default to a builder-reviewer-verifier loop instead of one monolithic pass.
Vanguard frontier agentic install
Raishin/vanguard-frontier-agentic/plugins/vanguard-frontier-agentic/skills/vanguard-frontier-agentic-install Skill
25★ repoInstall all Vanguard Frontier Agentic Codex agents and companion skills into the current user's ~/.codex home after adding or installing the plugin marketplace.
Aws bedrock agent security governor
Raishin/vanguard-frontier-agentic/skills/aws/aws-bedrock-agent-security-governor Skill
25★ repoReview Amazon Bedrock agents, AgentCore, Guardrails, knowledge bases, action groups, memory, MCP/tool integrations, prompt-injection and prompt-leakage defenses, PII handling, encryption, logging, observability, and least-privilege IAM. Use for AWS-native GenAI and agent security posture.
Aws devops agent skill designer
Raishin/vanguard-frontier-agentic/skills/aws/aws-devops-agent-skill-designer Skill
25★ repoDesign, review, and improve AWS DevOps Agent-compatible skills, investigation workflows, learned skills, tool-use best practices, agent type targeting, frontmatter descriptions, reference materials, and operational output contracts. Use when creating or adapting skills for AWS DevOps Agent or AWS-style incident agents.
Copilot data readiness protocol
Raishin/vanguard-frontier-agentic/skills/cross-functional/copilot-data-readiness-protocol Skill
25★ repoUse this skill before enabling Microsoft 365 Copilot for any user population. Runs an oversharing assessment, applies sensitivity labels and DLP controls, validates permissions baseline, and confirms a secure data foundation exists. Orchestrates m365-copilot-readiness-governance-agent as primary, m365-identity-zero-trust-agent for identity-layer controls, and copilot-governance-maestro-agent for cross-pillar sign-off. Hard refusal: Microsoft 365 Copilot must not be enabled for any user until the oversharing baseline is established and remediated. Never requests credentials, tenant IDs, or customer data. Production-impacting steps escalate to the relevant data owner or compliance team.
Identity to data access protocol
Raishin/vanguard-frontier-agentic/skills/cross-functional/identity-to-data-access-protocol Skill
25★ repoUse this skill when an identity lifecycle event (joiner, mover, leaver) or an access request must be evaluated end-to-end across Microsoft Entra identity, Conditional Access policy, and data access governance under a Zero Trust posture. Orchestrates m365-identity-zero-trust-agent as primary and m365-copilot-readiness-governance-agent for data-layer governance. Gates include access review sign-off and least-privilege validation before any access grant is recommended. Does not approve access; all recommendations require human owner confirmation. Never requests credentials, tenant IDs, or customer data.
Raishin/vanguard-frontier-agentic/skills/microsoft/copilot-governance-maestro Skill
25★ repoRoute Microsoft Copilot and Copilot Studio governance requests to the narrowest specialist or team of specialists from the catalog. Use when you do not already know the specialist. Not for direct Copilot governance answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatches live-guard agents — requires explicit human confirmation with blast-radius and rollback before routing to any broad agent publishing or connector/plugin access grant operation.
Copilot studio agent governance alm
Raishin/vanguard-frontier-agentic/skills/microsoft/copilot-studio-agent-governance-alm Skill
25★ repoReview Microsoft Copilot Studio agent governance and application lifecycle management health including authentication configuration, DLP policies for connectors and actions, environment strategy, solution-based ALM across dev/test/prod, content moderation, analytics and telemetry, human-handoff and approval boundaries, sharing and publishing controls, and compliance posture via Microsoft Purview. Use to detect ungoverned agent publishing, overly permissive connector grants, absent DLP enforcement, and missing ALM discipline. Static review only; broad publishing and connector grants are live-guard gated.
M365 copilot readiness governance
Raishin/vanguard-frontier-agentic/skills/microsoft/m365-copilot-readiness-governance Skill
25★ repoReview Microsoft 365 Copilot readiness posture and data-exposure governance against the Microsoft Zero Trust 7-layer model. Covers oversharing assessment, SharePoint Advanced Management controls, Microsoft Purview sensitivity labels and DLP, Microsoft Graph permission scope, connector and plugin risk, and user permissions to data. Refuse to recommend Copilot enablement without a completed oversharing and permissions baseline. Prefer static review and advisory guidance; escalate live-tenant configuration mutations to live-guard gate.
Raishin/vanguard-frontier-agentic/skills/microsoft/microsoft-maestro Skill
25★ repoRoute Microsoft SaaS tasks to the right sub-maestro (m365-maestro-agent, d365-maestro-agent, power-platform-maestro-agent, copilot-governance-maestro-agent) or directly to a specialist. Use when you do not already know the specialist. Not for direct Microsoft answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single sub-maestro or agent for focused tasks, parallel team (max 4) for multi-domain tasks. Refuses Azure IaaS and infrastructure tasks and deflects to azure-maestro. Never auto-dispatches live-guard agents — requires explicit human confirmation with blast-radius and rollback before routing to any live-tenant-mutation agent.
Netsuite ai connector mcp skill
Raishin/vanguard-frontier-agentic/skills/netsuite/netsuite-ai-connector-mcp-skill Skill
25★ repoFlashlight skill for reviewing the security and governance posture of NetSuite AI Connector Service (MCP) deployments. Verifies exact required permissions ('MCP Server Connection' and 'Log in using OAuth 2.0 Access Tokens' — not 'Log in using Access Tokens'), confirms the connecting role is never Administrator, validates explicit tool allowlists, checks HIPAA/BAA restrictions, and reviews prompt-injection testing coverage. T0 static review — no live account connection required. Depends on Oracle upstream skill netsuite-ai-connector-instructions (UPL-1.0) for tool-selection decision trees and SuiteQL safety patterns. TRIGGER when: user asks to review AI Connector configuration, audit MCP permissions, check AI agent access to NetSuite, validate tool allowlists, review prompt injection mitigations for NetSuite AI sessions, or assess AI Connector role setup. Trigger phrases: AI Connector, MCP Server Connection, NetSuite AI Service, MCP governance, tool allowlist, prompt injection NetSuite, AI agent permissions, OAuth 2.0 Access Tokens permission. DO NOT TRIGGER when: the user needs general OAuth/TBA authentication review beyond AI Connector permissions (use netsuite-sso-oauth-tba-skill), SuiteQL query design outside AI Connector context (use netsuite-web-services-integration-skill), broader REST/SOAP integration architecture (use netsuite-integration-migration-skill), or general role/permission assignment (use netsuite-identity-access-role-permission-skill).
Raishin/vanguard-frontier-agentic/skills/netsuite/netsuite-ai-foundations-skill Skill
25★ repoFlashlight skill for reviewing NetSuite AI feature enablement and AI Connector Service configuration posture, aligned to the AI Foundations Associate certification (N16765GC10, available). T0 static review — no live account connection required. NOTE: AI Specialist and AI Professional certifications are COMING SOON and are not yet available; this skill does not cover those levels. TRIGGER when: user asks to review NetSuite AI feature enablement (bill matching, anomaly detection, text enhancement, predicted risk), AI Connector Service configuration, MCP Server Connection permission setup, OAuth 2.0 Access Tokens permission for AI roles, HIPAA/BAA restriction for healthcare accounts, or AI governance and PII exposure controls. Trigger phrases: AI Foundations review, AI Connector configuration, MCP Server Connection permission, NetSuite AI features, AI bill matching, AI anomaly detection, HIPAA AI restriction, AI governance review, Log in using OAuth 2.0 Access Tokens. DO NOT TRIGGER when: request is about AI Connector MCP tool execution or SuiteQL query safety (use netsuite-ai-connector-mcp-agent); OAuth 2.0 authentication setup beyond the AI role (use netsuite-sso-oauth-tba-agent); SuiteScript code security (use netsuite-suitescript-secure-code-review-agent); or live account mutation is required (use netsuite-live-org-mutation-guard-agent). Never assert that AI Specialist or AI Professional certifications are available — they are COMING SOON.
Nvidia agentic ai platform review
Raishin/vanguard-frontier-agentic/skills/nvidia/nvidia-agentic-ai-platform-review Skill
25★ repoUse this skill when reviewing agentic-AI platforms built on the NVIDIA stack — NeMo Agent Toolkit, NIM-as-tool patterns, retrieval-augmented generation pipelines, tool-call safety, agent memory boundaries, and per-tenant audit logging. Trigger when the user asks whether agent tool calls are sandboxed, whether agent memory is tenant-scoped, whether tool definitions are signed, or whether the deployment meets NCP-AAI expectations.
Nvidia tensorrt llm deployment review
Raishin/vanguard-frontier-agentic/skills/nvidia/nvidia-tensorrt-llm-deployment-review Skill
25★ repoUse this skill when reviewing TensorRT or TensorRT-LLM deployment artifacts statically — ONNX/PyTorch export pipelines, precision selection (FP16/BF16/INT8/FP8/INT4), calibration cache integrity, dynamic shape profiles, custom plugin loading, engine cache and serialized engine provenance, runtime memory pool sizing. Trigger when the user asks whether a TensorRT build script, calibration pipeline, or trtexec invocation follows NVIDIA's published guidance.
Oci compute instance agent operator
Raishin/vanguard-frontier-agentic/skills/oci/oci-compute-instance-agent-operator Skill
25★ repoOperate and review OCI Compute instance-agent commands safely with scoped command payloads, target ownership, output handling, timeout controls, and mutation approval gates.
Oracle oci mcp grounded advisor
Raishin/vanguard-frontier-agentic/skills/oci/oracle-oci-mcp-grounded-advisor Skill
25★ repoGround Oracle, OCI, SQLcl, database, and Model Context Protocol recommendations in official Oracle sources and read-only evidence before advising.
Raishin/vanguard-frontier-agentic/skills/qa/llm-ai-pipeline-test-review Skill
25★ repoUse this skill when reviewing how an LLM or AI pipeline is evaluated — metric selection, golden datasets, threshold governance, adversarial coverage, and regression gating — to determine whether low-quality or unsafe model outputs can ship undetected. Trigger when a user provides evaluation configuration files, DeepEval or RAGAS test scripts, eval CI steps, or asks whether their AI pipeline actually prevents a bad model from reaching production. This skill reviews evaluation setup statically; it does not call LLM APIs, run evaluations, or contact inference endpoints.
Sap data privacy analytics ai protocol
Raishin/vanguard-frontier-agentic/skills/sap/sap-data-privacy-analytics-ai-protocol Skill
25★ repoCross-functional coordination protocol governing data privacy, analytics, and AI governance handoffs in SAP landscapes. Covers PII in Datasphere data products, analytics exports from SAP Analytics Cloud, RAG pipelines, embedding generation, prompt logging, SAP Generative AI Hub usage, Joule adoption, and model outputs that could leak sensitive business data. Defines data classification, consent and purpose limitation gates, approval requirements, and audit packaging. Never mutates live systems and never bypasses any guarded-mutating gate.
wells1137/media-skills/skills/kling-studio Skill
no license24★ repoFull-featured Kling 3.0 Omni video generation skill. Covers text-to-video, image-to-video, video editing (base mode), video reference (feature mode), multi-shot generation, and audio-synced video. Includes validated API constraint rules and prompt engineering guide.
The same file is in 2 other repositories
wells1137/media-skills/skills/seedance-prompter Skill
no license24★ repoExpert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and needs the best possible prompt.
The same file is in 2 other repositories
alebgl77/claude-inc/skills/claude-mem Skill
24★ repoPersistent filesystem memory across sessions — maintains memory/ with decisions.md, context.md, glossary.md and sessions/YYYY-MM-DD.md, loads and summarizes state at session start, appends decisions and open threads at session end, compacts monthly, and refuses secrets and transient noise. Use when the user says "remember this", "what did we decide about X", "pick up where we left off", or when starting or closing a session on a long-running project.
alebgl77/claude-inc/skills/hook-generator Skill
24★ repoGenerates 20-hook batches for any topic across eight proven patterns — curiosity gap, contrarian, specific number, mistake/warning, transformation, insider secret, question, call-out-the-reader — each tagged with pattern and platform fit, plus a top-3 pick with rationale. Refuses clickbait the content can't cash. Use when the user says "give me hooks for...", "punch up this opening line", "my posts get no traction", or "title options for this video".
alebgl77/claude-inc/skills/mcp-builder Skill
24★ repoScaffolds and ships MCP servers in Python (FastMCP) or TypeScript (@modelcontextprotocol/sdk) — tools designed around workflows rather than raw endpoints, with model-guiding schemas and error messages, pagination, a direct-call test harness, and wiring into .mcp.json or claude mcp add. Use when the user says "build an MCP server for X", "wrap this API so Claude can call it", "add a tool to our server", or "connect Claude to our internal service".
alebgl77/claude-inc/skills/skill-creator Skill
24★ repoAuthors new SKILL.md employees for this repo — interviews for the job-to-be-done, picks a slug, writes a trigger-rich description under 500 chars, fills the standard body sections, then tests triggering against five paraphrased asks and iterates. Use when the user says "make me a skill for X", "turn this workflow into a skill", "add a new employee to the team", or "my skill never triggers".
charlieviettq/awesome-agent-skill/.claude/skills/agent-tool-contracts Skill
24★ repoDesign agent tools and CLI surfaces—schemas, naming, errors, idempotency, and discoverability for LLM callers. Use when defining tools for agents, SDKs, or AI-native CLIs.
charlieviettq/awesome-agent-skill/.claude/skills/autoskill Skill
24★ repoObserve the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
charlieviettq/awesome-agent-skill/.claude/skills/context-window-management Skill
24★ repoManage LLM context budgets—prioritization, summarization, compaction, and what to load vs reference. Use for long sessions, large repos, or multi-doc tasks.
charlieviettq/awesome-agent-skill/.claude/skills/dispatching-parallel-agents Skill
24★ repoSplit independent work across parallel agents with explicit boundaries and a parent integration review. Use only when user allows subagents and tasks do not share mutable files.
charlieviettq/awesome-agent-skill/.claude/skills/gpt-taste Skill
24★ repoElite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing. Use when building motion-rich frontend pages with stricter GPT/Codex design enforcement.
charlieviettq/awesome-agent-skill/.claude/skills/gstack-benchmark-models Skill
24★ repoCross-model benchmark for gstack skills. (gstack).
charlieviettq/awesome-agent-skill/.claude/skills/gstack-benchmark Skill
24★ repoPerformance regression detection using the browse daemon. (gstack).
charlieviettq/awesome-agent-skill/.claude/skills/gstack-pair-agent Skill
24★ repoPair a remote AI agent with your browser. (gstack).
charlieviettq/awesome-agent-skill/.claude/skills/gstack-sync-gbrain Skill
24★ repoKeep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with state (gstack).
charlieviettq/awesome-agent-skill/.claude/skills/mcp-builder Skill
24★ repoDesign and implement MCP servers—tools, resources, prompts, schemas, and error contracts for agent clients. Use when adding MCP integration or exposing capabilities to Cursor/Claude agents.
charlieviettq/awesome-agent-skill/.claude/skills/mcp-ecosystem-optimizer Skill
24★ repoReview and optimize MCP server setup—inventory, registry hygiene, config, versioning, and observability. Use when managing multiple MCP servers in Cursor or Claude.
charlieviettq/awesome-agent-skill/.claude/skills/memory-management Skill
24★ repoTwo-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
charlieviettq/awesome-agent-skill/.claude/skills/rag-systems Skill
24★ repoDesign retrieval-augmented generation pipelines—chunking, embeddings, retrieval, reranking, grounding, and evaluation. Use when building or improving doc Q&A, code search agents, or knowledge bases.
charlieviettq/awesome-agent-skill/.claude/skills/subagent-driven-development Skill
24★ repoExecute an approved plan via one subagent per task with spec and quality checks. Use only when user allows subagents and a written plan exists.
charlieviettq/awesome-agent-skill/.claude/skills/tech-mcp-server-dev Skill
24★ repo"Build MCP (Model Context Protocol) servers including tool definition, schema design, authentication, error handling, and Claude Code integration. Use this skill when the user needs to create an MCP server, expose APIs or databases to AI agents, design tool schemas, or integrate with Claude Code — even if they say 'build an MCP server', 'connect Claude to our database', 'expose our API to AI', or 'create a tool for Claude Code'.".
charlieviettq/awesome-agent-skill/.claude/skills/tech-prompt-engineering Skill
24★ repo"Debug and harden production LLM prompts — handle prompt injection, output format drift, instruction forgetting in long contexts, and cross-model portability issues. Use this skill when the user ships an LLM-powered feature to production and needs to diagnose why outputs are inconsistent, unsafe, or regressed after model updates — NOT for basic 'write a better prompt' questions.".
charlieviettq/awesome-agent-skill/.claude/skills/va-llm-architect Skill
24★ repo"Use when designing LLM systems for production, implementing fine-tuning or RAG architectures, optimizing inference serving infrastructure, or managing multi-model deployments.".
charlieviettq/awesome-agent-skill/.claude/skills/va-multi-agent-coordinator Skill
24★ repo"Use when coordinating multiple concurrent agents that need to communicate, share state, synchronize work, and handle distributed failures across a system.".
charlieviettq/awesome-agent-skill/.claude/skills/va-prompt-engineer Skill
24★ repo"Use this agent when you need to design, optimize, test, or evaluate prompts for large language models in production systems.".
charlieviettq/awesome-agent-skill/.claude/skills/work-access-handoff Skill
24★ repoExplain and document work access layers—repo permissions, local vs cloud environments, handoff packages for collaborators.
charlieviettq/awesome-agent-skill/.cursor/skills/ai-agent-systems/agent-evaluation Skill
24★ repoEvaluate LLM agents and tool-using workflows—task success, tool accuracy, latency/cost, safety, and regression suites. Use when shipping agent features, comparing prompts/models, or debugging agent failures. Triggers: "agent eval", "benchmark agent", "tool accuracy", "agent regression".
charlieviettq/awesome-agent-skill/.cursor/skills/ai-agent-systems/agent-tool-contracts Skill
24★ repoDesign agent tools and CLI surfaces—schemas, naming, errors, idempotency, and discoverability for LLM callers. Use when defining tools for agents, SDKs, or AI-native CLIs. Triggers: "tool schema", "agent tool", "function calling", "AI CLI".
charlieviettq/awesome-agent-skill/.cursor/skills/ai-agent-systems/context-window-management Skill
24★ repoManage LLM context budgets—prioritization, summarization, compaction, and what to load vs reference. Use for long sessions, large repos, or multi-doc tasks. Triggers: "context window", "too long", "summarize context", "token budget".
charlieviettq/awesome-agent-skill/.cursor/skills/ai-agent-systems/dispatching-parallel-agents Skill
24★ repoSplit independent work across parallel agents with explicit boundaries and a parent integration review. Use only when user allows subagents and tasks do not share mutable files. Triggers: "parallel agents", "fan out tasks", "run in parallel".
charlieviettq/awesome-agent-skill/.cursor/skills/ai-agent-systems/mcp-builder Skill
24★ repoDesign and implement MCP servers—tools, resources, prompts, schemas, and error contracts for agent clients. Use when adding MCP integration or exposing capabilities to Cursor/Claude agents. Triggers: "MCP server", "MCP tool", "Model Context Protocol", "build MCP".
charlieviettq/awesome-agent-skill/.cursor/skills/ai-agent-systems/mcp-ecosystem-optimizer Skill
24★ repoReview and optimize MCP server setup—inventory, registry hygiene, config, versioning, and observability. Use when managing multiple MCP servers in Cursor or Claude. Triggers: "MCP server", "MCP config", "MCP registry", "optimize MCP", "too many MCP tools".
charlieviettq/awesome-agent-skill/.cursor/skills/ai-agent-systems/rag-systems Skill
24★ repoDesign retrieval-augmented generation pipelines—chunking, embeddings, retrieval, reranking, grounding, and evaluation. Use when building or improving doc Q&A, code search agents, or knowledge bases. Triggers: "RAG", "vector search", "embeddings", "retrieval", "knowledge base".