Context & AI engineering
25,772 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
ivanshamaev/de-agent-skills/group_skills/starrocks_group_skills/starrocks_ai_incident_rca Skill
no license15★ repoStarRocks AI incident RCA — autonomous root cause analysis agent for FE/BE failures, memory spike diagnosis (BE heap/process memory), Routine Load pause RCA (ErrorLogUrls + error patterns), Kafka consumer lag spike analysis, compaction backlog detection, tablet replication failures, OOM kill patterns, query timeout clusters, FE GC pressure detection, structured incident report generation
ivanshamaev/de-agent-skills/group_skills/starrocks_group_skills/starrocks_memory_tuning Skill
no license15★ repoStarRocks memory tuning — BE memory architecture (mem_limit, query pool, load pool, compaction pool, metadata cache), query memory limits (query_mem_limit session var), memory spill to disk (spill_mode), OOM analysis (be.out log), mem_tracker hierarchy, FE heap tuning (JAVA_OPTS), Primary Key table persistent index memory, jemalloc tuning
ivanshamaev/de-agent-skills/group_skills/trino_group_skills/trino_airflow_orchestration Skill
no license15★ repoAirflow orchestration for Trino pipelines — TrinoOperator and TrinoHook usage, trino_conn_id connection setup, idempotent DAG patterns (INSERT INTO / MERGE with deterministic run_ids), partition-aware scheduling with Airflow logical_date, sensor patterns (TrinoCheckOperator), SLA monitoring, retry configuration for Trino queries, incremental load orchestration, dbt + Trino Airflow integration (BashOperator/DbtRunOperator), metadata-driven DAG generation
ivanshamaev/de-agent-skills/group_skills/trino_group_skills/trino_memory_and_spill_tuning Skill
no license15★ repoTrino memory management and spill-to-disk tuning — query.max-memory/query.max-total-memory/query.max-memory-per-node properties, memory.heap-headroom-per-node, JVM heap sizing (80% of RAM), spill-enabled/spiller-spill-path/spill-compression-codec configuration, exchange buffer tuning, OOM kill diagnosis, memory pool sizing, fault-tolerant execution exchange manager (S3/filesystem), session-level memory overrides, memory-intensive operator patterns (HashJoin/Sort/Window/GroupBy)
ivanshamaev/de-agent-skills/group_skills/trino_group_skills/trino_self_healing_platform Skill
no license15★ repoAutonomous self-healing Trino platform — Python watchdog agents for automatic worker restart detection, hung query killer, OOM-killed query resubmission, Iceberg compaction auto-trigger on small-file detection, stale statistics auto-ANALYZE, cluster memory pressure relief (kill low-priority queries), anomaly detection on query latency (Z-score), Claude-based RCA generation for incidents, Prometheus AlertManager webhook integration, Airflow self-healing sensor
ivanshamaev/de-agent-skills/skills/mcp_server Skill
no license15★ repoMCP (Model Context Protocol) server development — FastMCP/Python SDK, tools/resources/prompts primitives, STDIO and Streamable HTTP transports, Claude Desktop/Claude Code client config, MCP Inspector testing, security best practices (input validation/OAuth2/confused deputy prevention), production Docker/Kubernetes deployment, agentic data platform integration
ivanshamaev/de-agent-skills/skills/rag_pipeline Skill
no license15★ repoUse when designing, building, or debugging a RAG (Retrieval-Augmented Generation) data pipeline — document ingestion, chunking strategies (fixed/recursive/semantic/structure-aware), embedding models (OpenAI/Cohere/sentence-transformers), vector stores (pgvector/Chroma/Qdrant/Weaviate), incremental refresh, hybrid retrieval (dense + BM25 + RRF), re-ranking with cross-encoders, metadata filtering, and production monitoring.
G1Joshi/Agent-Skills/skills/ai-ml/claude Skill
15★ repoAnthropic Claude AI models for analysis and coding. Use for AI assistants.
G1Joshi/Agent-Skills/skills/ai-ml/github-copilot Skill
15★ repoGitHub Copilot AI code suggestions and chat. Use for code completion.
G1Joshi/Agent-Skills/skills/ai-ml/openai-gpt Skill
15★ repoOpenAI GPT models API for chat, completion, and embeddings. Use for AI integration.
Sendmux/skills/plugins/sendmux/skills/sendmux-mailbox-agent Skill
no license15★ repoWork efficiently with one Sendmux mailbox from an AI agent. Use for reading, searching, counting, syncing, triaging, filing, deleting, threading, or replying from a mailbox with an smx_mbx_ key or scoped smx_agent_ token, especially when the user asks an agent to inspect an inbox, find relevant messages, mark messages, or continue from a prior mailbox sync state.
The same file is in 1 other repository
Sendmux/skills/plugins/sendmux/skills/sendmux-mcp-setup Skill
no license15★ repoConfigure Sendmux Model Context Protocol servers for AI agent clients, using hosted OAuth first when supported and secret-backed local env config otherwise. Use when the user wants to install sendmux-mcp, connect the hosted Sendmux MCP endpoint, run local stdio or HTTP MCP servers, set mailbox/management/sending key scopes, add bearer headers, or write MCP config for Claude Code, Cursor, Codex, VS Code/Copilot, Copilot CLI, Gemini CLI, Cline, or Windsurf/Cascade.
The same file is in 1 other repository
Sendmux/skills/skills/sendmux-mailbox-agent Skill
no license15★ repoWork efficiently with one Sendmux mailbox from an AI agent. Use for reading, searching, counting, syncing, triaging, filing, deleting, threading, or replying from a mailbox with an smx_mbx_ key or scoped smx_agent_ token, especially when the user asks an agent to inspect an inbox, find relevant messages, mark messages, or continue from a prior mailbox sync state.
The same file is in 1 other repository
Sendmux/skills/skills/sendmux-mcp-setup Skill
no license15★ repoConfigure Sendmux Model Context Protocol servers for AI agent clients, using hosted OAuth first when supported and secret-backed local env config otherwise. Use when the user wants to install sendmux-mcp, connect the hosted Sendmux MCP endpoint, run local stdio or HTTP MCP servers, set mailbox/management/sending key scopes, add bearer headers, or write MCP config for Claude Code, Cursor, Codex, VS Code/Copilot, Copilot CLI, Gemini CLI, Cline, or Windsurf/Cascade.
The same file is in 1 other repository
a-ariff/ariff-claude-plugins/plugins/memory-sync/skills/memory-sync Skill
14★ repoMemory Sync Skill
The same file is in 4 other repositories
a-ariff/ariff-claude-plugins/plugins/subagent-driven-development/skills/subagent-driven-development Skill
14★ repoUse fresh agents for focused subtasks to avoid context pollution
codingSamss/all-my-ai-needs/platforms/claude/skills/handoff Skill
no license14★ repoClaude Code + Codex 双平台 AI dotfiles:统一管理 skills/agents/hooks,并一键同步到 ~/.claude 与 ~/.codex。
codingSamss/all-my-ai-needs/platforms/claude/skills/skill-creator Skill
no license14★ 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 753 other repositories
codingSamss/all-my-ai-needs/platforms/codex/skills/aihot Skill
no license14★ repoClaude Code + Codex 双平台 AI dotfiles:统一管理 skills/agents/hooks,并一键同步到 ~/.claude 与 ~/.codex。
The same file is in 1 other repository
codingSamss/all-my-ai-needs/platforms/codex/skills/handoff Skill
no license14★ repoClaude Code + Codex 双平台 AI dotfiles:统一管理 skills/agents/hooks,并一键同步到 ~/.claude 与 ~/.codex。
codingSamss/all-my-ai-needs/platforms/codex/skills/taste-design/references/skills/taste-gpt Skill
no license14★ repo偏 Codex/GPT 的高强度页面设计与动效规则入口;适合需要强视觉冲击、AIDA 结构、GSAP 动效和非模板化排版的页面。
Calliope-Editor/writing-skills/skills/critique/agent-first-pages Skill
14★ repoSimulates a literary agent reading a manuscript's opening pages cold from the slush pile and delivering the verdict — request more, or pass — with the honest reasoning behind it. Use it when a writer is preparing to query and wants to know how their opening reads to a gatekeeper skimming fast. It reads and judges; it never writes or rewrites the author's prose.
Amey-Thakur/AI-SKILLS/skills/big-tech-processes/oncall-handoff Skill
14★ repoHand off an on-call rotation by transferring open incidents, watch items, and the tribal context runbooks miss. Use at the end of a shift or rotation when the pager passes to the next responder and continuity of understanding matters.
Amey-Thakur/AI-SKILLS/skills/data-engineering/pipeline-orchestration Skill
14★ repoOrchestrate data DAGs with data-aware scheduling, bounded retries, and SLAs that page the right owner. Use when structuring workflows in an orchestrator or fixing 3am cron archaeology.
Amey-Thakur/AI-SKILLS/skills/debugging/memory-leaks Skill
14★ repoFind the object that never gets freed by comparing heap snapshots and following retention paths. Use when a process grows in memory over time, gets OOM-killed, or slows under a garbage collector that keeps working harder.
Amey-Thakur/AI-SKILLS/skills/debugging/profiling-memory Skill
14★ repoAttribute memory growth and allocation churn to the exact call sites that produce it using an allocation profiler. Use when a process grows without bound, spends too much time in garbage collection, or allocates far more than its working set explains.
Amey-Thakur/AI-SKILLS/skills/embedded-iot/embedded-memory-constraints Skill
14★ repoFit firmware into kilobytes with static allocation, measured stack sizing, and linker-map budgeting. Use when developing on microcontrollers or debugging overflows and fragmentation on-device.
Amey-Thakur/AI-SKILLS/skills/gpu-ai-infrastructure/gpu-memory-hierarchy Skill
14★ repoPlace data across the GPU memory tiers so a kernel is limited by math rather than by repeated trips to HBM. Use when a kernel is memory-bound, when deciding what to stage in shared memory or L2, or when register spills are stalling a hot loop.
Amey-Thakur/AI-SKILLS/skills/jvm-dotnet/jvm-memory-model Skill
14★ repoApply happens-before reasoning, volatile, and safe publication to write correct concurrent Java/Kotlin. Use when writing shared-state JVM code or diagnosing visibility and reordering bugs.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/agent-memory Skill
14★ repoDesign memory for an AI agent so it recalls what matters and forgets the rest, without drowning in its own history. Use when adding persistence, context recall, or long-running state to an agent.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/agentic-loops Skill
14★ repoBuild reliable agent loops (plan, act, observe) with termination, error recovery, and progress guarantees. Use when building an LLM agent that takes multiple tool-using steps toward a goal.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/coding-agent-workflow Skill
14★ repoDirect and supervise a coding agent (Claude Code, Cursor, Antigravity) so it ships correct, verified work. Use when delegating engineering tasks to an AI agent and you want reliable results, not plausible-looking ones.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/context-engineering Skill
14★ repoAssemble what goes into an LLM's context on each call: selecting, ordering, and formatting the right information. Use when deciding what to put in a prompt or debugging why a model ignores or misuses provided information.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/context-window-management Skill
14★ repoBudget tokens across system prompt, history, and retrieval, with compaction that keeps what matters. Use when building long-running LLM applications or debugging context overflow and mid-conversation amnesia.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/embeddings-selection Skill
14★ repoChoose embedding models and chunking by evaluating retrieval on your own corpus, not by leaderboard rank. Use when building semantic search or RAG and deciding how to embed and chunk.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/fine-tuning-vs-prompting Skill
14★ repoDecide between prompting, retrieval, and fine-tuning with eval-first discipline and honest data requirements. Use when someone proposes fine-tuning or a prompt has hit its ceiling.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/llm-cost-latency Skill
14★ repoCut LLM cost and latency with caching, model tiering, prompt diet, batching, and streaming UX. Use when the inference bill or response time needs engineering down.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/llm-eval-design Skill
14★ repoBuild LLM evaluations from real failures with calibrated judges and regression gates that catch quality drift. Use when an LLM feature needs quality measurement or prompts change without anyone knowing what broke.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/llm-guardrails Skill
14★ repoLayer input filtering, output validation, injection defense, and human escalation around LLM features. Use when an LLM system faces untrusted input or its outputs carry real-world consequences.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/llm-observability Skill
14★ repoInstrument LLM applications with request tracing, token accounting, quality signals, and feedback loops. Use when running LLM features in production or debugging why quality or cost moved.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/mcp-server Skill
14★ repoDesign a Model Context Protocol server that exposes tools and data to AI agents safely and legibly. Use when building an MCP server or deciding what to expose to an agent.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/prompt-caching Skill
14★ repoCut LLM cost and latency by caching stable prompt prefixes, structuring prompts so the cache actually hits. Use when the same system prompt, tools, or examples repeat across calls and cost or time-to-first-token matters.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/prompt-engineering Skill
14★ repoBuild prompts that get accurate, reliably-shaped output from any LLM, choosing the right technique for the task. Use when writing, improving, or debugging a prompt.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/rag-pipeline Skill
14★ repoDesign a retrieval-augmented generation pipeline that answers from sources and can be trusted. Use when building or debugging RAG: chunking, embedding, retrieval, context assembly, and grounding.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/retrieval-reranking Skill
14★ repoImprove RAG answer quality by reranking retrieved candidates so the most relevant chunks reach the model. Use when a retrieval system returns roughly-right documents but the best ones are not on top, or answers miss available evidence.
Amey-Thakur/AI-SKILLS/skills/llm-engineering/tool-use-design Skill
14★ repoDesign LLM tools with descriptions that steer, granularity that composes, and error returns the model can act on. Use when building agent tool sets or debugging wrong-tool and wrong-argument failures.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-arch-board Skill
14★ repoRun an architecture board of agents where one proposes a design, several review it independently and blind, and a chair synthesizes a binding decision. Use when a design choice matters enough that one agent's opinion will not do and you want independent scrutiny before committing.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-code-review-loop Skill
14★ repoRun an author agent and a reviewer agent in a loop with a strict finding format, a mandatory verification pass, and a convergence rule that ends it. Use when you want agent-to-agent code review that improves the diff instead of spinning forever on style or re-flagging fixed issues.
Agent competitive analysis team
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-competitive-analysis-team Skill
14★ repoRun competitive analysis as agents that tear down assigned competitors on one template, enforce sourcing rules, and synthesize implications for your product. Use when you want a market landscape built by a coordinated agent team rather than one agent skimming marketing sites.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-context-isolation Skill
14★ repoGive each agent in a system only the context it needs, so failures stay contained and context stays clean. Use when designing a multi-agent system and deciding what each agent sees and shares.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-data-team Skill
14★ repoRun a data team as agents that build the pipeline, gate on quality checks, run the analysis, and independently audit every headline metric. Use when you want a number produced by a coordinated agent team rather than one agent's unverified query.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-design-review-panel Skill
14★ repoConvene several reviewer agents with fixed distinct lenses, correctness, security, cost, and simplicity, then synthesize their verdicts into one. Use when a single review agent keeps missing whole classes of problems because it cannot hold every concern at once on a design or plan.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-docs-guild Skill
14★ repoRun a team of documentation agents that finds the gaps, drafts the pages, gets them reviewed against the code, and sweeps for staleness on a schedule. Use when a codebase has outrun its docs and you need both new coverage and a way to stop pages from rotting.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-growth-team Skill
14★ repoRun a team of growth agents that designs an experiment, builds the variant, analyzes the result, and passes an ethics gate before anything ships. Use when you want product changes tested rigorously instead of shipped on a hunch, with a guardrail against manipulative tactics.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-handoff-protocol Skill
14★ repoDesign each handoff between two agents as an explicit artifact contract with a context budget and a rule for what must survive the crossing. Use when work passes from one agent to the next and the receiver keeps losing constraints, re-deriving decisions, or drowning in raw transcript.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-hiring-panel Skill
14★ repoSimulate an interview panel as agents that design questions, score independently on anchored rubrics, and reconcile in a debrief. Use when you want to pressure-test a hiring loop, calibrate rubrics, or dry-run questions, not to score a real candidate.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-incident-response-team Skill
14★ repoReplicate a live incident team as agents with a commander, parallel investigators, comms, and a scribe, coordinated on a fixed cadence. Use when you want an outage worked by a coordinated agent team instead of one agent debugging alone.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-migration-crew Skill
14★ repoRun a team of migration agents that inventories the work, transforms each slice in isolation, verifies it, and merges under strict discipline. Use when a large mechanical change like a framework bump, an API rename, or a schema move spans many files and one agent would lose the thread or break main.
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-oncall-triage Skill
14★ repoRun alert triage as agents that dedup the storm, rate severity by user impact, match a runbook, and draw a hard human-escalation line. Use when you want incoming alerts sorted and enriched by an agent team before they reach the on-call engineer.
Agent orchestration antipatterns
Amey-Thakur/AI-SKILLS/skills/multi-agent-teams/agent-orchestration-antipatterns Skill
14★ repoGuard a multi-agent team against the structural failures single agents never hit: context lost across handoffs, false agreement, and runaway cost. Use when a team costs more than one agent or trusts its own output, and you need to find out why.