agent-skills

In the author's own words, from each skill's SKILL.md.

• agent-architecture-patterns

  Choose the right architecture for an LLM agent or multi-agent system. Use when the user is designing, comparing, or debugging agentic workflows and mentions ReAct, Reflexion, Plan-and-Execute, Router, Supervisor, Hierarchical, multi-agent, tool-use loop, agent graph, LangGraph, AutoGen, CrewAI, or asks "which agent pattern should I use" / "how should this agent be structured".

  skills/agent-architecture-patterns/SKILL.md on GitHub (opens in a new tab)

• agent-cost-modeling

  Model the cost of an LLM agent before it ships, and after. Use when the user is planning a deployment, comparing patterns, choosing a model tier, or justifying a budget and mentions tokens per task, cost per task, unit economics, cost ceiling, cache hit rate, ReAct cost, multi-agent cost, or asks "how much will this cost?" / "is this economical at scale?".

  skills/agent-cost-modeling/SKILL.md on GitHub (opens in a new tab)

• agent-evaluation-harness

  Design an evaluation harness for an LLM agent before shipping it. Use when the user is building or rewriting an agent, deciding ship/no-ship, debugging regressions, or mentions golden sets, eval suites, regression tests, trace-level evals, LLM-as-judge, scoring rubrics, or asks "how do I test this agent?" / "how do I know if my agent got better?".

  skills/agent-evaluation-harness/SKILL.md on GitHub (opens in a new tab)

• agent-observability

  Instrument an LLM agent so failures are diagnosable, traces are replayable, and evals can run against production data. Use when the user is moving an agent past prototype and mentions tracing, spans, OpenTelemetry, LangSmith, Langfuse, Arize, OpenLLMetry, structured logs, GenAI semantic conventions, or asks "how do I debug this agent in production?" / "what should I log?".

  skills/agent-observability/SKILL.md on GitHub (opens in a new tab)

• context-window-hygiene

  Manage what enters and stays in the context window — pruning, compaction, summary fidelity, ordering — so the agent stays coherent on long runs without inflating cost. Use when the user is hitting context limits, running long agentic loops, paying for full-history replays, or asks "how do I keep context manageable?" / "the agent forgets things after N turns".

  skills/context-window-hygiene/SKILL.md on GitHub (opens in a new tab)

• guardrails-and-safety

  Design guardrails for an LLM agent that handles user input, calls real tools, or operates in a regulated domain. Use when the user is building a user-facing agent and mentions guardrails, jailbreaks, prompt injection, content moderation, PII redaction, output validation, red-teaming, safety filters, or asks "how do I keep this agent from doing X?" / "how do I make this production-safe?".

  skills/guardrails-and-safety/SKILL.md on GitHub (opens in a new tab)

• human-in-the-loop

  Design where, when, and how a human gates, reviews, or rescues an LLM agent — without turning the agent into a button labelled "approve". Use when the user is building an agent that takes irreversible actions or operates in regulated workflows and mentions human-in-the-loop, HITL, approval gate, escalation, review queue, oversight, or asks "when should a human approve this?" / "how do I add revie…

  skills/human-in-the-loop/SKILL.md on GitHub (opens in a new tab)

• latency-budgeting

  Budget and engineer latency for an LLM agent — TTFT, tokens-per-second, tool round-trips, parallelism, streaming. Use when the user is building a user-facing or real-time agent and mentions latency, p50, p95, p99, TTFT, streaming, throughput, time-to-first-token, slow agent, or asks "why is my agent slow?" / "how do I hit a 2-second latency target?".

  skills/latency-budgeting/SKILL.md on GitHub (opens in a new tab)

• llm-as-judge

  Design and validate LLM-as-judge scoring — pairwise vs pointwise, bias correction, anchor calibration, and the cases where a judge is the wrong tool. Use when the user is building an eval, scoring open-ended outputs, or comparing model versions and mentions LLM-as-judge, model grader, pairwise comparison, position bias, length bias, judge calibration, meta-eval, or asks "how do I score open-ended…

  skills/llm-as-judge/SKILL.md on GitHub (opens in a new tab)

• memory-design

  Design memory for an LLM agent — what to keep, where to keep it, and when memory hurts more than it helps. Use when the user is adding memory to an agent and mentions short-term memory, long-term memory, episodic, semantic, conversation history, summary memory, vector memory, memory store, mem0, Letta, MemGPT, or asks "should this agent remember?" / "why is the agent recalling the wrong thing?".

  skills/memory-design/SKILL.md on GitHub (opens in a new tab)

• model-routing

  Pick the right model per call, not per project — route Opus/Sonnet/Haiku, GPT-5/4o/mini, Gemini Pro/Flash by task, and cut cost without losing quality. Use when the user is choosing model tiers, building a router, or debating Opus-only vs mixed-tier deployments and mentions model selection, model router, cascade, fallback, cheap-first, draft-then-verify, or asks "which model should I use?" / "do…

  skills/model-routing/SKILL.md on GitHub (opens in a new tab)

• multi-agent-orchestration

  Decide when to split work across multiple agents vs one agent with tools, and design the handoffs when you do. Use when the user is sketching a multi-agent system or debugging one, and mentions handoff, delegation, supervisor, swarm, crew, sub-agent, agent-to-agent, A2A, manager-worker, team of agents, or asks "should I split this into multiple agents?" / "why do my agents talk forever and never…

  skills/multi-agent-orchestration/SKILL.md on GitHub (opens in a new tab)

• prompt-caching

  Use prompt caching correctly across Anthropic, OpenAI, Bedrock, and Gemini to cut cost and latency on hot paths. Use when the user is building a production LLM app and mentions prompt caching, cache hits, cache key, cache TTL, ephemeral cache, system-prompt caching, or asks "why is my cache hit rate low?" / "should I cache this?".

  skills/prompt-caching/SKILL.md on GitHub (opens in a new tab)

• prompt-injection-defense

  Defend an LLM agent against prompt injection — direct, indirect, tool-result, and document-borne. Use when the user is building an agent that reads untrusted content (web pages, emails, documents, tool outputs) or exposes user-provided text to a downstream agent, and mentions prompt injection, indirect injection, jailbreak via document, tool-result injection, untrusted input, instruction override…

  skills/prompt-injection-defense/SKILL.md on GitHub (opens in a new tab)

• rag-vs-context-engineering

  Decide between RAG, long-context, structured tool retrieval, and prompt-only approaches for grounding an LLM in private or fresh data. Use when the user is designing a knowledge-grounded agent or chatbot and mentions RAG, vector search, embeddings, retrieval, chunking, long context, context window, tool retrieval, hybrid search, rerank, or asks "do I need RAG?" / "should I just use a big context…

  skills/rag-vs-context-engineering/SKILL.md on GitHub (opens in a new tab)

• structured-output-reliability

  Get reliable structured output (JSON, typed objects) out of an LLM without regex repair, retry loops, or silent corruption. Use when the user is parsing model output, fighting malformed JSON, comparing JSON mode vs function calling vs structured outputs, or asks "why does the model keep breaking my schema?" / "how do I force valid JSON?".

  skills/structured-output-reliability/SKILL.md on GitHub (opens in a new tab)

• tool-failure-handling

  Design retry, idempotency, timeout, and recovery behaviour for an agent's tool calls — not the schema (that's a separate skill), but the runtime semantics. Use when the user is building or debugging an agent's tool loop and mentions retries, idempotency keys, timeouts, exponential backoff, compensation, partial failure, tool unavailable, 429, 503, flaky tool, or asks "how should the agent retry?"…

  skills/tool-failure-handling/SKILL.md on GitHub (opens in a new tab)

• tool-use-schema-design

  Design tool schemas (function-calling definitions) that LLMs can use reliably. Use when the user is defining tools for Claude, GPT, Gemini, or any function-calling agent and mentions tool definitions, function calling, JSON schema, tool descriptions, parameters, structured outputs, MCP tools, or asks "why is the model calling my tool wrong?" / "how should I design this tool?".

  skills/tool-use-schema-design/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages 97.3k stars · 13 skills
• Wazaby tw93 🥷 Engineering habits you already know, turned into skills AI assistants like Claude Code, Codex and Cursor can run. 7.3k stars · 8 skills
• geo-sleuthby Oldcircle An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and sho… 3k stars · 1 skill
• agent-skills-platformby FrancyJGLisboa Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine… 2.4k stars · 6 skills
• Pretty-mermaid-skillsby imxv AI Agent Skill to generate and render beautiful Mermaid diagrams as SVG or terminal ASCII — 15 themes, 6 diagram types, batch CLI, no brows… 1.5k stars · 1 skill
• claude-workflow-v2by CloudAI-X Universal Claude Code workflow plugin with agents, skills, hooks, and commands 1.4k stars · 14 skills