Best Claude skills for AI engineering

Pack1.7k20kProduct management

thinking-jobs-to-be-done

Deciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumstance, then rank by outcome and competing workarounds.

thinking-kepner-tregoe

Use when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/want weighting and adverse-consequence comparison.

thinking-model-combination

When one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conflict rule.

thinking-opportunity-cost

Before committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.

thinking-pre-mortem

Before committing to a plan or launch, assume it already failed and reason backward through concrete causes — convert failure paths into mitigations, gates, and stop checks.

thinking-probabilistic

Use when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into order-of-magnitude…

thinking-red-team

For authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified…

Pack1.7k20kSecurity

thinking-scientific-method

When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.

Pack1.7k20kScience

thinking-systems

When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.

thinking-thought-experiment

When a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate one variable, fix conditions, trace the mechanistic chain, and bound what the result implies.

Pack1.7k20kScience

thinking-triz

When two design requirements seem mutually exclusive, name the contradiction, separate conflicting states, then invent a concrete no-compromise resolution.

thinking-bounded-rationality

Use when search or investigation could run forever. Set an explicit good-enough threshold first, then stop at the first option that clears it.

thinking-circle-of-competence

Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.

thinking-cynefin

When the right response mode is unclear, classify the cause-effect domain first; decompose disorder.

thinking-first-principles

When a constraint is treated as fixed, separate physics from convention, keep only independently supported primitives, and rebuild the simplest solution that satisfies real constraints.

thinking-lindy-effect

Use when longevity of a non-perishable option matters. Treat survival duration as a remaining-life prior, then check domain drift before favoring the proven.

thinking-map-territory

When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.

thinking-margin-of-safety

When provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.

thinking-ooda

Use under time pressure when the situation is still changing and you must act before certainty — cycle Observe→Orient→Decide→Act on ~70% confidence, then re-observe.

thinking-reversibility

Before heavy deliberation, classify the decision as cheap or costly to undo; decide two-way doors fast and stage one-way doors to preserve options.

thinking-second-order

When a change has effects past the immediate fix—incentives, scale, feedback—trace consequence chains with timing and probability before committing.

thinking-socratic

When a request is vague, assumption-laden, or "obvious," ask the few load-bearing questions that expose hidden requirements before building or committing.

thinking-steel-manning

Before rejecting a proposal or reflexively agreeing, build the strongest faithful opposing case, state agreement conditions, then update or reaffirm.

thinking-theory-of-constraints

When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.

thinking-via-negativa

Use when the reflex is to add a feature, layer, or process. Prefer removing harmful or nonessential elements first, with an irreversibility guard before deletion.

Pack1.9k159AI engineering

BagelHole

DevOps Security Agent Skills

BagelHole

llm-cost-optimization

Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies. Track spend by team and model, set budgets…

Pack1.2k62kDevOps

benchflow-ai

Skillsbench

benchflow-ai

modal-gpu

Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU selection, data downloading…

BagelHole

DevOps Security Agent Skills

BagelHole

model-registry-governance

Establish model registry standards, governance controls, metadata schemas, approvals, and lifecycle policies for enterprise AI deployments.

Pack1.2k62kDevOps

yushui2022

MathModel Skill

paper-micro-unit-generator

按修复队列重写反复不通过的论文章节，或按明确要求生成旧版与演练草稿脚手架。当章节连续审计失败需要局部重写、或用户明确要求快速草稿而非正式论文时使用。

Pack458350Research

BagelHole

DevOps Security Agent Skills

BagelHole

rag-observability-evals

Monitor and evaluate RAG systems with retrieval quality metrics, groundedness checks, hallucination detection, and continuous regression testing.

Pack1.2k62kDevOps

chubbyguan

Chubbyskills

chubbyguan

douyin-transcribe

抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。支持短链接和完整链接；优先无 cookie 直采，被风控时回退 yt-dlp + 浏览器 cookie（无需登录）。

Pack1.3k461Video

yushui2022

MathModel Skill

paper-workflow-orchestrator

编排完整的数学建模工作流，从赛题与附件出发依次完成输入预检、题意分析、模型路线、数据与图表、代码与真实运行、证据门禁、正式写作与 Word/PDF 检查。当用户要做完整篇数学建模论文、需要从零跑通或从中断处续跑整个流程时使用。

Pack458350Research

yushui2022

MathModel Skill

problem-doc-model-selector

解析赛题 PDF 或 Word 或题面文本，抽取每一问的任务、数据条件与约束，并复核公式、图片与分问标题的提取完整性。当用户提供赛题文档、需要先明确题意与分问、或题面提取结果待人工复核时使用。

Pack458350AI engineering

yushui2022

MathModel Skill