This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches. NOT for evaluating agent quality or building evaluation rubrics (use agent-evaluation), NOT for multi-agent coordination or agent handoffs (use multi-agent-patterns).

> A plugin that ships without evals ships with hope instead of evidence. A plugin that ships without validation ships with structural debt. This workflow forces both before you can call it done.

Good writing is rewriting. First draft: get the thought on the page. Second draft: make the thought disappear behind the sentence. This skill is the second draft.

Expert FinOps guidance covering cloud, AI, SaaS, and adjacent technology spend. Includes AI cost management, GenAI capacity planning, AI-powered FinOps automation, Anthropic billing, AWS (EC2, Bedrock, Savings Plans, CUR, commitment strategy), Azure (reservations, Savings Plans, AHB, OpenAI PTUs, portfolio liquidity), GCP (Vertex AI, Compute Engine, BigQuery), Kubernetes and container FinOps (OpenCost, Kubecost), serverless FinOps (Lambda, Functions, Cloud Run), data platforms (Kafka/MSK, Elasticsearch/OpenSearch, Redis/Valkey), multi-cloud normalization (FOCUS specification), tagging governance, SaaS management (SAM, licence optimisation, SMPs, shadow IT), AI coding tools (Cursor, Claude Code, Copilot, Windsurf, Codex), ITAM, Databricks, Snowflake, OCI, and GreenOps. Use for any query about technology cost, commitment portfolio management, rightsizing, cost allocation, SaaS sprawl, AI dev tool spend, container cost attribution, serverless optimization, multi-cloud strategy, or connecting spend to business value. Built by OptimNow and Viktor Bezdek.

Establish and enforce uniform naming conventions, taxonomy standards, style guides, and content reuse patterns across a project. Use when the user asks to audit for consistency, standardize naming, create a style guide, align terminology across docs, eliminate drift, or define reuse patterns across content or code. NOT for formal knowledge graphs or semantic ontologies (use ontology-design). NOT for CMS content types or editorial workflows (use content-modelling). NOT for language-specific code conventions (use typescript-development or python-development).

Design structured content models for reusable, multi-channel content.

> Content platforms fail when teams skip the layers. You cannot design navigation for a content schema you haven't defined. You cannot enforce consistency on terminology that isn't named. You cannot produce examples for a structure that doesn't exist yet. This workflow enforces the order.

When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is aggressive compression to minimize tokens per request. The correct optimization target is tokens per task: total tokens consumed to complete a task, including re-fetching cos

Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and designing resilient systems. Context degradation is not a binary state but a continuum of performance degradation that manifests in several dist

Context is the complete state available to a language model at inference time. It includes everything the model can attend to when generating responses: system instructions, tool definitions, retrieved documents, message history, and tool outputs. Understanding context fundamentals is prerequisite t

Context optimization extends the effective capacity of limited context windows through strategic compression, masking, caching, and partitioning. The goal is not to magically increase context windows but to make better use of available capacity. Effective optimization can double or triple effective

This skill enables sophisticated creative and strategic thinking to help users find optimal, unconventional, and high-leverage solutions to complex problems.

Stress-test, critique, and challenge existing ideas through pattern recognition, bias detection, Bayesian reasoning, blind-spot exposure, and red-flag identification. Use when the user asks to stress-test a plan, challenge assumptions, find flaws, identify risks in an idea, expose hidden biases, audit a proposal for blind spots, or "poke holes in this". NOT for generating new ideas or solutions (use creative-problem-solving). NOT for structured risk registers or mitigation plans (use risk-management).

Comprehensive guide for Docker containerization covering core concepts, multi-stage builds, Docker Compose orchestration, development environment setup, and advanced patterns for isolated development workflows.

Decide what and when to write down, and produce Architecture Decision Records (ADRs), one-pagers, runbooks, and decision logs. Use when the user asks whether something should be documented, wants to write an ADR, needs a runbook or operational playbook, wants to keep a decision log, or is trying to decide between a one-pager and an RFC. NOT for auto-generating docs from code (use documentation-generator). NOT for end-user tutorials or how-tos (use example-design). NOT for docs-site information architecture (use navigation-design). NOT for cross-team alignment via RFCs (use stakeholder-alignment).

Generate comprehensive documentation for a codebase by reading the repository and producing READMEs, API docs, architecture docs, and technical references. Use when the user asks to "document this repo", "generate docs", "write a README", "create API documentation", "document this codebase", "write architecture docs", or "produce technical references" for an existing project. NOT for UX copy, button labels, or interface microcopy (use ux-writing). NOT for pedagogical code examples or tutorials (use example-design). NOT for inline code comments.

Identify and document boundary conditions, corner cases, error scenarios, and validation requirements that implementations must handle. Use when the user asks to find edge cases, identify corner cases, specify validation rules, enumerate error scenarios, harden a function against bad inputs, or think through what can go wrong at the boundaries of a system. NOT for writing the actual tests (use testing-framework or test-driven-development). NOT for structured risk registers around project-level risks (use risk-management). NOT for security vulnerability scanning (use code-review).

> The most dangerous state for an agent is "it mostly works." Teams stop measuring, stop improving, and slowly accumulate failure modes that nobody notices until a customer does. This workflow breaks that plateau by forcing a baseline measurement before any changes and a comparison measurement after

Design pedagogically effective code examples, tutorials, and runnable samples using progressive complexity and deliberate scaffolding. Use when the user asks to write a code example that teaches a concept, design a quickstart tutorial, create sample code for a library or API, build a runnable demo, or structure examples from simple to advanced. NOT for generating full repo documentation or READMEs (use documentation-generator). NOT for writing examples inside a skill file (use skill-foundry).