uygnoey
- 248 skills
- 0 followers
- 8 hours ago last updated
- ▌ Connector Observability · uygnoeyMonitor, debug, and improve a published Claude connector using directory observability signals like adoption, error rates, and latency.
- ▌ Commerce Agent Latency And Cost · uygnoey bundleMake a commerce agent fast and affordable by attacking task-completion latency, perceived latency, and prompt-caching hit rate separately. Covers the three latency levers (fewer turns, faster tools, faster tokens), pre-loading context, parallel tool use, eager dispatch, progressive streaming and progress lines, the three-segment cache layout that reaches 90-99% hit rates, and how to sweep models and effort levels against quality, latency and per-task cost. Use when an agent feels slow, when per-task cost is too high, or when choosing a model and configuration.
- ▌ Finding Your Unknowns · uygnoey bundleSurface what you did not know you needed to say before, during, and after an implementation. Use when starting work in an unfamiliar codebase or domain, when writing a plan or spec, when you want to find architectural decision points before any code is edited, when a change deviated from its plan, or when handing a finished change to reviewers. Provides a blind spot pass, brainstorm and prototype loops, one-question-at-a-time interviews, reference-code pointers, decision-point implementation plans, running implementation notes, shareable pitches and explainers, and self-assessment quizzes.
- ▌ Agentic Coding Adoption Playbook 2 · uygnoey bundlePosition the six benefits of transitioning to agentic coding (timeline acceleration, onboarding compression, autonomous problem solving, scaling without linear headcount growth, systematic code quality, democratized access) and pair each with a concrete starter task. Use when building a business case for Claude Code, choosing which benefit to lead with for a specific audience, or onboarding a team that needs evidence before delegating real work.
- ▌ Domain Partnership Benchmarking · uygnoey bundleCreate a domain-expert partnership plan to benchmark and improve model performance on specialized agentic tasks.
- ▌ Marketing Workflow Automation Playbook · uygnoey bundleBuild lightweight Claude Code workflows that remove repetitive marketing busywork—generating creative variations (e.g., via Figma plugins) and producing upload-ready ad copy (e.g., RSA headlines) with Skills for brand/accuracy/best practices.
- ▌ Token Efficient Sessions · uygnoey bundleGet more out of each Claude Code session by controlling what enters the context, how long it stays there, and what breaks the prompt cache. Use when sessions feel expensive, when a long conversation is dragging unrelated files into every turn, when deciding between /clear, /compact, and /rewind, when choosing model and effort, when tool output or MCP definitions are crowding the context, or when working out whether a job belongs in a subagent. Efficiency here means spending tokens on the task you actually asked for, not spending fewer tokens overall.
- ▌ Memory Curation · uygnoey bundleAudit, correct, and scope what Claude keeps in memory across chat and Cowork. Use when the user asks what Claude remembers about them, wants to fix or delete a saved memory topic, keeps re-explaining the same context between chat and Cowork, is deciding whether to turn on "include sensitive topics in memory", or needs to know which categories are never stored and who controls availability on Team and Enterprise plans.
- ▌ Self Improving Skill Loops · uygnoey bundleBuild agent skills that improve themselves from human feedback, using a base (inner) skill that does the work and an improver (outer) skill that runs on a schedule, reads accumulated feedback, and proposes small reviewable edits to the base skill. Use when an agent's output is roughly right but noisy, when feedback keeps getting lost at the end of a session, when hand-editing prompts or AGENTS.md no longer scales, or when deciding how many improver loops to run and how to guard against bad feedback.
- ▌
- ▌ Cost Aware Model Selection · uygnoey bundleDecide which model a workload should run on, and which cost controls to apply, using cost-per-outcome rather than token count as the metric. Use when rolling a product out to an organization, setting or enforcing a spend budget, reconciling spend against invoices, choosing between a frontier and a smaller model for a workload, or reducing the cost of a production API workload without losing quality where it matters. Covers the model family, enterprise admin controls (access gating, model controls, hard spend caps), usage observation tools, and API-side levers (prompt caching, batch processing, the effort parameter, and the advisor strategy).
- ▌ Financial Services Agent Deployment · uygnoeyGuides building and deploying AI agents in financial services with emphasis on integration, regulation, and real-time risk controls. Trigger when the user asks how to safely operationalize agents for banking, insurance, wealth management, fraud, compliance, or financial operations.
- ▌ Cowork Getting Started 2 · uygnoey bundleBest practices, checklists, and reusable prompts for delegating multi-step knowledge work in Claude Cowork to produce deliverables.
- ▌ Self Hosted Coding Environments · uygnoey bundleDecide whether to run agentic coding sessions on self-hosted infrastructure instead of the vendor-hosted default, then size and operate that environment. Use when network isolation, pre-installed internal toolchains, or keeping source and build artifacts on controlled infrastructure are hard requirements; when choosing between fixed and on-demand runner capacity; when clarifying the data boundary (what stays local vs. what is sent for inference); or when assigning ongoing ownership of runner images and orchestration to a platform, DevEx, or developer-productivity team.
- ▌ Frontier Model Evaluation · uygnoey bundleEvaluate a new frontier model on your own private repositories instead of trusting public benchmarks, then decide which work to route to it. Use when a new model ships and you need to answer "is this better for us, and where do we actually use it" — building a private eval set, scoring quality/cost/speed on separate leaderboards, comparing head-to-head against your current default, measuring steps-to-solution and code that runs but is wrong, and setting a deployment posture around the model (harness-level safety, security testing against your own products, data-retention tradeoffs). Based on how JetBrains evaluated and deployed Claude Fable 5.
- ▌ AI Fluency Curriculum Design · uygnoey bundleDesign AI training that increases learner agency and survives model releases. Use when writing internal AI enablement, an onboarding module, or a course and the draft keeps turning into a feature tour; when a program teaches tool operation but not which work should be delegated; when "safe use" has been reduced to prompt hygiene and omits task selection, skill preservation, and disclosure; or when you need an onboarding plus continuing-education structure rather than a one-time session.
- ▌ Skill Authoring Guide · uygnoey bundleWrite and refine Claude Skills (SKILL.md): naming, description writing for reliable triggering, instruction structure, testing/validation, and context-size management via companion files. Use when creating or reviewing a Skill, or when debugging why a Skill triggers incorrectly.
- ▌ Context Window Management · uygnoey bundleDecision framework for managing Claude Code sessions and the 1M-token context window. Covers when to continue, rewind, /clear, /compact, or delegate to a subagent, plus how to avoid bad autocompacts and steer compaction with hints.
- ▌ Bedrock Distillation And Latency Optimization Guide · uygnoey bundleDecision checklist for using latency-optimized Claude 3.5 Haiku on AWS Trainium2 and Amazon Bedrock Model Distillation for Claude 3 Haiku, based on the official announcement.
- ▌ Enterprise AI Agent Deployment Framework · uygnoeyA structured framework for planning and rolling out agentic AI across an enterprise, emphasizing workforce enablement, process redesign with human oversight, and scaling into durable product capabilities.
- ▌ Financial Services Rollout Playbook · uygnoey bundlePlan a Claude rollout for a financial services firm using the product matrix, the 10 pre-built finance agent templates, and the foundation/pilot/scale adoption phases described in Anthropic's "Deploying Claude across financial services" guide. Use when an AI leader needs to decide which Claude product belongs in which workflow, where to place pre-built finance agent templates, and how to sequence a phased deployment that survives review by risk, compliance, and IT.
- ▌ Clue Style Detection Platform Playbook · uygnoey bundlePlan a Claude-powered detection and response platform in the style of CLUE (Claude Looks Up Evidence), the internal platform Anthropic's Detection Platform Engineering team built with Claude Code. Use when a defensive security team is deciding whether to wrap their SIEM and internal systems with a triage surface and a natural-language investigation surface, where to set the deterministic-vs-agentic boundary, what context sources to plug in via tools, and how to measure impact (false-positive rate, query and tool-call volume, hours saved, coverage of low-confidence signals).
- ▌ Delegating Complex Work In Cowork · uygnoey bundleHand a frontier model a whole job in Claude Cowork instead of prompting it step by step — pick the model and effort level, brainstorm from a bare idea, brief with context rather than rules, delegate the approach/procedure/timing, and review the plan panel while it runs. Use when a Cowork task spans dozens of steps or several days, when a job needs multiple tools and a series of judgment calls, when you are unsure which model or effort setting fits, when a long conversation is burning usage, or when skills and memory files written for an older model may be holding a newer one back.
- ▌ Plan Fit Assessment · uygnoeyAssess whether a user needs higher usage limits and prioritize an upgrade path based on workload and constraints.
- ▌ Agent Skills Overview · uygnoey bundleOverview and adoption checklist for Agent Skills (reusable bundles of instructions, scripts, and resources that Claude loads when relevant).
- ▌ Android App Rollout · uygnoeyChecklist-style guidance for rolling out and communicating availability of the Claude Android app across platforms.
- ▌ Project Memory Practices · uygnoeyGuidelines for using Claude app memory (including project-scoped memory and incognito chat) to maintain context safely and intentionally across ongoing work.
- ▌ Automated Pr Review · uygnoey bundleDispatch a multi-pass, high-signal pull request review and deliver a consolidated overview plus actionable inline findings.
- ▌ Auto Mode Permissions · uygnoeyGuides when and how to use Claude Code's auto mode for permission handling. Use when deciding between default, auto, and --dangerously-skip-permissions flow, enabling auto mode for long multi-file edits, responding to repeated classifier blocks, or (as an admin) turning auto mode off via managed settings.
- ▌ Artifacts Ga Workflows · uygnoeyWorkflow patterns for using Claude Artifacts (GA) to iteratively build and share code, documents, and visualizations across Free/Pro/Team and mobile.
- ▌ Million Context Ga · uygnoeyGuidance for using Claude models with a generally available 1M-token context window (Opus 4.6 and Sonnet 4.6), including practical considerations for very large inputs.
- ▌ Analysis Tool Adoption · uygnoeyGuidance for enabling and using the Claude.ai analysis tool when you need precise calculations or data analysis.
- ▌ Research Workspace Briefing · uygnoeyTurn a question into a citation-backed briefing by combining web research with Google Workspace context (Gmail, Calendar, Docs).
- ▌ Deep Review · uygnoeyComprehensive code review that runs security, performance, and style reviews in parallel as subagents and synthesizes findings. Use when reviewing staged changes before a commit or PR.
- ▌ Code Plugin Basics · uygnoey bundlePackage and share Claude Code customizations using plugins, with a focus on when to use plugins and how to install them from Claude Code.
- ▌ Reduce Token Usage · uygnoey bundleCut cost, latency, and rate-limit pressure in an API application by applying prompt caching, cache-aware rate limits, and token-efficient tool use. Use when an application repeatedly sends long mostly-static context such as documents, codebase excerpts, or policies; when input-token rate limits are the throughput bottleneck; or when tool-calling workflows emit large outputs.
- ▌ Web Search Use Case Playbook · uygnoey bundleApply Claude's web search feature (announced March 20, 2025, made globally available May 27, 2025) effectively. Helps users decide when web search is the right tool, enable it correctly with Claude 3.7 Sonnet, get cited responses, and reuse the four use cases the post calls out — sales, finance, research, and shopping.
- ▌ Skills Stack Explainer · uygnoey bundleDecide when to use Skills vs prompts, Projects, MCP, and subagents, and combine them into a coherent workflow.
- ▌ Oncall First Responder · uygnoey bundleStand up and operate an agentic on-call first responder that triages CI/CD alerts, opens every incident with an evidence-grounded situation report, and accumulates its own investigation memory. Use when an on-call rotation is dominated by alert triage and after-hours interruptions, when incident knowledge lives only in people's heads, or when merge volume has outgrown a human-paced CI process.
- ▌ Manage API Console Workspaces · uygnoeyCreate and operate Anthropic API Console Workspaces to organize deployments, enforce workspace-level spend and rate limits, and manage access control.
- ▌ Long Context Capability Brief · uygnoeySummarize what a 1M-token context window enables and help decide when to use long context (codebases, document synthesis, long-running agent workflows), based on the Claude Sonnet 4 announcement.
- ▌ Slack Slack Integration · uygnoeyA reusable workflow for using Claude in Slack (and Slack as a connector) to draft replies, summarize threads, and pull relevant workspace context with permission-aware access.
- ▌ Using Subagents · uygnoeyDelegates research, parallel edits, or fresh-eyes reviews to subagents (separate AI instances with isolated context) in Claude Code. Use when a task requires reading 10+ files, has 3+ independent subtasks, needs a second opinion before commit, or a complex pipeline like design-then-implement-then-test. Covers four invocation methods (conversational, custom agent file, project policy, slash command skill), four practical patterns, and when NOT to use subagents.
- ▌ Loops Playbook · uygnoey bundleChoose the simplest loop primitive (turn-based, /goal, /loop, /schedule) and make success criteria explicit and verifiable.
- ▌ Prompt Template Bootstrap · uygnoey bundleUse Anthropic Console's prompt generator to bootstrap a production-ready prompt template from a short task description, then know what prompt-engineering techniques the output already carries (role setting, chain-of-thought scratchpad, XML tags, handlebars variables) and how to edit, version, and evaluate the result.
- ▌ Code Hooks Playbook · uygnoey bundleConfigure and maintain Claude Code hooks: choosing lifecycle events, writing matchers, selecting hook types (command vs prompt), and applying safety/operational best practices. Use when a user wants to automate Claude Code workflows via hooks or needs help authoring or reviewing hook JSON and companion scripts.
- ▌ Request Artifacts · uygnoey bundleRequest and iteratively publish shareable Claude Code artifacts (live, interactive pages) built from full session context.
- ▌ AI Native Sdlc · uygnoey bundleRedesign a software development lifecycle around agentic coding — six stages (Plan, Design, Build, Test, Deploy, Maintain) that each end by committing a version-controlled artifact the next stage reads. Use when agentic coding has made the build phase fast but planning, review, testing, and deployment still run at human speed; when review queues or security sign-off have become the bottleneck; when deciding which SDLC stage to transform first and in what order; when encoding policy as skills, hooks, and managed settings instead of enforcing it in review meetings; or when closing the loop so production signals write the next intent.md without a person in the invocation path. Covers the intent.md / spec.md / plan.md artifact chain, plan mode and auto mode, parallel worktree sessions and subagents, feedback loops and continuous evals, dual-direction PR review, approval-gate hooks, and per-stage leading and lagging indicators.