uygnoey
- 294 skills
- 0 followers
- 4 repo stars
- last week last updated
- ▌ Event Build · uygnoey bundleSet up an event, webinar, or integrated campaign end to end across the CRM, the marketing automation platform, the event platform, and email — including the integrations between them, which are rarely complete out of the box. Use when a build request has been routed from the intake queue. Posts two Slack updates (on pickup, and when the landing page is ready for review), then hands off to a fresh audit agent rather than marking its own work complete.
- ▌ Discovery Call Scorecard · uygnoey bundleScore a discovery call against the team's playbook and return a scorecard — top three things done well, top three areas to improve, an explicit pass or fail against the criteria, and the single highest-leverage thing to practice next. Use when call coaching does not scale past the calls a manager can personally listen to; when feedback needs to be specific to what was said rather than generic; or when a team wants a consistent, playbook-anchored standard applied to every discovery conversation.
- ▌ Finance Narrative Integrity Layer · uygnoey bundleKeep finance narratives (board decks, monthly reviews) coherent as numbers refresh by using Claude as an integrity layer for reconciliation, consistency checks, and first-pass variance commentary.
- ▌ Account Prospecting Sweep · uygnoey bundleRun an overnight prospecting sweep across a rep's whole book so each morning starts with a brief, a score, and an outbound play per account. Use when outbound coverage is capped by manual research across a hundred-plus accounts; when account state lives scattered across CRM, sales tools, call recordings, and a data warehouse; when research must be validated against curated outbound guidance and ICP criteria; when a memory file is needed to stop duplicate outreach; or when handling one-off book-wide analysis requests like undiscovered usage sweeps and event invite lists.
- ▌ Agent First Product Rebuild · uygnoey bundleRebuild a product from sequential, separate skills into a single agent that plans and orchestrates across tools in real time, and test candidate models on the ability that architecture depends on — planning and effective tool use. Use when a product is a collection of one-shot features that users have to sequence themselves, when evaluating whether a model can carry an agent across hundreds of tools, or when deciding what to measure about an AI initiative beyond cost per task.
- ▌ Pipeline Hygiene Proposals · uygnoey bundleKeep a CRM current by reading the team's own guidance on opportunity stages, checking it against what is actually happening in email and call recordings, and proposing each update with the evidence behind it for a rep to approve. Use when pipeline data drifts because updating stages is manual; when a stage change should be justified by evidence rather than memory; when an agent must propose rather than write to the system of record; or when rejected proposals should teach the skill instead of being silently discarded.
- ▌ Enterprise AI Retail Rollout Playbook · uygnoey bundleA practical, executive-friendly rollout playbook for moving from AI pilots to enterprise-wide transformation in retail, based on Anthropic’s retail guide summary.
- ▌ Domain Model Benchmarking · uygnoey bundleDecide whether a new model is worth adopting by running it against a domain-specific benchmark head-to-head with the model it would replace, rather than reading public scores — build tests that replicate the real jobs your users do, expand the benchmark with each release, and separate retrieval quality from synthesis quality when reading the results. Use when a new model ships and someone asks whether to switch, when building an internal eval for a high-accuracy domain, or when a benchmark result jumps and you need to know what actually improved.
- ▌ Document Grounded Analysis · uygnoey bundleRun analysis over large sets of dense, unstructured documents so that every answer is traceable to its source — decompose a plain-language request into per-step questions, answer each one in its own cell, cite it back to the document it came from, and keep the human able to see and steer each step. Use when working through data rooms, credit agreements, public filings, or any pile of proprietary documents where a missed detail is a real cost, and when turning that analysis into first-draft memos or covenant reviews.
- ▌ Visual Ideation Workflow · uygnoey bundleExplore, iterate on, and share visual ideas early — product prototypes, slide decks, landing pages, one-pagers, animations — by treating HTML as an interactive visual medium and directing the aesthetic explicitly. Use when engineering throughput has outrun design, when you need many versions of a flow fast for feedback, when generated visuals keep drifting to a generic look, or when deciding whether work belongs in early ideation or in production code.
- ▌ Report Proofreader · uygnoey bundleCheck that every number in a draft report traces back to a verified source before the report ships. Use on any metrics review, leadership slide, or data-backed narrative assembled from mixed sources — dashboards, a data warehouse, Slack messages, call transcripts. Marks each figure verified, unverified, or mismatched, and never reconciles two disagreeing sources on its own. The post recommends building this skill first, before any other reporting automation.
- ▌ Weekly Metrics Report · uygnoey bundleAssemble a weekly marketing metrics review when the numbers are scattered across a dashboard, a data warehouse, Slack, and call transcripts. Use to run the Sunday-night data hunt, produce metrics tables with suggested headlines, expand a confirmed headline into narrative with supporting detail, generate the leadership slide from the same data, and turn follow-ups into tasks. Also use at the quarter turn, when quarterly plans lead instead of weekly movement. Flags mismatches between sources rather than reconciling them silently.
- ▌ Slack Analytics Agent Deployment · uygnoey bundleDeploy a Slack-based data analytics agent that a whole company can ask ad hoc questions — keep its skill files refreshed like a data model, give it analytical skills beyond table access, wire it into business context, permission its service account deliberately, and instrument every answer so adoption and correctness are measurable.
- ▌ Senior Scope Delegation · uygnoey bundleHand a model the work that was previously reserved for your most senior or most specialized engineers — core changes touching interdependent parts — by briefing the goal and the why rather than every step, front-loading a question round, letting it run unattended, and gating on human review before shipping. Use when a core system change is blocked waiting for a specific engineer to free up, when deciding whether a non-engineer can own a piece of technical work, or when calibrating how much specification a model actually needs.
- ▌ Marketing Ops Dispatcher · uygnoey bundleHourly intake triage for a marketing operations request queue. Reads the intake channel, picks the most urgent request, stamps the ticket so the work is not duplicated, and hands off to the right specialist skill — event build, data import, apply-to-attend, or approval support. Does no setup work itself. Use when requests arrive in a shared channel through an intake form and several specialist workflows exist behind them.
- ▌ App Generation Model Evals · uygnoey bundleEvaluate a new model for an app-generation product by running it across different app types and measuring latency, cost, and build errors, plus stress builds that exercise unusual capabilities — then read the signals that matter for production, such as turns to completion, first-prompt completeness, and whether prompt changes break the cache. Use when a new model ships and someone asks whether to switch the generation engine, when designing an eval suite for a codegen or app-building product, or when an eval passes but production cost or latency regresses anyway.
- ▌ Personalized Weekly Digests · uygnoey bundleBuild and operate a recurring, per-person digest (weekly sales updates, field-marketing briefings, team roll-ups) with Claude Code. Use when a repeating update has to be personalized per recipient from CRM, event, and content data, when a manual Sunday-night briefing needs to become an automated Monday-morning send, or when an existing digest needs to be piloted, corrected through feedback, and scaled to more teams. Covers framing the business problem instead of the technical one, showing the output format by example, wiring real data sources, converting each piece of recipient feedback into an explicit content rule, and surviving schema drift in source spreadsheets.
- ▌ Solo To IOS Shipping Workflow · uygnoey bundleBuild and ship a real app with Claude Code by iterating from a fast prototype to a production-ready iOS release, coordinating specialist subagents and using Claude for engineering + launch tasks.
- ▌ Agent First Product Transformation · uygnoey bundleMove a product or an internal platform from bolted-on AI features to an agent-first design where people and agents work on the same items. Use when AI features shipped, adoption looked fine for a month, and usage has flattened into occasional summarization; when deciding whether to embed agents into an existing workflow or rebuild the workflow around them; when agents live in a chat surface parallel to the real work and context must be pasted in by hand; when pilots stall before production because governance, permissions, and reliability were never designed in; or when you need concrete per-function agent jobs instead of one general assistant.
- ▌ Artifacts Ideation Playbook · uygnoeyTurn a conversational idea into a shareable, interactive artifact by iterating on scope, interactivity, and user flow in short cycles.
- ▌ Project Context Files · uygnoey bundleAuthors and audits CLAUDE.md project-context files that get auto-loaded into every Claude Code conversation. Use when a developer asks how to create a CLAUDE.md, wants to stop re-explaining project structure or conventions each session, needs a team-wide configuration for consistent AI behavior in a repo, or asks to review/clean up an existing CLAUDE.md.
- ▌ Tool Use Ga Integration Playbook · uygnoey bundlePractical checklist for evaluating and integrating Claude tool use (now generally available) into an application, based on the official announcement.
- ▌ API Web Search With Citations · uygnoeyReusable implementation notes derived from the Claude blog post “Introducing web search on the Anthropic API”.
- ▌ Remote MCP Quickstart · uygnoeyHelp a user understand and adopt remote MCP servers in Claude Code, focusing on benefits, security, and low-maintenance setup.
- ▌ Team Plan Updates Summary · uygnoeySummarize the Claude Team plan updates from the referenced post, focusing on seat pricing and included features.
- ▌ Background Task Delegation · uygnoey bundleHand Claude Cowork a job that outlives one sitting — write the delegation brief, schedule it, and set the approval gates — so the work continues while you are away and only the decisions reach you. Use when a task accumulates over days rather than finishing in one session, when work should run overnight or before you arrive, when you will be moving between desk, phone, and web mid-task, or when the output must not ship until you have reviewed it. Built around the pattern of pointing Claude at the folder, thread, or half-finished deck and describing what done looks like.
- ▌ Large Scale Code Migration · uygnoey bundlePlan and execute a large-scale code migration — porting a codebase to a new language, framework, or architecture — using parallel agent loops, a written rulebook, a dependency map, adversarial review, and a mechanical verification harness. Use when a migration is too large to do by hand, when a port or rewrite keeps stalling, when deciding how to parallelize translation work across agents, or when a migration is producing plausible-looking code that drifts from the original's behavior. Covers the six-step process (rulebook and gap inventory, stress test, translate, compile, run, match behavior), how to design resumable work queues, when to fix the rulebook instead of the file, and how to build a judge that answers for both codebases.
- ▌ Prompt Caching Design Patterns · uygnoey bundleDecide when prompt caching helps, structure prompts so the cacheable prefix and dynamic suffix are cleanly separated, estimate cost and latency wins from the benchmarks reported in Anthropic's launch post, and pick the right Claude model among those that support caching.
- ▌ Message Batches Job Design · uygnoeyA reusable checklist for deciding when and how to use the Anthropic Message Batches API for asynchronous, high-volume processing at reduced cost.
- ▌ Connected Tools Research Playbook · uygnoey bundleUse Claude's Integrations and advanced Research together to pull context from your work apps and produce comprehensive cited reports. Apply when deciding which third-party app to connect via remote MCP servers, when planning multi-source investigations that span the web, Google Workspace, and connected services, or when standardizing how a team uses Integrations + Research instead of building bespoke automation.
- ▌ Create And Edit Deliverable Files · uygnoeyCreate and iteratively refine ready-to-use deliverable files (spreadsheets, documents, slide decks, PDFs) from user instructions and uploaded source materials.
- ▌ Context Editing Memory Tool · uygnoey bundleApply practical rules for what to keep in an agent’s context vs what to persist to memory when building long-running workflows on the Claude Developer Platform.
- ▌ Advisor Strategy Playbook · uygnoey bundlePair a lower-cost executor model with a higher-capability advisor model to get targeted guidance for hard decisions without paying frontier-model cost for every token.
- ▌
- ▌ Thinking Partner Workflow · uygnoeyUse Claude as an iterative thinking partner by combining memory, voice, and artifact creation to move from ideas to finished work.
- ▌ Agent Tool Design Playbook · uygnoeyPractical heuristics from the Claude Code team for designing, iterating, and pruning agent tools by thinking from the model’s perspective (“seeing like an agent”), with an emphasis on progressive disclosure.
- ▌ Desktop Browser Routing · uygnoey bundleChoose between the browser built into Cowork on the desktop app and Claude in Chrome for a given web task, and work safely in either one. Use when a web task should run on its own while you keep working elsewhere, when the work belongs on pages you already have open and signed into, when deciding which logins to import into the built-in browser, or when weighing the prompt-injection risk of letting an agent act on a website.
- ▌ Long Context Needle Finding · uygnoey bundleImprove long-context retrieval by requiring the model to first quote the most relevant sentence from the provided context before answering.
- ▌ Finance First Pass Deliverables · uygnoey bundleProduce structured first-pass finance deliverables and iterate with human validation, keeping work close to spreadsheets, decks, and source files.
- ▌ Interactive Visual Prompts · uygnoeyHelps the user prompt Claude to generate and iteratively refine temporary, inline interactive visuals (charts, diagrams, and visualizations) during a conversation. Trigger when the user asks to draw a diagram, visualize a trend over time, or wants an explanation supported by interactive visuals.
- ▌ AI Native Startup Playbook · uygnoey bundleStage-based playbook for using Claude across Idea, MVP, Launch, and Scale to build an AI-native startup.
- ▌ Agentic Risk Assessment · uygnoey bundleAssess and bound the security risk of an agentic AI deployment before approving it. Use when a team asks to connect an agent to internal systems, when reviewing a personal agent harness or an autonomous service agent, when writing an agent security review process, or when deciding which controls a vendor must demonstrate. Applies a four-question risk assessment (untrusted content, actions and identity, blast radius, observability), places the deployment on the identity spectrum from service account to human credential, and checks it against seven deployment controls covering identity, connector allowlists, per-action approval, sandboxed execution, egress allowlisting, telemetry, and an off switch.
- ▌ Console Prompt Iteration Playbook · uygnoeyA lightweight playbook for iterating on prompts in the Anthropic Console using prompt improvement, structured examples, and evaluations.
- ▌ Connectors Directory Browser · uygnoey bundleUse a lightweight checklist and prompt templates to evaluate a Claude connector from a directory, clarify required permissions, and define safe success criteria before you connect it.
- ▌ Code Routines · uygnoey bundleDesign and deploy routines in Claude Code — automations bundling a prompt, repo, and connectors that run on a schedule, via an API call, or in response to GitHub events. Covers trigger selection, prompt shape, and common patterns from the research preview announcement.
- ▌ Connectors Discovery · uygnoeyGuidance for discovering and using Claude connectors (especially everyday-life connectors) in conversations, with an emphasis on user control over what data is accessed and shared.
- ▌ Bundled API Skill Usage Patterns · uygnoey bundleGet the most out of the bundled claude-api skill (now shipping in CodeRabbit, JetBrains, Junie, Resolve AI, Warp, and Claude Code) by triggering the four post-named workflows — improving cache hit rate, adding context compaction, upgrading to the latest Claude model, and onboarding a deep research agent — instead of looking up API parameters manually.
- ▌ AWS Platform Access · uygnoey bundleEvaluate and plan how to access Anthropic's platform through AWS entry points (IAM, billing, and CloudTrail), and document the key differences versus Claude on Amazon Bedrock.
- ▌
- ▌ Enterprise Rollout Checklist · uygnoeyA checklist for rolling out Claude Enterprise with identity, compliance visibility, retention controls, and spend governance.
- ▌ Console Prompt Evaluation Workflow · uygnoeyA workflow for generating prompts, building test suites, running batch evaluations, and iterating based on side-by-side comparisons and SME scoring in the Anthropic Console.
- ▌ Slack To Code Session Routing · uygnoeyGuidance for delegating coding tasks from Slack to Claude Code sessions, including setup, when it works best, and what to expect in the workflow.
- ▌ Auto Mode Adoption · uygnoey bundleDecide, configure, and roll out a default permission mode in Claude Code now that auto mode is the default on Pro, Max, and Team plans. Use when choosing between auto mode, manual permission prompts, and bypass permissions; when an admin needs to pin or disable an org-wide default; when explaining the safety evidence behind the change; or when working out which permission rules still apply under auto mode and when to step out of it.
- ▌ Commerce Agent Blueprint · uygnoey bundleStand up a commerce agent from Anthropic's open blueprint, which ships reference implementations of a shopping agent and a merchant agent with examples across retail, travel, telecom and ticketing. Covers what the blueprint contains, the integration points each agent needs, the guardrails that ship with it, and where the deployment can run - the Claude API, Amazon Bedrock, Microsoft Foundry, or Google Cloud Vertex AI. Use when starting a commerce agent project, or when scoping what a shopping or merchant agent will need from your existing systems.
- ▌ Bedrock Availability Summary · uygnoeySummarize the Claude blog announcement that Claude 2 is available on Amazon Bedrock, including what it is and who it may be relevant for.
- ▌ Citations Grounded Answers · uygnoey bundleBuild and evaluate “grounded answers” experiences using Anthropic API Citations so users can trace each claim back to source passages.
- ▌ Browser Based Code Delegation · uygnoeyEnables delegating well-defined coding tasks to a cloud sandbox from a web browser (useful for bug backlogs, routine fixes, and parallel coding work). Trigger when the user asks to connect a GitHub repo and have Claude implement changes without using a local terminal.
- ▌ Manage Agent View Sessions · uygnoey bundleRun and manage multiple Claude Code background sessions efficiently using agent view (dispatch, peek/reply, attach/detach, filtering, and lifecycle commands).
- ▌ Realistic Agent Evals · uygnoey bundleBuild an internal evaluation that reflects how engineers actually prompt a coding agent — underspecified requests, missing context, wrong premises — instead of well-defined benchmark problems, and score whether the model understood the request rather than only whether the answer was right. Use when public benchmark scores stop matching what your developers report, when designing an internal benchmark, when writing eval tasks from real user prompts, or when a suspiciously high score needs to be checked by reading traces.
- ▌ Browser Side Panel Sessions · uygnoey bundleRun and hand off work in the Chrome side panel now that it is a Cowork session — decide when the browser is the right surface, write a task brief that survives the action check, choose an autonomy level against the prompt-injection risk, and continue the same session on desktop, web, or mobile.
- ▌ MCP Integration Primer · uygnoeyReusable implementation notes derived from the Claude blog post “What is Model Context Protocol? Connect AI to your world”.
- ▌ Frontier Model Routing · uygnoey bundleDecide when a task deserves the most capable model and when a lighter, faster one is enough, using the A-to-B heuristic Cursor settled on — if you know the path from A to B, a cheaper model will do; if you are at A with no idea where B is, reach for the frontier model. Use when configuring a mixed-model setup, when choosing a model for a gnarly refactor or an open-ended migration, when a task keeps stalling under a cheaper model, or when deciding whether a long-shelved rewrite is now worth starting.
- ▌ Code Team Playbook · uygnoey bundleA practical playbook of Claude Code usage patterns across teams (navigation, testing, debugging, prototyping, docs, and automation), distilled from Anthropic’s internal examples.
- ▌ Microsoft 365 Enterprise Search · uygnoey bundleUse Claude with Microsoft 365 context (SharePoint/OneDrive, Outlook, Teams) by framing questions for cross-tool enterprise search and producing source-backed reports.
- ▌ Startup Agent Adoption · uygnoey bundleSelect, launch, and scale AI agent use cases in a startup with a pragmatic approach to risk, modularity, and human oversight.
- ▌ Contribution Metrics Github Setup · uygnoeyEnable Claude Code contribution metrics by connecting your organization to GitHub, then verify the analytics dashboard is populating PR and commit attribution.
- ▌ Cowork Enterprise Admin Controls · uygnoeyA checklist-style reference of the enterprise admin controls described for Claude Cowork (RBAC, spend limits, usage analytics, and OpenTelemetry observability).
- ▌ Legal Industry Workflows · uygnoey bundleBuild reusable, practice-specific legal workflows with Claude by collecting context via a short setup interview and producing grounded, verifiable work product across documents and tools.
- ▌ Cowork Getting Started · uygnoeyUse Claude Cowork for multi-step knowledge work across local files and connected apps, aiming for concrete deliverables with traceable citations.
- ▌ Foundation Models Handoff · uygnoeyUse Apple Foundation Models for fast on-device tasks, then hand off to Claude for multi-step reasoning, code generation, web search, or code execution—while keeping a single, continuous user experience.
- ▌ Auto Mode Production Practices · uygnoey bundleOperating patterns for running Claude Code's auto mode as a daily production default, drawn from how Nuro, Gusto, and Garner Health use it. Use when deciding whether a team should default to auto mode, when designing the guardrails around it (deny rules, MCP proxying, classifier tuning, telemetry), when choosing which work to leave unattended overnight, or when deciding which sessions should step out of auto mode and into manual review.
- ▌ Responsive Layout Refactor · uygnoey bundleIdentify rigid CSS layout constraints and refactor them into responsive patterns with breakpoint checks and device-coverage tests.
- ▌
- ▌ Parallel Desktop Workflows · uygnoeyA reusable checklist for using Claude Code desktop features to manage parallel work across multiple sessions, panes, and projects.
- ▌ Agent Identity Access Model · uygnoeyConfigure and roll out workspace-owned “agent identities” for team-wide AI agents with least privilege, strong boundaries, and reliable auditing.
- ▌ Inference Dlp Rollout · uygnoey bundlePlan and execute a staged rollout of inline data loss prevention for an enterprise AI deployment, where a policy server returns an allow/deny verdict on every prompt and tool call response before the model sees it. Use when a security or compliance team must inspect AI traffic at a control point they own, when an existing DLP program has to be extended to AI surfaces, or when enforcement must be introduced without blocking users on day one.
- ▌
- ▌ Compliance API Audit Feed · uygnoeyEnable and use the Claude Platform Compliance API to retrieve and filter organization audit activity (by time range, user, or API key) for security and compliance workflows.
- ▌ Managed Agent Orchestration · uygnoey bundleCreate better Claude Managed Agents runs by defining outcomes rubrics, clarifying multiagent roles (lead/specialist/grader), and using a lightweight dreaming review checklist.
- ▌ Managed Agents New Capabilities · uygnoey bundleAdopt the four capabilities Anthropic shipped to Claude Managed Agents at Code w/ Claude SF 2026 — Dreaming (scheduled memory curation from past sessions), Multiagent orchestration (a lead agent delegating to parallel specialist subagents on a shared filesystem), Outcomes (a separate grader scoring each result against a developer-defined rubric until the bar is met), and Webhooks (async completion notification). Use when a team building on Claude Managed Agents needs to decide which of these to turn on, in what order, and how they fit a production pipeline.
- ▌ Apps Gateway Rollout · uygnoey bundlePlan and roll out Claude Code via a self-hosted apps gateway, using centralized SSO login, managed settings enforcement, and per-user usage attribution when running on Amazon Bedrock or Google Cloud.
- ▌ Bedrock Haiku Finetune Checklist · uygnoeyChecklist-style workflow for preparing prompt–completion training data and evaluating a fine-tuned Claude 3 Haiku model in Amazon Bedrock.
- ▌ Agentic Coding Foundations · uygnoey bundleIntroduce engineers to agentic coding with Claude Code — how it differs from autocomplete and chat-based assistants, how a two-phase workflow (context gathering + planning, then implementation + coordination) plays out, what permission model to expect, and which onboarding prompts produce immediate value. Use when explaining Claude Code to a new team, deciding which workflows to delegate first, or grounding a pitch in the Rakuten case study.
- ▌ Enterprise Managed Connector Auth · uygnoeyCentralize authorization for MCP connectors via an identity provider so admins provision once and users inherit access via IdP groups and roles.
- ▌ Intelligence Cost Routing · uygnoey bundleDecide which work gets a frontier model and which gets a smaller one by measuring task completion ratio alongside cost per task, then sending the frontier model only the work where the extra capability changes the outcome. Use when frontier pricing limits how widely a model can be deployed, when justifying a more expensive model for a subset of work, or when comparing models whose per-token price differs but whose token usage and wrong-turn rate also differ.
- ▌ MCP 2026 07 28 Adoption · uygnoey bundleAdopt the MCP 2026-07-28 specification — the fifth Model Context Protocol spec release, which moves MCP to a stateless request/response core, graduates MCP Apps and Tasks into a versioned extensions framework, and hardens authorization to align with production OAuth 2.0 and OIDC. Use when planning an MCP server against the new spec, when deciding whether to deploy a server on serverless or edge infrastructure, when connecting a server to an enterprise identity provider such as Entra or Okta, when adding interactive UI or long-running work to a server, or when preparing a connector for the Claude connectors directory. Also covers what shipped on the Claude side — MCP Apps, enterprise-managed auth, connector observability, and MCP tunnels.
- ▌ Life Sciences AI Rollout · uygnoey bundlePlan and run a staged rollout of an agentic AI research workbench inside a life sciences organization — choosing the right surface for each kind of work, getting the install next to real data and compute, and moving from foundation to pilot to scale with metrics that show it is working. Use when a research org is deciding where AI fits across analysis, document, and pipeline work, when Research IT must review install footprint and governance before controlled data is touched, or when a pilot needs measurable criteria rather than enthusiasm.
- ▌ Enterprise Workspace Security Basics · uygnoeyEstablish baseline administrative and security practices for rolling out Claude in an organization, based on capabilities highlighted in the Claude for Enterprise announcement.
- ▌ Overnight Agent Delegation · uygnoey bundleHand an agent a whole task instead of a pre-chunked sequence, and let it run unattended for hours or a full day — because the model re-checks its own assumptions mid-run, returns to first principles at each step, and carries memory of past failures between runs. Use when deciding how large a unit of work to delegate, when a long agentic run keeps failing on an early wrong turn, when setting up agents to run overnight without a human checking in, or when the number of tasks is rising faster than the human judgment available to review them.
- ▌ Interactive Connectors Overview · uygnoeyTurn a connector feature announcement (like MCP Apps interactive connectors) into a practical evaluation and rollout checklist your team can reuse.
- ▌ Building On Evolving Models · uygnoeyApplies three patterns for building applications on a model whose intelligence keeps improving — use general tools the model already knows, remove scaffolding the model can now do itself, and set boundaries only where UX, observability, or security demand it. Use when the user is designing an agent, LLM-powered app, or tool layer and is deciding how much structure to impose around the model.
- ▌ Managed Agents Memory Overview · uygnoeyConceptual guidance for using built-in, filesystem-based memory with Claude Managed Agents (portable memories, enterprise controls, and operational considerations).
- ▌ Configure Wif Service Accounts · uygnoeyPlan and review a Workload Identity Federation (WIF) setup for Claude Platform workloads, using service accounts, federation rules, and least-privilege scopes.
- ▌ Foundry Azure Deployment Choice · uygnoeyDecide whether to run Claude via Microsoft Foundry hosted on Azure or hosted on Anthropic, based on Azure-native requirements vs. needing full API feature/model availability.
- ▌ Browser Control Safety · uygnoey bundleDecide when browser control is the right tool for a task and understand the safety layers behind it — autonomous approval of safe actions, prompt-injection defenses, and enterprise domain restrictions. Use when a workflow depends on an internal dashboard, legacy system, or vendor portal with no native integration, when weighing whether to let an agent act in a browser session, or when an admin needs to scope which domains are in reach.
- ▌ Agent Capabilities Adoption Checklist · uygnoey bundleChecklist and implementation notes for adopting Claude API capabilities for agentic applications (code execution, MCP connector, Files API, and extended prompt caching).
- ▌ API Integration Resilience Playbook · uygnoey bundlePlan and implement resilient third-party API integrations with Claude. Use Claude.ai to enumerate failure modes, authentication risks, and rate-limit strategies before coding, then use Claude Code to generate typed clients, OAuth/JWT/key-rotation flows, and contract/refresh tests across the codebase. Apply when onboarding a new API, hardening a flaky integration, or standardizing how a team splits planning vs implementation work for integrations.
- ▌
- ▌ Computer Use With Dispatch Workflow · uygnoeyUse a "connectors-first, UI-second" workflow to complete multi-step tasks on a user's computer, with explicit permission checkpoints and safe handoff via Dispatch.
- ▌ Agentic Coding Operating Rules · uygnoey bundleApply the five operating rules fast-growing startups use to ship with agentic coding — everyone ships, automate the tedium, trust but verify, build for rebuilding, and prototype-dogfood-productionize. Use when deciding how a small team should organize around Claude Code; when non-engineers want to contribute product changes; when choosing which parts of the SDLC to hand to agents and how to gate them; when a rewrite keeps losing the prioritization fight; or when you want internal agent experiments to graduate into customer-facing product.