Updates a presentation with new numbers — quarterly refreshes, earnings updates, comp rolls, rebased market data. Use whenever the user asks to "update the deck with Q4 numbers", "refresh the comps", "roll this forward", "swap in the new earnings", "change all the $485M to $512M", or any request to swap figures across an existing deck without rebuilding it.

Codebase assessment skill - evaluates code quality, identifies hotspots, and prioritizes refactoring opportunities

Verification skill - confirms behavior preservation and quality improvement after refactoring

Run Gemini Deep Research from Claude Code. Optimizes prompts for depth and structure, then executes multi-step research via the Interactions API. Use when you need in-depth analysis, competitive landscaping, literature reviews, market research, or any question requiring real-time web research across many sources.

Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.

Enhance a plan with parallel research agents validating each section against best practices

View execute-mode session status — phase, plan_hash, drift, change_log, test results, 3-dimension verdict table, rollback log, discoveries

Add, remove, replace, or list hard guardrails for the active deepwork session

View deepwork session status — phase, team, bar verdicts, proposals, guardrails

Use when invalid data causes failures deep in execution, bypassing initial checks - adds validation at entry, business logic, and environment layers to make bugs structurally impossible

Delete tidbits (defaults, custom, or all)

Display a summary table of available deltas or show recommended next deltas

Extract deltas from the project vision

Build a demand generation strategy and multi-channel campaigns. Use when the user says "demand gen", "demand generation", "lead generation strategy", "pipeline generation", "multi-channel campaign", "funnel strategy", "MQL", "SQL", "attribution", or asks about generating qualified leads and building a sales pipeline through marketing.

Provides a reference template and structural guide for creating Claude Code plugin skills. Activates when the user asks about skill development patterns, requests a skill template, or wants to understand the SKILL.md format and frontmatter options.

Surface dependency debt — outdated packages, abandoned/deprecated libs, unused deps, version drift across manifests. Static analysis only (no package manager calls). Use before upgrades, audits, or when planning tech renewal.

[experimental] Evaluate deployment risk by analyzing code changes against incident history, active incidents, and on-call readiness. Forked-subagent flow may not have MCP access in all Claude Code contexts.

Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use when architecting deployment workflows, setting up continuous delivery, or implementing GitOps practices.

Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use when architecting deployment workflows, setting up continuous delivery, or implementing GitOps practices.

Get full schema for a Salesforce object - field names, types, picklist values, relationship names. Use before writing SOQL to discover custom fields (ending in __c) and relationship traversal names.

Technical design and architecture for implementation

Surface design-level debt — inconsistent patterns (error handling, naming, response shapes), architectural drift from declared principles, duplicated business logic. Use when the codebase feels harder to reason about than it used to.

Run the full design-to-build workflow as a guided sequence. Orchestrates all designer skills in order, from grilling through review. Use when user wants to go through the complete design process, start a project from scratch, run the full flow, or mentions "design flow" or "full workflow".

Enforce design-to-code fidelity rules. Use when implementing UI from Figma, mockups, or design specs to ensure pixel-perfect accuracy.

Generate a design tokens file (CSS variables or Tailwind config) based on a chosen aesthetic philosophy, with light and dark mode palettes, spacing scale, type ramp, and component-level tokens. Use when starting a new project, establishing a visual system, setting up tokens, or mentions "tokens" or "design system".

Designs software architecture and selects appropriate patterns for projects. Use when designing systems, choosing architecture patterns, structuring projects, making technical decisions, or when asked about microservices, monoliths, or architectural approaches.

Analyze git changes to determine release scope (marketplace/plugin/variants)

Discover project types, build commands, test commands, and language-specific guidelines for the current workspace. Use when the user says "what kind of project", "detect project", "build command", "test command", "project type", asks what language or framework the code uses, or wants to know how to build, test, or format the project. Also use early in any session before making changes.

Generate Playwright E2E tests by exploring websites and automating browser interactions. Use when the user wants to generate Playwright tests by exploring a website, or needs browser automation.

List, manage, and interact with connected Apple devices (iPad, iPhone, Mac). Use when user asks "what devices are connected", "list devices", "launch app on iPad", "kill app on device", "reset permissions", or needs to manage TCC permissions for Screen Recording/Accessibility.

Audit devloop against Claude Code updates to identify integration opportunities. Use after Claude Code releases, monthly maintenance, or when exploring new features.

Verify DevOps/infrastructure code against best practices, security, simplicity, and documentation standards. Use after implementing or before shipping infrastructure changes.

Advanced multichain DEX aggregator. Finds the best token swap routes across 50+ decentralized exchanges on 9+ blockchain networks (Ethereum, BSC, Polygon, Arbitrum, Optimism, Base, Avalanche, Gnosis,

Interactive troubleshooting assistant for Claude Code issues

# Diagram Design Philosophy

Use when a documentation request is ambiguous, involves planning a docs structure, or a page seems to mix multiple purposes. Classifies content into Diátaxis quadrants (tutorial, how-to, reference, explanation), proposes a documentation map, and produces a writing plan with ordering. Triggers on phrases like "plan my docs", "what docs do I need", "help me organise my documentation", "docs architecture", "I need to write docs for my project", or when a user asks for a README and a full docs set together.

Writes high-converting landing pages and sales copy using proven page architecture and persuasion principles. This skill should be used when creating sales pages, landing pages, product pages, or any copy designed to drive immediate action like purchases, sign-ups, or bookings.

Display directory structure as a formatted tree. Use when the user needs to visualize a directory structure, analyze folder organization, or share a file tree view. Supports custom paths via the /tree command.

When the user wants to create, optimize, or audit an affiliate, sponsor, or paid partnership disclosure page. Also use when the user mentions "disclosure," "affiliate disclosure," "sponsored content," "FTC disclosure," or "paid partnership." For sitewide page planning, use website-structure.

Automatically discover data pipeline and ETL skills when working with ETL, data pipelines, streaming, batch processing, data validation, or pipeline orchestration. Activates for data development tasks.

Automatically discover software engineering practice skills when working with code review, documentation, pair programming, production debugging, performance profiling, deployment strategies, or software engineering practices. Activates for engineering development tasks.

Automatically discover cloud, infrastructure, deployment, and container skills when working with AWS, GCP, Azure, Docker, Kubernetes, Terraform, Netlify, Heroku, serverless, or IaC

Automatically discover MCP (Model Context Protocol) skills when building MCP servers, designing tools, implementing resources/prompts, or testing MCP integrations. Activates for MCP server development tasks.

Automatically discover eBPF, compiler, programming language theory, information retrieval, and formal verification skills when working with kernel tracing, parsers, type systems, Z3, Lean, or theorem proving

Requirements elicitation and validation through structured questioning. Invoke whenever task involves defining what to build, scoping a problem or feature, or starting the DRAFT pipeline.

Intent router. Auto-detects execution mode from context and routes to the appropriate skill.

When the user wants to run display, banner, or ad network campaigns. Also use when the user mentions "display ads," "banner ads," "ad network," "ad alliance," "programmatic display," "native ads," or "retargeting display." For strategy, use paid-ads-strategy.

Easily display and interact with HTML content in your Flutter app using the `easy_web_view` package, which supports both web and mobile platforms.

Use when implementing distributed tracing, using Jaeger or Tempo, debugging microservices latency, or asking about "tracing", "Jaeger", "OpenTelemetry", "spans", "traces", "observability"

Guides the user through distributing Tauri applications for Android, including Google Play Store submission, APK and AAB generation, build configuration, signing setup, and version management.

Django REST Framework patterns. Trigger: When building REST APIs with Django - ViewSets, Serializers, Filters.

Execute a task through plan, implement, evaluate phases with automatic retry logic until completion

Surface documentation debt — stale READMEs, missing public API docs, broken internal links, undocumented env vars. Use when onboarding gets friction, before a release, or when an API has evolved without matching doc updates.

Chain document operations into reusable pipelines

Update documentation to match implementation

Docs/changelog checkpoint. Detects whether changes are user-facing and ensures documentation hygiene (CHANGELOG + lessons-learned) is handled or explicitly bypassed. Use when: 'docs check', 'changelog', 'release notes', 'did we update docs?'.

Documentation creation and summarization. Use when the user asks to "write docs", "create documentation", "update README", "document this", "summarize code", "add docs", "write a changelog", "document the API", "explain this module", or mentions documentation, summarization, or README updates.

Captures unrelated follow-up issues discovered during repository work and records them for later. Use proactively when: (1) working inside a git repository, (2) an out-of-scope bug, cleanup item, missing test or documentation, or tech-debt task is discovered, (3) the user mentions filing an issue, follow-up, backlog item, or nytid import. Prefer gh issue, ask before creating anything unless autonomous issue capture is enabled, and optionally import created GitHub issues into nytid todo.

Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.

Documents dbt models and columns in schema.yml. Use when working with dbt documentation for: (1) Adding model descriptions or column definitions to schema.yml (2) Task mentions "document", "describe", "description", "dbt docs", or "schema.yml" (3) Explaining business context, grain, meaning of data, or business rules (4) Preparing dbt docs generate or improving model discoverability Matches existing project documentation style and conventions before writing.

Identifies domain modules, ownership boundaries, dependencies, and interfaces using Domain-Driven Design principles. Provides domain maps, bounded contexts, refactor recommendations. Use for "DDD", "domain modeling", "bounded contexts", or "service boundaries".

Refactor a backend domain to follow the 3-layer architecture pattern (Controller → Service → Entity). Use when asked to refactor a domain, add an entity layer, fix architecture violations, or align a domain with backend-architecture.md. Triggers on phrases like "refactor domain", "add entity", "fix architecture", "align with pattern", or "domain doesn't have an entity".

Finds all publicly available email addresses and contacts at a company domain. Use when the user asks who works at a company, wants to find contacts at a domain, or needs email addresses for an organization.

Create and customize Domino Compute Environments - Docker containers defining tools, packages, and configurations. Covers Dockerfile customization, package installation, IDE configuration, DSE (Domino Standard Environments), and troubleshooting build failures. Use when installing dependencies, customizing environments, or fixing environment issues.

Monitor deployed models in Domino including drift detection, model quality tracking, and alerting. Covers data drift analysis, prediction capture, baseline comparison, alert configuration, and remediation workflows. Use when monitoring production models, detecting drift, or setting up model health alerts.

Build a graph-structured dossier on a seed entity via parallel fan-out + recursive expansion across web, memory, knowledge-graph, codebase, ADR index, and git intel

Using artifacts output layout. UseArtifactsOutput, ArtifactsPath, impact on CI and Docker.

Writing async/await code. Task patterns, ConfigureAwait, cancellation, and common agent pitfalls.

Registering or resolving services with MS DI. Keyed services, scopes, decoration, hosted services.

Creating a new .NET project. Generates solution with CPM, analyzers, editorconfig, SourceLink.

Choosing inter-service protocols. REST vs gRPC vs SignalR vs SSE decision matrix, tradeoffs.

Installing or managing .NET tools. Global, local, manifests, restore, version pinning.

Export PostHog events, persons, or sessions on demand and download the resulting files. Use when the user asks to download/export raw PostHog data, create a one-off file export, fetch a Parquet or JSONLines export, or use the file_download_batch_exports API. Covers starting the export with MCP, polling completion, and downloading via the existing REST redirect endpoint.

Consolidates stored memories by merging duplicates, resolving contradictions, and pruning stale entries. Use when memory count is high, search results feel noisy or repetitive, or periodic cleanup is needed to maintain memory quality.

Stage N1. Stochastic scanning of past conversations to gather raw memory fragments. Broad, unfocused, deliberately noisy. The only stage that touches conversation history directly.

Detect documentation-code drift. Deterministic collection (grep/AST) feeds a single LLM semantic analysis call. Reports mismatches with certainty grades.

Teaches dynamic import() for on-demand code loading. Use when you need to reduce initial bundle size by lazily loading modules that aren't required at startup.

East Execution Engine (e3) - durable dataflow execution for East programs. Use when: (1) Authoring e3 packages with @elaraai/e3 (e3.input, e3.task, e3.package, e3.export), (2) Running e3 CLI commands (e3 repo create, e3 start, e3 watch, e3 get, e3 set), (3) Working with workspaces and packages, (4) Content-addressable caching and dataflow execution.

Rust eBPF skill using the Aya framework. Use when writing eBPF programs in Rust with aya-bpf and aya-log, defining BPF map types, integrating with tokio userspace, sharing maps between kernel and userspace, or debugging Aya compilation and loading errors. Activates on queries about Aya, aya-bpf, Rust eBPF, aya-log, eBPF in Rust, or BPF programs with tokio.

Cross-platform keyword research for e-commerce. Discover high-converting keywords across Amazon, Shopify, Etsy, Google Shopping, TikTok Shop, and Walmart. Analyzes search volume signals, competition indicators, commercial intent, and long-tail opportunities.

Plan social media marketing strategy for e-commerce brands. Content calendars, platform selection, posting schedules, engagement tactics, and social commerce integration for Instagram, TikTok, Facebook, Pinterest, and YouTube.

Multi-platform Electron build configuration - esbuild bundling, electron-builder setup, and distribution

Creates automated email sequences for every stage of the customer journey including welcome, nurture, conversion, and launch flows. This skill should be used when building automated email flows, launching products, improving email-driven conversions, or onboarding new customers.

Review existing Encore.ts code for best practices and common anti-patterns.

Bootstrap a brand-new Encore.ts project from zero. Only for first-time CLI install and `encore app create` — not for architecture or feature questions.

Bootstrap a brand-new Encore Go project from zero. Only for first-time CLI install and `encore app create` — not for architecture or feature questions.

Asynchronous messaging in Encore Go via `pubsub.NewTopic` and `pubsub.NewSubscription` from `encore.dev/pubsub` — broadcast events, decouple producers from consumers, and run background handlers.

End session, save progress, create handoff. Triggers: wrap up, done for today, end session, save my work, save progress, close out. Runs health checks and captures resume point.

Commit and branch naming standards for Engram contributors, enforced by GitHub rulesets. Trigger: Any commit creation, review, or branch cleanup.

Incremental data loading patterns including backfill strategies, CDC, timestamp-based loads, and pipeline orchestration.

Configure content eval settings. Use when: adjusting score thresholds, dimension weights, or auto-reject rules.

Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relevance, generating synthetic QA pairs for retrieval testing, or optimizing chunking strategies.

Full onboarding flow — detects auth state, handles access requests for new users, and sets up project for all users.

Core Eve CLI primitives and capabilities for app developers. Use as the quick reference for commands and flows.

Configure a new Eve Horizon project after running eve init (profile, auth, manifest, and repo linkage).

Troubleshoot common Eve deploy and job failures using CLI-first diagnostics.