Claude Skills by eric-sabe

Stand up and operate a fleet of named, long-running Claude Code sessions for a project on an always-on machine — the merge orchestrator, the maintenance watchdog, and interactive worker roles — wired for cross-session messaging, remote control, and per-role permission modes. Use when the user says "launch the agent sessions", "start the fleet", "set up the always-on sessions", or asks how to inspect/attach to running agent sessions.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing screenshots, analyzing network traffic, and profiling performance.

Local code review before push. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security).

GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping

Implement GitHub issues using isolated Git worktrees to prevent conflicts when multiple AI agents work in parallel. Use when implementing issues, creating feature branches, or when the user mentions worktrees, parallel work, or agent implementation workflow.

GitHub Actions workflow authoring guidance — the `${{ }}` expression function set, shell-injection and multi-line-output safety in `run:` steps, draft-gated CI triggers, and GraphQL rate-limit handling. Activate when editing `.github/workflows/*.yml`/`*.yaml`, authoring or reviewing GitHub Actions workflows, or debugging a CI gate that runs/skips unexpectedly.

Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, or manage issue workflows. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", or any GitHub issue management task.

Build single-file interactive HTML explainers/explorers that visually explain systems — cycles, workflows, pipelines, dependency graphs, state machines, architectures, timelines. Use when asked for an "interactive explainer", "HTML explorer", "explain this visually", "make an interactive diagram of how X works", or when a markdown explanation of structure (who calls what, what depends on what, what loops back) is getting long. Produces a self-contained, offline-safe .html with focus+context h...

Cross-provider reference for LLM structured outputs with Claude 4.6, GPT-5.3, Gemini 3.1 Pro, and Grok 4. Use when implementing json_schema constrained decoding, writing Zod schemas for LLM APIs, building multi-provider abstractions, or debugging schema compliance failures.

Run the Maintenance Monster watchdog session — own the security/dependency baton, continuously watch Dependabot PRs + alerts, GHAS/CodeQL, Secret Scan, and the push-only Trivy image scan, dedup + triage each finding, and (from Phase 2 on) drive safe fixes into mm:ready PRs for Merge Monster to merge; escalate the rest. Phase 1 is read-only — watch, triage, and report only. Use when the user says "start maintenance monster", "run the maintenance watchdog", or "/maintenance-monster".

Run the Merge Monster merge-orchestrator session — own the merge baton, order the PR queue, pilot PRs through ready→CI→merge, auto-handle easy Dependabot PRs, dispatch fix agents, escalate with diagnosis. Use when the user says "start merge monster", "run the merge orchestrator", or "/merge-monster".

Run the project's diff-aware pre-push gate before pushing — builds, lints, and tests only what changed. Use when the user says "run precheck", "pre-push check", or "validate before push".

Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

Register and watch long-running background subagents so a quiet death never leaves this session idle on a corpse. Use BEFORE dispatching any background agent expected to run more than a few minutes (implementation agents, investigation agents, reviewers, builds) — and on any AGENT_OVERDUE / AGENT_STALE event those watchers emit. Not needed for quick synchronous lookups. The monsters (merge-monster, maintenance-monster) already carry this discipline in their own skills — this is the same subst...

This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage, then performs fixes at the source code level.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Preflight validation for AWS infrastructure deployments (CloudFormation/CDK). Run before any cdk deploy / aws cloudformation deploy. Validates templates (cdk synth, cdk diff, CloudFormation validate-template / lint), cleans up stale or failed stacks that block re-deploy, catches globally-unique naming conflicts (S3/ECR/etc.), and checks service quota / capacity limits. Activate when the active cloud is AWS and the user mentions deploying, validating CDK/CloudFormation, previewing infra change...

AWS service-level architecture knowledge — compute (Lambda/Fargate/ECS/EC2), data (DynamoDB/Aurora/RDS), messaging (SQS/SNS/EventBridge/Step Functions), edge (CloudFront/API Gateway), storage (S3/KMS), and Bedrock. Cost models, service quotas, failure modes, and p99/cold-start gotchas. Activate when the active cloud is AWS and the work involves designing, scaling, costing, or diagnosing AWS architecture (Lambda cold starts, Aurora connection limits, DynamoDB hot partitions, NAT egress, Fargat...

Preflight validation for Azure infrastructure deployments (Bicep/ARM). Run before any az deployment / azd up. Validates templates (bicep build, az deployment group validate / what-if), cleans up stale failed ARM deployments that block re-deploy, catches globally-unique naming conflicts (Key Vault/ACR/etc.), and checks SKU/tier and service-limit restrictions. Carries the hard-won Bicep lessons (PgBouncer Burstable limit, alert module location, KQL interpolation, ACR SKU). Activate when the act...

Azure service-level architecture knowledge — compute (Container Apps/AKS/Functions), data (PostgreSQL Flexible Server/Cosmos DB), messaging (Service Bus/Event Grid/Event Hubs), edge (Front Door/API Management), identity (Entra), storage + secrets (Blob/Key Vault/ACR), and Azure OpenAI. Cost models, service limits, failure modes, and cold-start gotchas. Activate when the active cloud is Azure and the work involves designing, scaling, costing, or diagnosing Azure architecture (Container Apps co...

Cloudflare edge/serverless architecture knowledge — compute (Workers isolates/Containers, smart placement), Pages, storage (R2/D1/KV/Durable Objects/Vectorize), messaging (Queues), AI (Workers AI/AI Gateway), and origin pooling (Hyperdrive/Cache API). CPU-time and subrequest limits, consistency tradeoffs, failure modes, and request+CPU pricing gotchas (no R2 egress). Activate when the active cloud is Cloudflare and the work involves designing, scaling, costing, or diagnosing Cloudflare archit...

Preflight validation for Cloudflare Workers/Pages deployments via Wrangler. Run before any wrangler deploy. Dry-run builds (wrangler deploy --dry-run), gradual rollout via versions upload + deployments, secrets via wrangler secret, D1 migrations (wrangler d1 migrations), account/auth check (wrangler whoami), bindings correctness in wrangler.toml (vars/KV/R2/D1/Durable Objects/Queues), and wrangler tail for logs. Activate when the active cloud is Cloudflare and the user mentions deploying a Wo...

GCP service-level architecture knowledge — compute (Cloud Run/GKE/Cloud Functions/GCE), data (Cloud SQL/Spanner/Firestore/Bigtable), messaging (Pub/Sub/Cloud Tasks/Workflows), analytics (BigQuery), edge (Cloud CDN/Load Balancing/API Gateway), storage + secrets (GCS/Secret Manager/Artifact Registry), and Vertex AI. Cost models, quotas, failure modes, and cold-start gotchas. Activate when the active cloud is GCP and the work involves designing, scaling, costing, or diagnosing GCP architecture (...

Preflight validation for GCP infrastructure deployments (Terraform / gcloud / Deployment Manager / Config Connector). Run before any deploy. Validates templates (terraform validate/plan or gcloud deployment preview), cleans up stale/failed deployments and stuck resources, catches globally-unique naming conflicts (GCS bucket, project IDs, Artifact Registry), and checks quota/capacity limits. Activate when the active cloud is GCP and the user mentions deploying, validating, previewing infra cha...

MongoDB conventions for this repo — async access via Motor, append-only data-lake discipline, and provenance on every datum. Use when reading/writing Mongo collections, adding ingest or transform pipelines, designing indexes, building an embedding/vector store on Mongo, or reasoning about which data is the system of record.

When adding or changing TypeScript under the shared database package that index.ts re-exports, update every service Dockerfile's COPY list or the container build fails with TS2307. Use for database-package modules, Dockerfile edits, or "works locally but the container build breaks".

Prisma ORM conventions for this repo — schema/migration discipline, constraints Prisma can't express, and the @@map/@map gotcha that bites $queryRaw. Activate when writing or reviewing Prisma schema (schema.prisma), migrations, generated-client usage, or raw SQL through Prisma ($queryRaw/$executeRaw), or when debugging P2002 unique-constraint errors or "relation does not exist" at runtime.

Understand Apple Ads and App Store acquisition mechanics. Use when evaluating Apple Search Ads / Apple Ads placements, campaign structure, keyword strategy, custom product pages, customer type targeting, attribution via AdServices or AdAttributionKit, App Store creative alignment, or Apple app-growth cost planning such as CPT, CPA, ROAS, and budget scenarios.

Understand Google Play growth and Google Ads app acquisition. Use when evaluating Android app growth strategy, Google Ads App campaigns, Google Play store listing optimization, store listing experiments, custom store listings, web-to-app flows, Android app-growth cost planning such as CPI, CPA, tCPA, tROAS, and the measurement realities around Google Ads, GAID, Firebase, and modern attribution.

Bicep / ARM discipline for any project where Bicep is the active IaC tool — modules/environments/main.bicep layout, parameter files (.bicepparam), the az validate → what-if flow, deployment scopes, and the hard-won Azure Bicep gotchas (globally-unique names, ACR SKU, PgBouncer Burstable limit, alert module location, KQL interpolation, metric names). Activate when working on *.bicep / *.bicepparam files, az deployment / azd provision, ARM deployment failures, or diagnosing Bicep validation and...

AWS CDK discipline for any project where CDK is the active IaC tool — app/stack structure, constructs (L1/L2/L3), synth/diff/deploy flow, stack separation, context and environment config, asset bundling, and bootstrapping. Activate when working on CDK code (bin/ + lib/ TypeScript or app.py), cdk synth/diff/deploy, construct design, or diagnosing CDK/CloudFormation deploy failures.

Terraform discipline for any project where Terraform is the active IaC tool — modules, remote state, workspaces, backends, plan/apply gates, drift detection, and import/state surgery. Activate when working on *.tf / *.tfvars files, terraform plan/apply/state operations, backend or workspace config, provider versioning, or diagnosing drift and partial applies.

Terraform code conventions — security, modularity, maintainability, style, documentation, and testing expectations for any *.tf file. Activate when writing or reviewing Terraform configuration (typically under infra/terraform/ or the project's IaC directory) to enforce consistent structure and safe defaults.

Write and review Android/Kotlin tests across the pyramid: JUnit (4/5) unit tests, MockK, Turbine for Flow/StateFlow assertions, coroutine testing with runTest and test dispatchers, Robolectric JVM tests, Espresso instrumented UI tests, and Compose UI testing with createComposeRule and semantics matchers. Use when writing or fixing unit tests, testing coroutines/Flows, mocking dependencies, choosing JVM vs instrumented tests, or testing Compose UI and ViewModels on Android.

Build Android UIs with Jetpack Compose: composition, state hoisting, remember/rememberSaveable/derivedStateOf, recomposition correctness and performance, side-effect APIs (LaunchedEffect/DisposableEffect/rememberCoroutineScope/produceState/snapshotFlow), Material 3 theming, and Compose navigation. Use when writing or reviewing @Composable functions, fixing recomposition or state bugs, hoisting state, choosing a side-effect API, applying Material 3, or improving Compose performance and stability.

Write data-safe asynchronous Kotlin with coroutines, Flow, and structured concurrency on Android. Use when fixing coroutine cancellation or leak bugs, choosing dispatchers (Default/IO/Main), designing suspend functions, modeling streams with Flow/StateFlow/SharedFlow, scoping work to viewModelScope/lifecycleScope, handling exceptions with CoroutineExceptionHandler/supervisorScope, or converting callback/RxJava APIs to coroutines. Covers Kotlin 2.x, kotlinx.coroutines structured concurrency di...

Python coding conventions for this repo (Python 3.12+, type hints, PEP 257/8). Use when writing, reviewing, or editing any *.py file. Covers type hints, docstrings, formatting, exception handling, async I/O, virtualenv discipline, and test expectations.

Shell scripting conventions for bash/sh/zsh in this repo. Use when writing or editing any *.sh file — including scripts/, .githooks/, and one-off shell snippets. Covers safety flags, structure, error handling, JSON/YAML parsing, and a script template.

Resolve Swift concurrency compiler errors, adopt approachable concurrency (SE-0466), and write data-race-safe async code. Use when fixing Sendable conformance errors, actor isolation warnings, or strict concurrency diagnostics; when adopting default MainActor isolation, @concurrent, nonisolated(nonsending), or Task.immediate; when designing actor-based architectures, structured concurrency with TaskGroup, or background work offloading; or when migrating from @preconcurrency to full Swift 6 st...

Write and migrate tests using the Swift Testing framework with @Test, @Suite, #expect, #require, confirmation, parameterized tests, test tags, traits, withKnownIssue, XCTest UI testing, XCUITest, test plan, mocking, test doubles, testable architecture, snapshot testing, async test patterns, test organization, and test-driven development in Swift. Use when writing or migrating tests with Swift Testing framework, implementing parameterized tests, working with test traits, converting XCTest to S...

Implement, review, or improve data persistence using SwiftData. Use when defining @Model classes with @Attribute, @Relationship, @Transient, @Unique, or @Index; when querying with @Query, #Predicate, FetchDescriptor, or SortDescriptor; when configuring ModelContainer and ModelContext for SwiftUI or background work with @ModelActor; when planning schema migrations with VersionedSchema and SchemaMigrationPlan; when setting up CloudKit sync with ModelConfiguration; or when coexisting with or mig...

Build SwiftUI views with modern MV architecture, state management, and view composition patterns. Covers @Observable ownership rules, @State/@Bindable/@Environment wiring, view decomposition, custom ViewModifiers, environment values, async data loading with .task, iOS 26+ APIs, Writing Tools, and performance guidelines. Use when structuring a SwiftUI app, managing state with @Observable, composing view hierarchies, or applying SwiftUI best practices.

TypeScript conventions for this repo (TS 5.x targeting ES2022, Node 22, pnpm workspaces). Use when writing or reviewing any *.ts file. Covers naming, type-system expectations, async/error handling, the pnpm-monorepo @smithy hoisting gotcha, and lib-DOM-for-fetch.

Configure and verify Android Gradle builds: Kotlin DSL (build.gradle.kts), version catalogs (libs.versions.toml), build types and product flavors, R8/ProGuard shrinking and keep rules, signing configs, and the local build/verify gate (./gradlew assembleDebug, testDebugUnitTest, lintDebug). Use when editing Gradle build files, adding dependencies, setting up flavors/variants, configuring minification or signing, or running the Android build/test/lint gate before reporting a change complete.

Use XcodeBuildMCP to run iOS simulator workflows and capture logs without manual copy/paste. Use when asked to build or run the iOS app in Simulator, inspect session defaults, start or stop simulator log capture, collect app logs for debugging, or troubleshoot StoreKit and runtime issues from simulator output.

Frontend test discipline for this repo — Vitest 4, Testing Library (RTL / React Testing Library), and Playwright E2E for React / Next.js apps. Use when writing or reviewing Vitest specs, vi.mock factories, fake-timer tests, RTL component tests, Radix portal tests, or Playwright E2E specs and their CI matrix wiring. Covers vi.hoisted mock-factory hoisting, keeping every vi.mock factory in sync, Vitest 4 pool config (fileParallelism), the fake-timers act() pattern, RTL accessible-query discipli...

React + Next.js client conventions for this repo (React 19 / Next.js 16, React Query / TanStack Query, Radix UI, shadcn-style cards/dialogs). Use when writing or reviewing React components, hooks, optimistic cache patches, data-fetching code, dialogs, Radix Select usage, JSX, interactive cards/rows, or Next.js Edge Runtime / middleware code. Covers optimistic-cache completeness, fetch error states, destructive-dialog error handling, the React 19 set-state-in-effect rule, a Radix Select form f...

Web platform conventions for this repo — Content-Security-Policy discipline and (for Next.js 16+) the proxy.ts-not-middleware convention. Use when editing CSP headers, adding a third-party SDK / analytics / external API origin, touching request-edge code (middleware/proxy), or wiring auth/redirects/headers on a web frontend.