Menu
Skills in this repository
SkillsMP has collected 722 skills from Sheshiyer/skill-clusters. Open a skill to review its source and details.
Sheshiyer/skill-clustersShowing 40 of 722 collected skills.
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. USE WHEN an agent run fails, loops, or behaves unexpectedly and you need a repeatable post-mortem and recovery process.
Operate as an agentic engineer using eval-first execution, task decomposition, and cost-aware model routing. USE WHEN planning or executing LLM-driven engineering work and you need disciplined evals, decomposition, and model-selection practices.
Build persistent multi-agent operating systems on Claude Code, covering kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and database-free state. USE WHEN designing a multi-agent system, kernel, or file-based…
Regression testing strategies for AI-assisted development: sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch blind spots when the same model writes and reviews code. USE WHEN guarding AI-generated…
Clean Architecture patterns for Android and Kotlin Multiplatform projects, covering module structure, dependency rules, UseCases, Repositories, and data-layer patterns. USE WHEN structuring an Android/KMP codebase, defining module boundaries, or applying…
Generate Angular code and architectural guidance covering signals reactivity, forms, dependency injection, routing, SSR, ARIA, animations, styling, testing, and CLI tooling. USE WHEN creating Angular projects, components, or services, or applying modern…
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs. USE WHEN designing or reviewing a REST API's endpoints, response shapes, versioning, or error…
Capture architectural decisions as structured ADRs, recording context, alternatives considered, and rationale, and maintaining an ADR log of why the codebase is shaped as it is. USE WHEN a significant design or technology choice is made and should be…
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. USE WHEN building or refactoring Node/Express/Next.js backend code, API routes, or data-access and server-side logic.
Measure performance baselines, detect regressions before and after PRs, and compare stack alternatives. USE WHEN establishing a perf baseline, checking whether a change slowed things down, or benchmarking competing libraries or approaches.
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent projects, with self-contained per-step briefs, adversarial review gate, dependency graph, and parallel-step detection. USE WHEN planning a complex multi-PR or…
Automate visual testing and UI interaction verification through browser automation. USE WHEN confirming a deployed or in-progress feature renders and behaves correctly in a real browser, or catching visual and interaction regressions.
Guide to building polished apps with Expo Router, covering fundamentals, styling, components, navigation, animations, patterns, and native tabs. USE WHEN building or styling Expo/React Native UI, setting up Expo Router navigation, or adding native tabs and…
Set up Tauri CI/CD with GitHub Actions and tauri-action for cross-platform desktop builds. USE WHEN automating Tauri build, test, or release across Windows/macOS/Linux, configuring workflow triggers, or publishing signed releases.
Bun as runtime, package manager, bundler, and test runner, including when to choose Bun vs Node. USE WHEN adopting Bun, migrating from Node, writing or debugging Bun scripts/tests, or configuring Bun on Vercel.
Call the Tauri v2 frontend from Rust via the event system, channels, and JavaScript evaluation. USE WHEN emitting events from Rust to the webview, streaming data over IPC channels, or pushing state changes from backend to frontend.
Call Rust backend functions from the Tauri v2 frontend with invoke and #[tauri::command]. USE WHEN defining commands, passing arguments or return values across IPC, handling command errors, or wiring async frontend-to-Rust calls.
Monitor and verify a deployed URL by checking HTTP endpoints, SSE streams, static assets, console errors, and performance regressions. USE WHEN smoke-testing or canary-watching after a deploy, a risky merge, or a dependency upgrade.
Cisco IOS and IOS-XE review patterns for show commands, config hierarchy, wildcard masks, ACL placement, and interface hygiene. USE WHEN reviewing IOS/IOS-XE config before a change, picking read-only show commands, or verifying a change-window landed safely.
Persistent per-project memory for Claude Code that auto-loads context on session start, tracks sessions with git activity, and writes native memory via deterministic Node.js scripts. USE WHEN running /ck:* commands or keeping project context across sessions.
ClickHouse schema, query optimization, and data-engineering patterns for high-performance OLAP workloads. USE WHEN designing MergeTree tables, writing or tuning analytical queries, ingesting large data volumes, or migrating from Postgres/MySQL to ClickHouse.
Create CodeTour .tour files — persona-targeted, step-by-step walkthroughs anchored to real files and line ranges. USE WHEN building onboarding tours, architecture walkthroughs, PR tours, RCA tours, or a reusable 'explain how this works' artifact.
Compose Multiplatform and Jetpack Compose patterns for KMP — state management, navigation, theming, performance, and platform-specific UI. USE WHEN building shared Compose UI across Android/iOS/Desktop/Web, managing Compose state, or optimizing recomposition.
Configure Tauri v2 apps via tauri.conf.json, Cargo.toml, and package.json, including environment-specific overrides. USE WHEN setting up or editing Tauri config, tuning window/bundle/plugin options, or managing per-environment desktop and mobile settings.
Configure Tauri v2 capabilities to bind permissions to specific windows and webviews for access control. USE WHEN writing capability files, scoping permissions per window label, setting desktop/mobile targets, or tightening frontend security boundaries.
Configure Content Security Policy (CSP) in Tauri v2 apps to prevent XSS and restrict where the webview loads resources. USE WHEN setting or hardening CSP in tauri.conf.json, debugging blocked scripts/styles, or tightening webview trust boundaries.
Configure HTTP response headers in Tauri v2.1+ webview responses, covering security headers, custom headers, and CORS from the allowlist. USE WHEN adding security headers, setting CORS for cross-origin requests, or customizing webview response headers.
Configure the Tauri v2 permission system controlling frontend access to backend commands and resources. USE WHEN defining allow/deny lists, enabling plugin permissions, referencing permission identifiers, or wiring permissions into scopes and capabilities.
Configure Tauri v2 command scopes for fine-grained authorization with allow/deny rules, where deny wins. USE WHEN restricting filesystem paths or URL patterns per command, managing scopes dynamically, or enforcing capability-based access in command logic.
Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. USE WHEN running long-lived agent loops and choosing between sequential, continuous-PR, RFC-DAG, or infinite parallel modes with safe recovery.
Instinct-based learning that observes Claude Code sessions via hooks, creates confidence-scored atomic instincts, and evolves them into skills/commands/agents with project-scoped isolation. USE WHEN setting up session learning, tuning instinct thresholds, or…
Cost optimization patterns for LLM API usage: model routing by task complexity, budget tracking, retry logic, and prompt caching. USE WHEN LLM API spend is too high, picking models per task, adding budget caps, or wiring prompt caching.
C++ test authoring and tooling with GoogleTest and CTest. USE WHEN writing, updating, or fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage or sanitizers.
Customize Tauri desktop windows: custom titlebars, transparent windows, decorations, drag regions, menus, submenus, and menu keyboard shortcuts. USE WHEN building a frameless or custom titlebar, transparent window, drag region, or native window menu in Tauri.
Production Dart and Flutter patterns: null safety, immutable state, async, widget architecture, BLoC/Riverpod/Provider, GoRouter, Dio, Freezed, and clean architecture. USE WHEN structuring a Flutter app, choosing state management, or wiring navigation and…
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deploys across PostgreSQL, MySQL, and ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate). USE WHEN writing a migration, planning a zero-downtime…
Debug Tauri v2 apps across VS Code, RustRover, IntelliJ, and Neovim: console debugging, WebView DevTools, Rust backtraces, CrabNebula DevTools, and IDE launch configs. USE WHEN a Tauri app misbehaves and you need breakpoints, DevTools, or backtraces wired up.
Security checklist for Solidity AMM contracts, liquidity pools, and swap flows: reentrancy, CEI ordering, donation/inflation attacks, oracle manipulation, slippage, admin controls, and integer math. USE WHEN auditing or writing an AMM, liquidity pool, or swap…
Deployment workflows for web apps: CI/CD pipelines, Docker containerization, health checks, rollback strategies, and production readiness checklists. USE WHEN shipping a web app, setting up a CI/CD pipeline, containerizing with Docker, or hardening a release…
Generate or audit design systems, check visual consistency, and review styling changes. USE WHEN creating a design system or design tokens, auditing visual consistency, or reviewing a PR that touches CSS, theming, or styling.