Claude Skills by D0NMEGA

Generate a SESSION_REPORT.md summarizing work performed, outcomes, files changed, and context usage read from the live statusline bridge when available. Use at the end of a work session to produce a shareable record of what happened.

Configures Donny workflow toggles and the model profile. With no argument, runs the interactive settings flow (agents, pipeline, quality gates, git, model, and the text_mode/discuss_mode options); with a profile name, switches the model profile directly. Use to tune which agents run, the model tier, branching, and other workflow options.

Ships a verified phase or milestone to a pull request: pushes the branch, builds a clean PR history that drops .planning commits by default, opens the PR with an auto-generated body, and offers review. Use when verification passes and you are ready for code review and merge.

Creates, lists, or resumes lightweight context threads that carry knowledge across sessions for work that spans multiple sittings but is not yet a phase. Use to park an investigation or line of work and pick it up later from a cold start. No args lists threads; an existing slug resumes; new text creates one.

Generates a UI design contract (UI-SPEC.md) that locks spacing, typography, color, copywriting, and component-registry decisions before a frontend phase is planned. Use when starting a UI-heavy or frontend phase, after discuss-phase and before plan-phase, to give the planner a fixed visual contract instead of leaving styling to executor discretion.

Runs a retroactive 6-pillar visual audit (copywriting, visuals, color, typography, spacing, registry and experience) of implemented frontend code and writes a scored UI-REVIEW.md with the top priority fixes. Use when grading or reviewing the visual quality of a built frontend phase, after execute-phase; works on any project, managed by donny or not.

Updates the installed Donny toolkit from the local source repo using a git-tag version check (no npm), then always reapplies local patches atomically. Use to sync ~/.claude with the donny repo after it advances, or to restore local modifications the redeploy overwrote. Modifies the global install, so it does not auto-run inside donny-autonomous.

Validates built features through conversational UAT, one acceptance test at a time with plain-text answers, then diagnoses failures and prepares verified fix plans. Use after executing a phase to confirm it works from the user's perspective and to generate gap-closure plans for anything that fails.

Manage parallel workstreams within one project milestone: list, create, status, switch, progress, complete, resume. Use when running or tracking several concurrent streams of work inside a single project. Distinct from /donny-env-new, which creates physical multi-repo workspaces; workstreams are a logical concurrency layer tracked by donny-tools.

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.

Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.

Pattern for progressively refining context retrieval to solve the subagent context problem

Java coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.

Kotlin Coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, and testing.

JetBrains Exposed ORM patterns including DSL queries, DAO pattern, transactions, HikariCP connection pooling, Flyway migrations, and repository pattern.

Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing.

Laravel architecture patterns, routing/controllers, Eloquent ORM, service layers, queues, events, caching, and API resources for production apps.

Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.

Verification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.

Modern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable Perl applications.

Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.

Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.

Example project-specific skill template based on a real production application.

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.

Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.

Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

A comprehensive verification system for Claude Code sessions.

Default method for ANY web search, web research, or "find the best tools/libraries/papers/prior-art" task — including Donny research phases and donny-plan-phase. Use browser-harness (real Chrome, beats blocks/logins) plus the multi-source scrapers in ~/.claude/scrapers. Prefer this over WebSearch/WebFetch for anything beyond a trivial single-fact lookup.