Rafał Araszkiewicz
Community@Arasz · Poland
Fullstack developer from Poland. .NET (C#) enthusiast and expert. Cloud explorer. Security focused. Architecture connoisseur. AI tamer.
Agent Skills by Rafał Araszkiewicz
Showing 103 vetted skills indexed across 2 GitHub repositories.
Araszauto-wm
Auto-approves Claude Code tool calls within time-boxed, project-scoped windows via PreToolUse hooks.
Araszdotnet-logger-message-design
Designs and tests high-performance LoggerMessage logging in .NET with FakeLogger assertions.
Araszdotnet-domain-modeling
Implements immutable C# domain models with sealed records, guards, and pure-domain TDD.
Araszarchify
Generate validated interactive HTML diagrams from typed JSON specifications.
Araszspec-driven-refactoring
Guides large codebase refactors through spec writing and two review gates.
Araszcomplete-project-scope-code-review
Orchestrates parallel expert lanes to review an entire codebase and deliver verified findings, plans, and merges.
Araszdocumentation-drift-audit
Audit documentation claims against actual code and fix only verifiably false statements.
Araszmulti-lane-report-assembly
Merges parallel research lane outputs into one evidence-graded findings report.
Araszmcp-index
Indexes MCP server tools with tags and intents to recommend relevant tools per prompt.
Araszdocumentation
Routes documentation tasks to scaffold, update, or migrate skills via manifest.json.
Araszdotnet-workload
Routes .NET workload tasks to one of eleven specialized dotnet skill guides.
Araszcode-review-evidence
Verifies code review claims and test evidence against upstream sources and real data stores.
Araszowner-gate-review
Generates HTML review forms that bind reviewer verdicts to individual design decisions.
Araszprompt-markers
Detects prompt prefix markers and injects matching behavior instructions via a UserPromptSubmit hook.
Araszsemantica-knowledge-graph
Record decisions and trace causal chains in a session-scoped knowledge graph.
Araszreview-tests
Reviews existing test suites against a shared ruleset and returns findings without editing code.
Araszsqlite-bank-space-diagnosis
Diagnose SQLite database and WAL file bloat using read-only space analysis and checkpoint quantification.
Araszsqlite-schema-review
Reviews SQLite schema and migration changes by verifying semantics claims against a scratch database.
Araszdebug-issue
Trace call chains from symptom to entry point before proposing bug fixes.
Araszsend-message
Send messages between agent sessions through a machine-wide SQLite message bus.
Araszrefactor-safely
Previews, applies, and verifies code renames, extractions, and removals with full reference enumeration.
Araszexplore-codebase
Orient in an unfamiliar codebase by tracing entry points, modules, and one end-to-end path.
Araszcommit-reminder
Detects accumulating uncommitted git changes and commands a commit via a PostToolUse hook.
Arasztest-economy
Counts full-suite test runs per session and nudges when they exceed the budget.
Frequently Asked Questions About Rafał Araszkiewicz
FAQPage SchemaWhat tasks can I accomplish with Arasz's skill collection?▼
You can model DDD domain layers in C#, run spec-driven refactors across 5+ files, execute whole-project adversarial code reviews, design and audit tests, diagnose flaky xunit suites, review SQLite schemas and WAL bloat, publish NuGet packages, and coordinate parallel agents via git worktrees and a message bus.
Who is the target audience for these skills?▼
Senior .NET/C# engineers, fullstack developers, and technical reviewers who need disciplined, evidence-first practices. The skills suit engineers running TDD, BDD with Reqnroll, BackgroundService reviews, and teams orchestrating multiple concurrent coding sessions with isolation and review gates.
How are the skills installed and executed?▼
Skills are folder-based packages with YAML frontmatter (name, description, version, platforms) loaded by compatible agent runtimes such as Hermes Agent or ai-badger. Most run cross-platform on Linux, macOS, and Windows; gateway skills like dotnet-workload route to specialized members via manifest.json.
Are these skills open source and what do they cost?▼
Yes, the skills are free and open source under the MIT license, as declared in their frontmatter. There is no cost to use, modify, or redistribute them, and the feed-badger skill even supports contributing project-agnostic improvements back to the framework via draft pull requests.
What prerequisites or dependencies do the skills require?▼
Most skills require only a compatible agent runtime and a git repository. .NET-specific skills assume the .NET SDK (verified on .NET 10), xunit.v3, Reqnroll, or SQLCipher/SQLitePCLRaw where relevant. Some orchestration skills depend on the ai-badger configuration in .ai-badger/config.json.