Agent skills for Claude Desktop

Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system.

Generate milestone test reports and build verification reports with pass rates.

Use this skill to test strategy changes against a fresh test repository.

Use when running tests, reporting failures, or diagnosing broken suites.

Verify working-tree changes against an 8-tier test pyramid.

Provides guidelines for writing test code for Unity projects.

How to write tests, when to use each type of test, and how to run them.

Audit or plan a single-player falling-tetromino implementation against an explicit historical gameplay baseline covering field geometry…

Transforms unstructured text and articles into structured SVG logic diagrams optimized for WeChat Official Accounts and social publishing.

Translates selected text or prompt content between Japanese and English while strictly preserving formatting, links, and code structures.

Manage Telegram channel access — approve pairings, edit allowlists, set DM/group policy.

Refresh GME's Thailand remittance rate-comparison report — fetches live competitor quotes (Cross, SBI, JRF, E9Pay, GmoneyTrans, Coinshot…

Instruments code so production behavior is visible and diagnosable.

Collaboratively design, implement, review, and refine software features with a human developer using an iterative pair programming workflow.

Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both.

Use when executing implementation plans with independent tasks in the current session

Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece…

Stop. That last message did not land: re-pitch it.

Use when designing a migration — graceful transition where the old interface stays as a thin stub/proxy/shim, real implementation moves…

Use when building features with TCA (The Composable Architecture), structuring reducers, managing state, handling effects, navigation, or…

Intelligent fix-loop for Playwright e2e suites with failing or skipped tests.