Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Fix Sphinx linkcheck failures in Mir docs: disambiguate ambiguous internal links, replace stale external anchors, add known 403-only URLs to linkcheck_ignore, and verify with doc-clean-doc, doc-html, doc-linkcheck targets.
Run NES ROMs in the Mesen2 emulator to debug runtime behavior. Use this skill whenever the user wants to run a ROM and inspect what actually happens at runtime: read NES memory (RAM, palette, nametable, OAM), dump CPU/PPU/APU state after N frames, capture the screen buffer, compare runtime behavior between two ROMs, or verify that a sample displays correctly. Also use when the user says things like "run the ROM", "what does the screen look like", "check the palette", "inspect nametable", "read zero page", "dump memory", or "the ROM doesn't display correctly". This is the dynamic/runtime counterpart to nes-rom-debug (which does static binary analysis).
Disassemble and debug NES ROM files (.nes) produced by the dotnes transpiler. Use this skill whenever the user wants to disassemble a .nes ROM, inspect 6502 machine code, compare two NES ROMs side-by-side, debug transpiler output, investigate byte differences between a cc65 reference ROM and a dotnes ROM, or understand what 6502 instructions the transpiler emitted. Also use when the user mentions disasm, disassembly, PRG ROM, ROM bytes, NES addresses, or wants to look at the hex/binary output of a build. Even if the user just says something like "the ROM looks wrong" or "what did the transpiler emit", this skill applies.
Benchmarking and performance auditing for the Wax repo. Use when running or interpreting Wax benchmarks, diagnosing CPU, memory, or I/O bottlenecks, or investigating Swift 6.2 concurrency issues such as Sendable, actor isolation, `@unchecked Sendable`, task-group fan-out, and data races.
Use when the user asks to review GitHub pull requests, identify concrete risks, and write review comments with `gh`. Focus on actionable findings, not summaries.
Detect drift between a documentation property and its source code, classify each finding (Confirmed / Tracked / Upcoming / Intentional / Needs-eng- confirmation), and draft held DOCSP tickets for confirmed drift only. Runs against any property given a manifest (docs source, code repo(s)). Use when a docs engineer wants an accuracy/drift check of a property against its source. Trigger phrases: "check docs drift", "accuracy report", "docs vs source audit", "find documentation drift", "drift check".
Audit, upgrade, and maintain Grove test suites. Use when the user asks to "audit the test suite", "find untested examples", "upgrade dependencies", "check suite health", "find dead code", "clean up the test suite", "maintain Grove", "what examples are missing tests", or wants to analyze and improve the overall health of a Grove test suite.
Migrate existing untested code into the Grove test suite. Use when the user asks to "migrate this code", "convert to Grove", "make this testable", "move this example to the test suite", "add tests for this existing code", "migrate the code on this page", or wants to convert documentation code examples that currently live outside of Grove into properly tested, snippeted examples. Supports both page-level migration (scan an RST page for all code) and snippet-level migration (convert a single code block).
Create or fix tests for existing Grove code examples. Use when the user asks to "add a test", "create a test", "fix this test", "update the test", "the test doesn't match the output", "test is failing", or wants to add test coverage for an existing example or fix a broken test.