Provides targeted, evidence-driven guidance for fixing and testing Linux kernel code. It helps the agent classify kernel failures, pick the smallest relevant reference, propose minimal patches, and verify results with concrete commands and expected signals. Typical outputs include a short diagnosis, a minimal patch sequence, and a verification step with expected logs or behaviors.
Best used by code-capable assistants with shell access and build tooling (Copilot/Codex-like agents, Claude Code, or other code-capable LLMs) that can run build/test commands and read logs.
This skill has not been reviewed by our automated audit pipeline yet.
Write-Skill: AI Writing Cleanup
Edit and rewrite text to remove AI-generated patterns and make prose sound more natural and human.
Modern C Makefile
Generate, analyze, or improve Makefiles for modern C/C++ projects using a tested gnaro-based template to add compilation, testing, linting, formatting, and depe
HM Fetch Skill (HarmonyOS Docs)
Fetch and convert Huawei HarmonyOS developer documentation via the documentPortal API, converting HTML to Markdown and maintaining a local-first migration refer
CS Course Systematic Study
Produce a structured, in-depth learning report for a CS course from its syllabus, lectures, and readings.
HarmonyOS Linux CLI Developer
Command-line workflows and scripts for building, packaging, installing, debugging HarmonyOS apps on Linux.