UtsavBalar1231

Runtime debugging loop, reproduce, form ranked hypotheses, instrument, fix, verify. Use for crashes, wrong output, intermittent failures, race conditions, or anything that works locally but not in prod. Triggers: "debug this", "why is this failing at runtime", "intermittent failure", "race condition", "works locally but not in prod", "flaky test", "silent failure". NOT for build failures, type errors, or toolchain issues; those belong to the hephaestus flow. This skill owns runtime misbehavior only.

Strip AI-generated code slop from changed files: double-guards, dead fallbacks, redundant re-validation, narrating comments, speculative flexibility, premature abstraction, and more. Each category pairs with a KEEP rule and a trust-boundary proof requirement, so cleanup never strips load-bearing validation or error handling. Triggers: 'remove ai slop', 'clean up generated code', 'de-slop', 'remove defensive clutter', 'strip ai slop', 'clean up ai-generated code'.

Designer-turned-developer who crafts stunning UI/UX even without design mockups. Use for UI components, styling, layout, animations, and visual design work.

MUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.

Configure ~/.claude/ for oh-my-claudeagent (deps check, block injection, settings, statusline).

Create a detailed context summary for seamless continuation in a new session.

Consolidate agent project memories and notepad learnings into a unified summary

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows.

Use when reviewing code for AI-generated quality issues, detecting patterns of low-quality AI output, or auditing codebases with significant AI-assisted development. Provides systematic detection, prevention, and remediation strategies with human oversight and CI/CD integration. Triggers on "AI-generated code", "code quality", "AI slop", "review code", "detect AI patterns", "audit codebase", "quality issues", "slopsquatting", "hallucinated packages".

Expert Debian package builder specializing in git-buildpackage, debhelper, and Debian Policy compliance. Use for .deb packaging, debian/ directory work, dpkg operations, and package maintenance. Triggers on "Debian", ".deb", "dpkg", "debhelper", "gbp", "pbuilder", "lintian", "dch".

Interactive wizard for creating custom Claude Code skills. Use when the user wants to create a new skill, write a skill, build a custom capability, or asks how to make a skill. Guides through requirements, validation, and best practices. Triggers on "create skill", "help me write a skill", "make a skill".

Use when creating well-structured, conventional git commits from code changes. Triggers after completing work, before pushing changes, or when organizing unstaged/staged changes into meaningful commits. Triggers on "commit", "git commit", "create commit", "stage changes", "conventional commits", "commit message", "atomic commits".

Use when needing expert Linux kernel development assistance for device drivers, kernel modules, subsystems, and system programming. Triggers on "Linux kernel", "device driver", "kernel module", "kernel development", "system programming", "DMA", "interrupt handler", "device tree", "platform driver".

Stage, unstage, split, and commit changes at file, hunk, or line granularity through the pgs MCP server, and build clean atomic commits with well-formed messages. Use whenever work involves staging or committing in a git repo — e.g. "commit just this function", "split this messy diff into separate commits", "stage only the bug fix, not the debug prints", "unstage that file", "amend the last commit message", or turning a mixed working tree into atomic commits. Prefer it over raw git or `git add -p`, which needs a TTY that agents lack.

Provides Linux kernel development workflows, checklists, and guardrail scripts covering driver APIs, debugging, tracing, devicetree, patch submission, and CI triage. Use when working on Linux kernel or kernel-adjacent changes, including drivers, Kconfig, defconfig, DTS/devicetree bindings, kernel debugging, CI failures, KUnit/kselftest, patch review, maintainer routing, stable/regression fixes, or vendor/LTS kernel maintenance. Also use for RK3576/Lapis vendor kernel work.