maintaining-claude-code
Validate and improve Claude Code configurations (CLAUDE.md, skills, commands, hooks). Use when auditing config quality, checking skill discoverability, organizing .claude directory, or deciding which entity type to use.
book-reader
Read and search digital books (PDF, EPUB, MOBI, TXT). Use when answering questions about a book, finding quotes or passages, navigating to specific pages or chapters, or extracting information from documents.
git-workflow
Handle squashing multiple commits and rebasing feature branches safely. Use when consolidating commits into a single commit, or rebasing feature branches onto updated development branches. Falls back from jj when not available.
Linear CLI
Query, create, and manage Linear issues from the command line. Use when checking assigned work, viewing issue details, creating new issues, or updating issue status.
Skill Builder
Create and validate Agent Skills with proper structure and effective descriptions. Use when building custom skills, testing skill discovery, or designing new skill workflows.
jj-workflow
Jujutsu (jj) version control, load skill when hook output shows vcs=jj-colocated or vcs=jj in the system-reminder.
claude-code-web-docker
Set up and use Docker in Claude Code for Web environments. Use when Docker builds fail with bridge/iptables errors, SSL certificate errors through proxy, or when working in containerized web environments.
cuda-kernel-refine
|
glhf
Search Claude Code conversation history to find past solutions, recall commands, and discover related work. Use when looking for previous implementations, finding commands you ran before, or exploring what was done in past sessions.
notion-formatter
Format markdown content for Notion import with proper syntax for toggles, code blocks, and tables. Use when formatting responses for Notion, creating Notion-compatible documentation, or preparing markdown for Notion paste/import.
qwen3-tts-profile
|
svelte5
Svelte 5 syntax reference. Use when writing ANY Svelte component. Svelte 5 uses runes ($state, $derived, $effect, $props) instead of Svelte 4 patterns. Training data is heavily Svelte 4—this skill prevents outdated syntax.
SwiftUI Engineer
Build, review, debug, and modernize SwiftUI apps for macOS with modern patterns. Use when building SwiftUI UIs, reviewing code quality, debugging view issues, checking anti-patterns, migrating from AppKit, or designing app architecture.
whisper-test
|
analyzing-wav
Analyze WAV audio files for debugging TTS and audio pipelines. Use when checking audio quality, validating WAV format, inspecting waveform patterns, or diagnosing generated speech issues.
building-swiftui
Build, review, debug, and modernize SwiftUI apps for macOS with modern patterns. Use when building SwiftUI UIs, reviewing code quality, debugging view issues, checking anti-patterns, migrating from AppKit, or designing app architecture.
cleaning-commit-history
Reorganize and clean up messy commit history on a feature branch into logical, reviewable commits. Use when cleaning up commits, preparing a branch for review, separating formatting from logic changes, fixing broken intermediate states, or squashing WIP commits.
committing-changes
Stage, validate, and commit changes with a clear message, optionally pushing to remote and monitoring CI. Use when committing code, creating a commit, pushing changes, or doing a commit-and-push workflow.
configuring-tmux
Build, review, and troubleshoot tmux configurations with modern best practices. Use when creating tmux.conf from scratch, adding plugins, configuring themes, integrating with Neovim, setting up session management, or debugging tmux issues.
cuda-kernels
Develop, test, and optimize custom CUDA kernels in the candle framework for qwen3-tts-rs. Use when writing CUDA kernels, debugging GPU code, integrating kernels with candle, optimizing throughput, profiling with nsys/ncu, analyzing roofline, or investigating register pressure and occupancy.
downloading-hf-models
Get the correct command syntax for downloading models from HuggingFace. Use when downloading models, running "hf download", or pulling models from HuggingFace repos.
executing-test-plans
Execute a structured test plan and emit a concise, comprehensive results document (JSON + Markdown). Use when running test plans, executing QA workflows, verifying acceptance criteria systematically, or producing test results documentation.
implementing-issues
Implement a GitHub or Linear issue end-to-end with TDD, branch management, and PR creation. Use when implementing an issue, working on a ticket, starting a feature from an issue, or building from issue requirements.
maintaining-claude-code
Create, validate, and improve Claude Code configuration — SKILL.md files, CLAUDE.md, rules, hooks, and settings.json. Use when creating a new skill, writing a SKILL.md, adding a hook, editing rules, auditing skill descriptions, checking config quality, debugging hook behavior, or deciding between skills vs rules vs CLAUDE.md. Also auto-loads when working in ~/.claude/ on skills, rules, hooks, or settings.
managing-dotfiles
Manage dotfiles tracked in ~/.claude/dotfiles/ using GNU Stow. Use when adding config files to dotfiles, stowing/unstowing packages, or troubleshooting symlink conflicts.
managing-starship-fork
Sync, build, and install the custom starship fork with jj support. Use when updating starship, rebuilding the binary, syncing with upstream, or modifying the jj_status module.
monitoring-ci
Monitor and watch GitHub Actions CI/CD pipeline runs in real time. Use when the user has pushed code and wants to watch the build, check CI status, see if tests passed, monitor a pipeline, or wait for a workflow run to complete. Also use after any `jj git push` or `git push` command. Reports pass/fail with failed job logs. Do NOT use for writing or editing CI workflow YAML files, optimizing CI config, or debugging CI configuration — only for monitoring active runs.
profiling-qwen3-tts
Profile and benchmark qwen3-tts-rs inference using e2e_bench with chrome tracing, flamegraph, or Nsight Systems inside a CUDA Docker container. Use when profiling, benchmarking, checking performance, finding bottlenecks, or running flamegraphs.
reading-books
Read and search digital books (PDF, EPUB, MOBI, TXT). Use when answering questions about a book, finding quotes or passages, navigating to specific pages or chapters, or extracting information from documents.
reviewing-pull-requests
Review a pull request against issue requirements and coding best practices, then submit structured feedback. Use when reviewing a PR, checking a pull request, doing code review, or providing PR feedback.
searching-history
>-
specifying-and-planning
Multi-mode skill for project planning workflows -- extract requirements from specs, break into tasks, create GitHub issues, set up project boards, or generate agent team configurations. Use when planning a project, extracting requirements, breaking down tasks, creating issues from tasks, setting up GitHub projects, or generating team plans.
testing-whisper
Transcribe WAV audio files using OpenAI Whisper for intelligibility testing. Use when transcribing audio, testing speech output quality, running whisper, or checking if generated audio is intelligible.
using-docker-in-web
Set up and use Docker in Claude Code for Web environments. Use when Docker builds fail with bridge/iptables errors, SSL certificate errors through proxy, or when working in containerized web environments.
using-git
ALWAYS load this skill when the user mentions ANY of these git topics — squash, rebase, cherry-pick, merge conflicts, conflict resolution, reflog, recovering lost commits, resetting commits, pre-commit hooks, or fixing broken git state. This skill contains safe, non-interactive git approaches that must be preferred over default git commands. Trigger for squashing commits, rebasing onto main/dev/master, cherry-picking from another branch, resolving rebase conflicts, recovering commits after reset, reflog to find lost work, accidentally committed to wrong branch, pre-commit hook modified files, non-interactive squash before PR, cleaning up commit history, consolidating commits, force push after rebase, or bad reset recovery. Load this skill for ANY git workflow involving history rewriting, commit manipulation, or branch rebasing — even if the request seems straightforward.
using-jina-reader
Fetch web page content using Jina Reader as a fallback when websites block direct access. Use when WebFetch returns 403, 406, captcha pages, empty content, Cloudflare blocks, or anti-bot responses. Also use when the user explicitly asks to use Jina Reader.
using-jj
Use this skill for ANY task involving jj or jujutsu version control. ALWAYS trigger when the user mentions jj, jujutsu, revsets, change IDs, bookmarks, or oplog. Also trigger when the user wants to squash, split, or reorder commits in a stack, write a revset query, absorb fixup changes, undo or restore a previous operation, resolve conflicts after rebasing, recover from force-pushes, rewrite protected/immutable commits, view change evolution (evolog), or try parallel approaches. Trigger even if "jj" is not explicitly said — "changes" instead of "commits", "stack" instead of "branch", "absorb", "squash into the right commit", "undo my last operation", "conflict after rebase", or "compare approaches in parallel" are strong jj signals. This skill contains critical non-obvious rules (like always using -m flags) that prevent broken workflows.
using-linear
Query, create, and manage Linear issues from the command line. Use when checking assigned work, viewing issue details, creating new issues, or updating issue status.
validating-project
Auto-detect and run formatters, linters, type checkers, and tests for the current project. Use when validating a project, running all checks, checking code quality before committing, or verifying the build passes.
writing-svelte5
Svelte 5 syntax reference. Use when writing ANY Svelte component. Svelte 5 uses runes ($state, $derived, $effect, $props) instead of Svelte 4 patterns. Training data is heavily Svelte 4—this skill prevents outdated syntax.