nijaru
58 verified skills
second-pass
Use after completing a bug fix, feature, refactor, or tk task when the first implementation taught enough context to replace it with a simpler, cleaner, or more coherent version before finalizing.
development
chezmoi-expert
Use for managing dotfiles, syncing agent skills/config, and handling chezmoi source/destination workflows.
testing
ai-context
Full conventions for the ai/ persistent context system — file roles, index discipline, frontmatter spec, consolidation rules, and DECISIONS.md compaction. Use when operating on ai/ files or enforcing conventions mid-session.
testing
codex
Use ONLY when explicitly asked to invoke or run the Codex CLI tool for agentic review. Do NOT trigger when "codex" appears in conversation as a model name, topic, or reference.
tools
gemini
Use ONLY when explicitly asked to consult or invoke the Gemini CLI tool for a second opinion. Do NOT trigger when the word "gemini" appears in conversation as a model name or topic.
tools
gitbutler-expert
Use when the user asks for GitButler, the `but` CLI, virtual branches, stacked branches, multi-branch workspaces, GitButler PRs, or GitButler history editing.
tools
mojo-python-interop
Aids in writing Mojo code that interoperates with Python using current syntax and conventions. Use this skill in addition to mojo-syntax when writing Mojo code that interacts with Python, calls Python libraries from Mojo, or exposes Mojo types/functions to Python. Also use when the user wants to build Python extension modules in Mojo, wrap Mojo structs for Python consumption, or convert between Python and Mojo types.
tools
new-modular-project
Creates a new Mojo or MAX project. Use when wanting to start a new Mojo or MAX project, initializing the Pixi or UV environment to use Mojo or MAX, or when the user wants to begin a new Mojo or MAX project from scratch.
tools
hf-cli
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.
tools
writer
Use when reviewing or revising text (prose, docs, commits) to remove AI patterns and improve voice/clarity.
documentation
sg
Use when searching or replacing code structures (functions, calls, blocks) across a codebase using tree-sitter patterns instead of regex.
development
systems-expert
Use when designing or implementing performance-critical, safety-critical, or real-time systems requiring Tiger Style, Mechanical Sympathy, or Data-Oriented Design principles.
testing
nu-data
Use when about to reach for jq, awk, or a Python one-liner to query, filter, or transform structured data (JSON, CSV, TOML, NDJSON, Parquet).
development
github-actions-workflows
Use when writing, auditing, or fixing GitHub Actions workflows for CI, release, or deployment. Trigger on new workflow creation, auditing existing ones, or debugging pipeline failures and incidents.
development
git-expert
Use when performing complex git operations, semantic diffs with `sem`, entity-level merges with `weave`, or GitHub CLI (`gh`) tasks beyond basic commits.
tools
save
Use when persisting session state before compaction, session handoff, or completion of substantial work in a repo that already uses ai/ context or tk tasks.
data-ai
autoresearch
Use when setting up, documenting, or running an autonomous experiment loop with a fixed evaluation harness, a narrow edit surface, and keep-or-revert iteration; especially for karpathy/autoresearch-style overnight model tuning.
testing
bun-expert
Use when writing, testing, or managing dependencies in a Bun-based JavaScript/TypeScript project.
development
cmake-expert
Use when writing, debugging, or structuring CMake build systems for C++, JUCE, or mixed-language projects. Covers modern target-based CMake, presets, FetchContent, and Ninja backend.
development
cpp-expert
Use when needing idiomatic, high-performance C++ (C++23 baseline, C++17/20 compatibility notes) guidance. Covers the modern "safe subset", RAII, error handling, tooling, and cross-language interop.
tools
creating-skills
Use when creating, modifying, or testing AI agent skill definitions (.md files) to ensure they are high-performance, compact, and verified.
testing
elixir-expert
Use when needing idiomatic, high-performance Elixir (v1.18+) guidance for distributed systems, Phoenix applications, or Nerves-based embedded logic.
tools
fish-expert
Use when adding or modifying Fish shell functions, abbreviations, aliases, or config that must also be mirrored in Nushell.
tools
git-history-purge
Use when purging sensitive data, large files, or private content from the full git history.
data-ai
git-local-exclude
Use when keeping files local but out of git history (e.g., ai/, .tasks/, secrets). Use for removing files from git history while retaining them on disk without leaking patterns to .gitignore.
data-ai
gleam-expert
Use when needing idiomatic, high-performance Gleam (v1.x) guidance for type-safe functional programming on Erlang or JavaScript targets.
development
go-expert
Use when needing idiomatic, high-performance Go (v1.26) guidance for system-level logic, SIMD-accelerated algorithms, or memory-mapped storage engines.
development
handoff
Use when generating or updating a handoff document to transition the session to another agent or TUI. DO NOT trigger when the user says "read the handoff", "load the handoff", or "here's the handoff"—handle those as plain file reads.
documentation
huggingface-community-evals
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
tools
huggingface-datasets
Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
development
huggingface-gradio
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
development
huggingface-llm-trainer
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
development
huggingface-paper-publisher
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
data-ai
huggingface-papers
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
development
huggingface-tool-builder
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
tools
huggingface-trackio
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.
tools
huggingface-vision-trainer
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
development
hyperfine
Use when benchmarking CLI tools or scripts instead of time — measuring performance, comparing implementations, or tracking regressions with statistical validity.
tools
jb
Use when running commands expected to take several minutes or more (dev servers, large builds, full test suites).
development
juce-expert
Use when building JUCE 8 audio plugins or applications. Covers AudioProcessor lifecycle, APVTS, DSP module, CMake setup, real-time safety rules, and plugin format targets.
tools
mojo-gpu-fundamentals
The basics of how to program GPUs using Mojo. Use this skill in addition to mojo-syntax when writing Mojo code that targets GPUs or other accelerators. Use targeting code to NVIDIA, AMD, Apple silicon GPUs, or others. Use this skill to overcome misconceptions about how Mojo GPU code is written.
development
prune
Use when cleaning up workspace clutter, organizing the ai/ directory, or removing stale task files. Trigger on root directory sprawl, outdated ai/ documents, or redundant temporary scripts.
documentation
python-expert
Use when needing idiomatic, high-performance Python (3.14+) guidance using the Astral stack (uv, ruff, ty).
development
refactor
Use when improving existing code structure while preserving behavior; trigger on complex functions, deep nesting, duplication, unclear names, or technical debt that does not require changing the design.
development
repo-hooks
Use when setting up, auditing, or troubleshooting repo-local Git hooks, formatter checks, or bootstrap commands across repositories.
development
research
Use when researching unfamiliar patterns, evaluating tools or libraries, comparing approaches, or answering "what's the best way" questions with web, docs, and code search.
tools
review
Use when performing deep code analysis for correctness, safety, quality, or to simplify recently modified code. Trigger on feature completion, unpushed commits, or before merging significant changes.
development
rewrite
Use when evaluating whether a project, feature, module, or component should be replaced by a ground-up design before implementation; trigger when incremental fixes seem structurally inadequate.
documentation
rust-expert
Use when needing idiomatic, high-performance Rust (Edition 2024, 1.93+) guidance for systems logic, async services, or performance-critical libraries.
development
setup-ai
Use when initializing or migrating AI agent context management (AGENTS.md, ai/ structure) for a project. Run on new repos to scaffold, and on existing repos to audit, consolidate, and migrate to current conventions.
testing
sprint
Use when a project spec or design doc exists and needs breaking down into demoable sprints and atomic tasks.
documentation
Use when fetching X/Twitter post content by URL, or searching for recent X posts.
content-media
zig-expert
Use when writing, migrating, or reviewing Zig code across recent stable versions (0.14-0.16), especially to correct stale syntax or stdlib, build.zig, allocator, formatting, or runtime API knowledge.
development
bubbletea
Use when writing, debugging, or migrating Bubbletea v2 TUI applications in Go. Covers inline mode, scrollback output, key handling, tea.View, and v1→v2 breaking changes.
development
git-commit
Use when writing git commit messages to enforce consistent format and quality.
development
jj
Use when a repository contains `.jj/`, when the user asks to use Jujutsu/jj, or when recovering/inspecting jj operation history.
data-ai
transformers-js
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.
development
mojo-syntax
Help to write Mojo code using current syntax and conventions. Always use this skill when writing any Mojo code, including when other Mojo-specific skills (e.g., mojo-gpu-fundamentals) also apply. Use when writing Mojo code, translating projects to Mojo, or otherwise generating Mojo. Use this skill to overcome misconceptions with how Mojo is written.
development