Dev & Engineering Claude Skills — Page 12
TAO Platform Execution SDK
Submit, monitor, and manage NVIDIA TAO GPU training jobs across supported platforms.
Expo App Clip Builder
Configure an iOS App Clip for an Expo app and launch it from web URLs.
Expo Data Fetching
Practical networking guidance for Expo apps, covering API calls, caching, offline behavior, and authentication.
Spec-Driven Development
Turn ambiguous engineering requests into testable specifications before coding.
Context Engineering Fundamentals
Understand and shape reliable agent context through attention budgets, context-window mechanics, and signal-density principles.
Latent Briefing
Share task-relevant orchestrator state with workers through task-guided KV-cache compaction when the inference runtime is controllable.
Multi-Agent Architecture Patterns
Design multi-agent systems with context isolation, explicit handoffs, coordinated execution, and controlled failure handling.
ce-debug: Systematic Bug Diagnosis & Fix
Systematically trace root causes of bugs, diagnose before fixing, and produce regression tests.
Loop Library
Guide AI agents to discover, find, audit, craft, run, and improve bounded, repeatable workflows.
Chained PR Splitter
Break oversized PRs over 400 lines into chained, reviewable pull requests to preserve reviewer focus.
Vibeyard: Add npm Dependency Skill
A project-specific playbook for adding npm dependencies to an Electron app with three build targets, preventing silent breakage of CSS, native modules, and the renderer bundle.
SPARV Five-Phase Workflow
A Specify→Plan→Act→Review→Vault workflow with external memory files that pushes vague requirements through to verifiable delivery in one pass, instead of coding on assumptions.
RenderCV PR Reviewer
Reviews GitHub pull requests against RenderCV's codebase standards, architecture, and test requirements, then posts a structured review.
Orient — Repo Orientation Generator
Generates a repo-specific orientation.md so newcomers build a high-level mental model of an unfamiliar codebase without reading it line by line.
Hugging Face CLI Skill
Lets your AI assistant run Hugging Face Hub operations in the terminal — model downloads, uploads, repo management, cache cleanup, and cloud GPU jobs.
SwarmVault
The local-first LLM Wiki toolchain: compile docs, code, transcripts, and URLs into a durable markdown vault, knowledge graph, and retrieval index — all on disk and auditable.
CCM — Claude Code Manager
A pure-Bash CLI toolkit for Claude Code: multi-account switching, session cleanup, environment snapshots, token analytics, and health checks in one tool.
Marmite Static Site Generator Skill
A skill for a zero-config Rust static site generator that turns a folder of Markdown into a complete blog, letting an AI agent manage the full build-author-publish workflow.
cmux-capture: Screenshot and Record cmux Windows
Capture screenshots or recordings of a cmux window from the CLI to supply real evidence for PRs, bug reports, and visual verification — with no screen recording permission required.
cmux Customization
A skill for safely customizing the cmux terminal: edit cmux., Dock config and Ghostty preferences to tailor actions, layouts, shortcuts and notifications without breaking existing config.
cmux Review — Pre-merge Agent Code Review
Reviews agent-written code changes before merge, using an independent review subagent to surface correctness defects and evidence-based verification, while suppressing style noise.
text-to-cad SDF Skill
Lets your agent author, validate, and visually review SDFormat robot models and worlds, handing them off cleanly to simulators like Gazebo.
step.parts Catalog Skill
Give your agent the ability to search the step.parts hosted catalog and download real off-the-shelf STEP parts — screws, bearings, motors, servos — instead of sketching crude placeholder geometry.
Executing Plans
Turn a written implementation plan into verified, checkpointed development work.