#developer-tools
690 resources · page 2 of 12
Results
- agents-generator
Generate project-specific AGENTS.md and companion rules by analyzing a codebase.
- physicsnemo-shard-tensor
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or…
- tao-port-huggingface-model
Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).
- lab:autoresearch
Self-improving loop for plugin skills.
- manim-video
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if…
- openclaw-persona-forge
The publisher’s description is only a heading. Open the skill to read what it does.
- videodb
See, Understand, Act on video and audio.
- aihot
The publisher’s description is only a heading. Open the skill to read what it does.
- hv-analysis
The publisher’s description is only a heading. Open the skill to read what it does.
- neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the…
- storage-analyzer
The publisher’s description is only a heading. Open the skill to read what it does.
- citation-verification
This skill provides reference guidance for citation verification in academic writing.
- skill-quality-reviewer
A meta-skill for evaluating the quality of Claude Skills.
- coding-agent-sessions
MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, OpenCode,…
- data-scientist
Expert data processing specialist with intelligent DuckDB/Polars selection for maximum performance.
- frontend
MUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, performance audits, visual QA, taste, and…
- ulw-plan
ACTIVATES ONLY on an explicit user request for the ulw-plan workflow: the user themselves saying ulw-plan, ulw plan, /skill:ulw-plan, or…
- visual-qa
MUST USE after building/changing any UI or when asked whether a page, component, or TUI looks right.
- accelerated-computing-cudf
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable…
- deepstream-import-vision-model
When this skill is active, read the relevant reference document before starting each phase.
- dynamo-interconnect-check
After dynamo-recipe-runner deploys a disagg or multi-node recipe.
- dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes.
- dynamo-router-starter
Start or patch Dynamo router modes and run router endpoint smoke checks.
- dynamo-troubleshoot
Diagnose failed or unhealthy Dynamo deployments.
- hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit.
- zotero-obsidian-bridge
Use this skill when Zotero is the literature source of truth and the project KB should receive source notes under Sources/Papers plus…
- j-space
This is the entry. Everything else in this skill is read from here, on demand.
- repo-harness
Route explicit repo-harness setup, planning, execution, verification, and handoff actions through deterministic repository state
- architecture-design
Use only when creating new registrable ML components that require Factory or Registry patterns.
- synthetic-market-research
An installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI…
- expression-skill
This skill should be used when the user asks for efficient communication, task reports, file-operation summaries, research discussion,…
- nature-writing
Draft, restructure, or plan Nature-style manuscript sections from author-provided claims, results, figures, notes, or Chinese drafts.
- paper-self-review
A systematic paper quality checking tool that helps researchers conduct comprehensive self-review before submission.
- post-acceptance
A post-acceptance conference preparation workflow that helps researchers efficiently complete presentations, posters, and promotional content.
- research-ideation
Supports the complete workflow for the research project initiation phase, from vague idea to a traceable research contract: research question, hypothesis, evidence needs, falsification criteria, method selection, and next action.
- results-analysis
Run strict, evidence-first experimental analysis for ML/AI research.
- results-report
Write the complete post-experiment summary report after analysis artifacts are ready.
- verification-loop
A comprehensive verification system for Claude Code sessions.
- writing-anti-ai
Remove AI-generated writing patterns from text to make it sound natural and human-written.
- skill-comply
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents,…
- autoresearch-loop
Domain-agnostic metric-driven improvement loop, generalizing Karpathy's autoresearch.
- frontend-dev
Full-stack frontend development combining premium UI design, cinematic animations, AI-generated media assets, persuasive copywriting, and visual art.
- minimax-xlsx
Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv).
- init
Bootstraps a project for Claude Code — generates CLAUDE.md and scoped docs from detected structure (single project, monorepo, or multi-repo…
- latex-document
Universal LaTeX document skill: create, compile, and convert any document to professional PDF with PNG previews.
- elves
Autonomous multi-batch development agent for long unattended runs, reviewed-PR landing, Cobbler-first orchestration, and optional Fugu, Manus, Grok,…
- oma-slide
HTML presentation deck generator and multi-format exporter.
- sloptrim
Trims AI slop from text. Works a catalogue of 71 patterns: 62 machine-checked by scripts/detect.py, 9 requiring semantic judgment during the rewrite. Of the 62, 50 can move the score; the rest are reported as writing advice and count for
- okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read.
- overleaf
Sync and manage Overleaf LaTeX projects from the command line.
- oma-orchestration
Automated multi-agent orchestration that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress.
- obsidian-project-kb-core
Use this as the main Claude Scholar skill for a vault-first, project-scoped Obsidian research knowledge base rooted at…
- oma-design
Defining or revising a project design system - Creating or auditing DESIGN.md - Selecting typography, color, layout, motion, or component…
- brain-page
Operating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI;…
- prompt-sensei
Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents…
- continuous-learning
[DEPRECATED - use continuous-learning-v2] Legacy v1 stop-hook skill extractor.
- council-multi-model
Add one optional external Codex critique after the existing council has produced a decision draft.
- delivery-gate
Stop hook that blocks Claude from finishing until quality checks pass.
- ios-icon-gen
Generate iOS app icons as PNG imagesets for Xcode asset catalogs from SF Symbols (5000+ Apple-native) or Iconify API (275k+ open source icons from 200+…
- ito-baskets
Read-only Itô basket and prediction-market data skill.
