Megatron-LM Base Image Bump
NVIDIA/Megatron-LM
Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up.
Guide to JSON Crack for visualizing complex JSON data structures
$ npx skills add wentorai/research-plugins --skill json-data-visualizer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install wentorai/research-plugins json-data-visualizer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/wentorai/research-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tools/diagram/json-data-visualizer .claude/skills/json-data-visualizer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "json-data-visualizer" agent skill from https://github.com/wentorai/research-plugins/tree/main/skills/tools/diagram/json-data-visualizer into .claude/skills/json-data-visualizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "json-data-visualizer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/wentorai/research-plugins/tree/main/skills/tools/diagram/json-data-visualizerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add wentorai/research-plugins --skill json-data-visualizer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install wentorai/research-plugins json-data-visualizer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wentorai/research-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/tools/diagram/json-data-visualizer .agents/skills/json-data-visualizer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "json-data-visualizer" agent skill from https://github.com/wentorai/research-plugins/tree/main/skills/tools/diagram/json-data-visualizer into .agents/skills/json-data-visualizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "json-data-visualizer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add wentorai/research-plugins --skill json-data-visualizer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install wentorai/research-plugins json-data-visualizer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wentorai/research-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/tools/diagram/json-data-visualizer .cursor/skills/json-data-visualizer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "json-data-visualizer" agent skill from https://github.com/wentorai/research-plugins/tree/main/skills/tools/diagram/json-data-visualizer into .cursor/skills/json-data-visualizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "json-data-visualizer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/wentorai/research-plugins.git --path skills/tools/diagram/json-data-visualizer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add wentorai/research-plugins --skill json-data-visualizer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install wentorai/research-plugins json-data-visualizer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wentorai/research-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/tools/diagram/json-data-visualizer .gemini/skills/json-data-visualizer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "json-data-visualizer" agent skill from https://github.com/wentorai/research-plugins/tree/main/skills/tools/diagram/json-data-visualizer into .gemini/skills/json-data-visualizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "json-data-visualizer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install wentorai/research-plugins json-data-visualizerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add wentorai/research-plugins --skill json-data-visualizer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/wentorai/research-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/tools/diagram/json-data-visualizer .github/skills/json-data-visualizer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "json-data-visualizer" agent skill from https://github.com/wentorai/research-plugins/tree/main/skills/tools/diagram/json-data-visualizer into .github/skills/json-data-visualizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "json-data-visualizer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add wentorai/research-plugins --skill json-data-visualizer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install wentorai/research-plugins json-data-visualizer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wentorai/research-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/tools/diagram/json-data-visualizer .opencode/skills/json-data-visualizer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "json-data-visualizer" agent skill from https://github.com/wentorai/research-plugins/tree/main/skills/tools/diagram/json-data-visualizer into .opencode/skills/json-data-visualizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "json-data-visualizer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
json-data-visualizerGuide to JSON Crack for visualizing complex JSON data structures
JSON Data Visualizer is an agent skill from wentorai/research-plugins. Guide to JSON Crack for visualizing complex JSON data structures
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud. It works with Docker. The repository describes itself as: 350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents. The licence is MIT.
Read from SKILL.md and the folder at commit bf44b3c. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
npmgitdockerFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
github.comapi.crossref.orgjsoncrack.internal.labAlso links to:
jsoncrack.comnpmjs.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
JSON Data Visualizer loads about 2.1k tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 613 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from wentorai/research-plugins at commit bf44b3c, republished under its MIT licence (© wentorai). 613 words, ~2,107 tokens.
.claude/skills/json-data-visualizer/SKILL.md (or your agent's skills folder).JSON Crack (formerly JSON Visio) is an open-source data visualization tool with over 43K stars on GitHub that transforms JSON, YAML, XML, TOML, and CSV data into interactive graph diagrams. Instead of reading raw nested data structures, researchers can instantly see the hierarchical relationships, nested objects, and array structures as a navigable node-link diagram rendered on an infinite canvas.
For academic researchers, JSON Crack is particularly valuable when working with complex API responses, configuration files, experimental metadata schemas, and nested data exports. Bioinformatics researchers dealing with deeply nested gene ontology JSON files, social scientists working with survey platform API responses, and computational researchers inspecting machine learning model configuration files all benefit from being able to see their data structures visually rather than scrolling through thousands of lines of text.
The tool is available as a hosted web application at jsoncrack.com, as a self-hosted Docker deployment for institutional use, and as an embeddable React component that can be integrated into custom research tools. It also provides an API for programmatic access, making it suitable for integration into data processing pipelines.
The fastest way to use JSON Crack is through the web interface. Paste or upload JSON data and the visualization renders immediately.
# Clone the repository
git clone https://github.com/AykutSarac/jsoncrack.com.git
cd jsoncrack.com
# Install dependencies
npm install
# Start development server
npm run dev
# Or build and serve for production
npm run build
npm start# Run with Docker
docker run -d -p 8888:8080 \
--name json-crack \
--restart unless-stopped \
jsoncrack/jsoncrack
# Access at http://localhost:8888version: "3.8"
services:
json-crack:
image: jsoncrack/jsoncrack
container_name: json-crack
ports:
- "8888:8080"
restart: unless-stoppedResearchers frequently work with complex nested JSON structures for experimental metadata. JSON Crack makes these immediately readable.
{
"experiment": {
"id": "EXP-2026-0142",
"title": "Effect of Temperature on Protein Folding Kinetics",
"principal_investigator": {
"name": "Dr. Jane Smith",
"orcid": "0000-0002-1234-5678",
"affiliation": "Department of Biochemistry"
},
"protocol": {
"version": "3.2",
"steps": [
{
"order": 1,
"name": "Sample Preparation",
"duration_minutes": 120,
"equipment": ["centrifuge", "spectrophotometer"],
"parameters": {
"temperature_celsius": 25,
"buffer_ph": 7.4,
"concentration_mm": 0.5
}
},
{
"order": 2,
"name": "Thermal Denaturation",
"duration_minutes": 180,
"temperature_range": {
"start": 25,
"end": 95,
"step": 1,
"unit": "celsius"
}
},
{
"order": 3,
"name": "Data Acquisition",
"instrument": "circular_dichroism_spectrometer",
"wavelength_range_nm": [190, 260]
}
]
},
"samples": [
{
"id": "S001",
"condition": "wild_type",
"replicates": 3,
"measurements": {
"tm_celsius": 68.2,
"delta_h_kcal": -45.3,
"r_squared": 0.997
}
}
]
}
}When loaded into JSON Crack, this structure displays as an interactive tree diagram where each nested object becomes a card node, arrays show their elements as connected child nodes, and researchers can click to expand or collapse sections for focused exploration.
When working with research APIs (PubMed, CrossRef, OpenAlex, etc.), responses are often deeply nested. JSON Crack helps researchers understand the response schema before writing parsing code.
import requests
import json
# Fetch metadata from CrossRef API
response = requests.get(
"https://api.crossref.org/works/10.1038/nature12373"
)
data = response.json()
# Save for visualization in JSON Crack
with open("crossref_response.json", "w") as f:
json.dump(data, f, indent=2)
# Open crossref_response.json in JSON Crack to explore the schema
# This reveals the nested structure of author arrays, funding info,
# reference lists, and license metadataJSON Crack provides a React component that can be embedded in custom research tools.
import { JsonCrackEmbed } from "jsoncrack-react";
import { useState } from "react";
function DataSchemaViewer({ experimentData }) {
const [jsonContent, setJsonContent] = useState(
JSON.stringify(experimentData, null, 2)
);
return (
<div style={{ width: "100%", height: "600px" }}>
<h3>Experiment Data Schema</h3>
<JsonCrackEmbed
json={jsonContent}
style={{ width: "100%", height: "100%" }}
/>
</div>
);
}<iframe
src="https://jsoncrack.internal.lab/widget"
width="100%"
height="600"
style="border: 1px solid #e5e7eb; border-radius: 8px;"
></iframe>JSON Crack handles multiple data serialization formats commonly used in research.
The primary format. Supports nested objects, arrays, primitives, and null values. JSON Schema validation is available to verify data conforms to expected structures.
Common in configuration files for research software, CI/CD pipelines, and computational workflow definitions (e.g., Snakemake, Nextflow configs).
pipeline:
name: rnaseq-analysis
steps:
- name: quality-control
tool: fastqc
input: raw_reads/*.fastq.gz
- name: trimming
tool: trimmomatic
parameters:
min_length: 36
quality_threshold: 20
- name: alignment
tool: star
genome_index: /ref/hg38Tabular data from experiments and surveys can be visualized to understand column relationships and data types.
Used in Python project configuration (pyproject.toml), Rust cargo files, and various research tool configurations.
Use JSON Crack to generate visual documentation of your lab's data schemas. Export the visualization as an image for inclusion in lab manuals, onboarding documents, or data management plans.
When building research APIs with FastAPI or Flask, use JSON Crack to visualize and verify your API response structures during development.
Before processing large datasets, visualize a sample record in JSON Crack to verify the structure matches expectations. This is faster than writing validation code for initial inspection.
When data schemas evolve between experiment versions, visualize both versions side-by-side to identify structural differences and plan migration logic.
© wentorai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/tools/diagram/json-data-visualizer of wentorai/research-plugins.
Open the folder on GitHubat commit bf44b3c
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in wentorai/research-plugins, which our catalogue first saw on October 7, 2026.
JSON Data Visualizer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| JSON Data Visualizer this skillwentorai/research-plugins | 298 | 1 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Megatron-LM Base Image BumpNVIDIA/Megatron-LM | 18k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Borg Live Debugkaranhudia/borg-ui | 1.7k | — | ~1.4k | Automated safety check: Notes | AGPL-3.0 | |
| Opik Local Dev Environmentcomet-ml/opik | 22k | — | ~734 | Automated safety check: Pass | Apache-2.0 | |
| Oneclickvirtoneclickvirt/oneclickvirt | 372 | — | ~1.1k | Automated safety check: Pass | GPL-3.0 | |
| Cosmos3 Env TroubleshootNVIDIA/cosmos-framework | 556 | — | ~1.3k | Automated safety check: Notes | Custom licence |
NVIDIA/Megatron-LM
Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up.
karanhudia/borg-ui
Live Borg debugging by exec-ing into the borg-web-ui Docker container.
comet-ml/opik
Starts, rebuilds, and troubleshoots the Opik local dev stack, including an optional Comet Platform integration mode for the Opik team.
oneclickvirt/oneclickvirt
OneClickVirt operations skill for managing containers, virtual machines, provider nodes, health checks, and metrics through MCP.
NVIDIA/cosmos-framework
Diagnose and fix Cosmos3 environment, installation, and runtime errors.
brevdev/workshop-build-an-agent
This skill should be used when the user wants to set up, install, deploy, bootstrap, or "spin up" the Build-an-Agent workshop (a.k.a.
wentorai/research-plugins
Craft structured research abstracts that maximize clarity and journal acceptance
wentorai/research-plugins
Manage academic citations across BibTeX, APA, MLA, and Chicago formats
wentorai/research-plugins
Summarize academic papers with structured extraction of key elements
wentorai/research-plugins
Evidence-based study techniques for academic learning and retention
wentorai/research-plugins
Adjust writing tone and register for academic audiences and venues
wentorai/research-plugins
Academic translation, post-editing, and Chinglish correction guide
Works with
Guide to JSON Crack for visualizing complex JSON data structures. JSON Data Visualizer is an agent skill from wentorai/research-plugins.
JSON Data Visualizer fits situations like: devOps & Cloud work in your project.
Run `npx skills add wentorai/research-plugins --skill json-data-visualizer -a claude-code`. Or copy the skill folder (skills/tools/diagram/json-data-visualizer in wentorai/research-plugins) into .claude/skills/json-data-visualizer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add wentorai/research-plugins --skill json-data-visualizer -a codex`. Or copy the skill folder (skills/tools/diagram/json-data-visualizer in wentorai/research-plugins) into .agents/skills/json-data-visualizer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wentorai/research-plugins --skill json-data-visualizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/json-data-visualizer, .gemini/skills/json-data-visualizer, .github/skills/json-data-visualizer and .opencode/skills/json-data-visualizer in your project.
Going by SKILL.md and its folder, JSON Data Visualizer needs the command-line tools its instructions call (npm, git and docker). Our summary lists: Python 3; Node.js; Docker.
SKILL.md names 5 domains. In commands or code: github.com, api.crossref.org and jsoncrack.internal.lab; the agent is likely to contact these when it follows the instructions. As links in the text: jsoncrack.com and npmjs.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
JSON Data Visualizer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with JSON Data Visualizer: Megatron-LM Base Image Bump (NVIDIA/Megatron-LM, 18k stars), Borg Live Debug (karanhudia/borg-ui, 1.7k stars), Opik Local Dev Environment (comet-ml/opik, 22k stars) and Oneclickvirt (oneclickvirt/oneclickvirt, 372 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
wentorai (a GitHub user) maintains it in wentorai/research-plugins, which has 298 GitHub stars. The repository holds 428 skills in this directory. The repository was last updated on June 19, 2026.
Source: wentorai/research-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.