Plannotator Visual Explainer
backnotprop/plannotator
Builds self-contained HTML explainers for plans, pull requests and technical concepts in Plannotator's theme, then opens them in its annotation view.
Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB).
Install Campaign Md Orchestration
$ npx skills add Hello-QM/catgo-LRG --skill campaign-md-orchestration -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Hello-QM/catgo-LRG campaign-md-orchestration --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/Hello-QM/catgo-LRG.git skills-src && mkdir -p .claude/skills && cp -r skills-src/server/catgo/workflow/skills/campaign .claude/skills/campaign-md-orchestration && 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 "campaign-md-orchestration" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/campaign into .claude/skills/campaign-md-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "campaign-md-orchestration", 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/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/campaignType 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 Hello-QM/catgo-LRG --skill campaign-md-orchestration -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Hello-QM/catgo-LRG campaign-md-orchestration --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .agents/skills && cp -r skills-src/server/catgo/workflow/skills/campaign .agents/skills/campaign-md-orchestration && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "campaign-md-orchestration" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/campaign into .agents/skills/campaign-md-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "campaign-md-orchestration", 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 Hello-QM/catgo-LRG --skill campaign-md-orchestration -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Hello-QM/catgo-LRG campaign-md-orchestration --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/server/catgo/workflow/skills/campaign .cursor/skills/campaign-md-orchestration && 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 "campaign-md-orchestration" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/campaign into .cursor/skills/campaign-md-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "campaign-md-orchestration", 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/Hello-QM/catgo-LRG.git --path server/catgo/workflow/skills/campaign--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 Hello-QM/catgo-LRG --skill campaign-md-orchestration -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Hello-QM/catgo-LRG campaign-md-orchestration --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/server/catgo/workflow/skills/campaign .gemini/skills/campaign-md-orchestration && 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 "campaign-md-orchestration" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/campaign into .gemini/skills/campaign-md-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "campaign-md-orchestration", 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 Hello-QM/catgo-LRG campaign-md-orchestrationInstalls 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 Hello-QM/catgo-LRG --skill campaign-md-orchestration -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .github/skills && cp -r skills-src/server/catgo/workflow/skills/campaign .github/skills/campaign-md-orchestration && 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 "campaign-md-orchestration" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/campaign into .github/skills/campaign-md-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "campaign-md-orchestration", 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 Hello-QM/catgo-LRG --skill campaign-md-orchestration -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Hello-QM/catgo-LRG campaign-md-orchestration --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Hello-QM/catgo-LRG.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/server/catgo/workflow/skills/campaign .opencode/skills/campaign-md-orchestration && 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 "campaign-md-orchestration" agent skill from https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/campaign into .opencode/skills/campaign-md-orchestration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "campaign-md-orchestration", 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.
Facts
- Skill name
campaign-md-orchestration- GitHub stars
- 205
- Token cost
- ~1.6k tokens
- SKILL.md length
- 768 words
- Files
- 26 (incl. scripts, references)
- Skills in repo
- 75
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB).
- Works in 2 steps: Input-file gate (per submission). Before… → Stage / decision-point checkpoint. At a…
- The user opts out of the visual workflow engine
- SKILL.md covers When to use, Conventions, Setup gate — confirm the… and Gates (default…, plus 6 more sections
- Runs Python scripts from its folder; calls python
What it does
Campaign Md Orchestration is an agent skill from Hello-QM/catgo-LRG. Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB). Use when the user opts out of the visual workflow engine.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 27 other files, including scripts and reference files (for example `references/catgo-cli.md`, `scripts/INDEX.md` and `scripts/aggregate.py`).
It sits in Agent Workflows. The repository describes itself as: AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language CatBot assistant, visual DAG workflow engine, HPC job submission… The licence is AGPL-3.0.
When your agent uses it
- The user opts out of the visual workflow engine
Example prompts
- “/campaign-md-orchestration”
Requirements
- Python 3
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- Input-file gate (per submission). Before each submit_calc.py, show the
- Stage / decision-point checkpoint. At a stage end or a plan.md decision
What it can do on your machine
Read from SKILL.md and the folder at commit fd6291b. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Ships 17 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Campaign Md Orchestration loads about 1.6k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 46 tokens; SKILL.md has 768 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.
Safety
Auto-check passed
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); the scripts in this folder are not scanned.
SKILL.md
The full file from Hello-QM/catgo-LRG at commit fd6291b, republished under its AGPL-3.0 licence (© Hello-QM). 768 words, ~1,563 tokens.
Download SKILL.mdSave it as
.claude/skills/campaign-md-orchestration/SKILL.md (or your agent's skills folder). This skill also uses 25 other files; get the full folder from GitHub.- name
- campaign-md-orchestration
- description
- Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB). Use when the user opts out of the visual workflow engine.
Campaign (md-orchestration) — agent playbook
TL;DR: Run multi-step HPC campaigns from a human-readable folder + markdown tree. You (the agent) read
plan.md+STATUS.md, render inputs, submit via the reference scripts (plain ssh sbatch), update markdown, and check in at gates. No DB. Files are the source of truth.
When to use
The user chose md-orchestration over the visual workflow engine (exploratory / iterative / mixed-software / cross-cluster work). The visual DB engine still exists for fixed routines + teaching — don't use this skill for those.
Conventions
Authoring conventions (progressive md, README+INDEX pairs + keeping them current, logging
interventions to LESSONS, human-readable/never-hash names, the top→stage→calc progressive
plan, filling scaffold stubs) live in the catgo-campaign-conventions skill — follow
it whenever you create/edit campaign markdown.
Setup gate — confirm the environment (NEVER guess)
Before submitting anything, confirm with the user and record in cluster.md:
cluster identity + SSH host/account + partition/walltime/ntasks, the compute
binary + load method (module/conda/full path + run command), the POTCAR root,
the python env, and the remote base dir. The user may give a reference job
script — local, or a path on the cluster (pull it with fetch_ref.py);
CatGO adapts it instead of synthesizing the preamble. Run catgo_validate_config
before the first submit. submit_calc.py refuses while cluster.md is
incomplete — this is enforced in code, not just here. Never guess cluster paths.
Gates (default human-in-the-loop)
- Input-file gate (per submission). Before each
submit_calc.py, show the user the renderedINCAR/POSCAR/KPOINTS/POTCAR/job.sband ask to confirm. Run the script only after they confirm. - Stage / decision-point checkpoint. At a stage end or a
plan.mddecision point, write a stage summary and ask: proceed / modify / stop.
YOLO / autopilot opt-in disables both gates. Set it only if the user says so per-run ("go as you set" / "yolo") or persistently ("always skip review"). With YOLO off and the user away, hold at the gate: keep polling running jobs but submit nothing new and cross no stage.
Plan creation — ask the user first
Before writing or finalizing plan.md, ASK the user how to create it — do not assume:
- Brainstorm together — read
literature/INDEX.mdfirst, then ask clarifying questions ONE at a time (goal, candidate set, descriptor, funnel thresholds, reference systems), propose 2-3 stage / decision-point approaches with a recommendation, and writeplan.mdonly after the user approves. - Template / direct — instantiate a template (e.g.
saa_her) or generateplan.mdfrom the user's stated intent, then let them review and edit it.
Default to asking. Skip the question only if the user already opted in ("just use the template" / "go as you set" / YOLO).
Derive the full pipeline from the TARGET OBSERVABLE — before building ANY input.
Work backward from what the user wants to measure to every calc it requires, and write
that into plan.md BEFORE scaffolding structures/inputs (the build order is: plan first,
inputs second). Common traps:
- Overpotential / free-energy diagram / ΔG / Gibbs / adsorption free energy ⇒ needs
free energies, not raw DFT energies ⇒ follow the
catgo-gibbs-pipelineskill (the per-speciesgeo_opt → freq → gibbspipeline, freq setup, gas-ref convention, CHE, η). Wire freq as the auto-next-step after each species' geo_opt inplan.md. - Reaction barriers / TS ⇒ NEB/dimer + a freq to confirm one imaginary mode.
- Band gap / DOS / COHP ⇒ a dense-k static after relax. Confirm the full stage list with the user before building. Do NOT jump from "scope" to rendering inputs — discuss the plan (and its observables) first.
Show full SKILL.md (229 more words)Show less
The loop + resuming
Driving the ~10-min poll loop (delegate each poll to a subagent → compact summary; verify
convergence by force; auto-advance each converged species per-species, pipeline not
barrier; stage checkpoints) AND resuming a campaign from disk after compaction / a new
session live in the catgo-campaign-loop skill. Gates stay with the main agent.
Scripts (in scripts/, see scripts/INDEX.md)
python new_campaign.py <dir> --name "<name>" --template saa_her|blank
python fetch_ref.py --project <dir> --ssh <alias> --remote_path <cluster .sb>
python submit_calc.py --project <dir> --calc calc/<stage>/<candidate> --ssh <alias>
python poll.py --project <dir> --ssh <alias>Run them as-is (gates enforced), or read scripts/campaign_lib.py and adapt for
the unforeseen (mixed software / odd clusters / novel calc types).
Archiving (explicit / propose — never auto-decide)
Keep the live tree clean by moving superseded/abandoned calcs into archive/, but
NEVER guess what is stale: python archive.py --project <dir> --list proposes only
STATUS=FAILED calcs (it does not move anything). Funnel rejects (a DONE calc with a
high E_form) are kept — the ranking/volcano/funnel need them as data. Move one only on
explicit user instruction: python archive.py --project <dir> --calc calc/<stage>/<name> --reason "..." (leaves a tombstone ARCHIVED.md at the original location).
catgo CLI during a campaign
Use the existing catgo CLI for the actual chemistry — see
references/catgo-cli.md. Build structures (catgo slab/supercell/reticular/
convert/inspect) and analyze results (catgo dos/band/cohp/freq). These
run offline (no viewer needed). Aggregate per-calc result.md files with
scripts/aggregate.py; draft reports with scripts/make_report.py; ingest
literature with scripts/ingest_lit.py.
Literature -> plan -> skill
Drop papers (PDF -> MinerU md) + GitHub repos into literature/; ground plan.md
in them with citations. Mine reusable recipes into literature/extracted-skills.md;
promote the best into the global SKILL library.
© Hello-QM, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 25 other files (scripts, references) in server/catgo/workflow/skills/campaign of Hello-QM/catgo-LRG.
- SKILL.md
- references/catgo-cli.md
- scripts/INDEX.md
- scripts/aggregate.py
- scripts/archive.py
- scripts/campaign_analysis.py
- scripts/campaign_lib.py
- scripts/campaign_lit.py
- scripts/campaign_report.py
- scripts/fetch_ref.py
- scripts/ingest_lit.py
- scripts/make_report.py
- scripts/new_campaign.py
- scripts/poll.py
- scripts/submit_calc.py
- scripts/test_campaign_analysis.py
- scripts/test_campaign_lib.py
- scripts/test_campaign_lit.py
- scripts/test_campaign_report.py
- … and 7 more
Open the folder on GitHubat commit fd6291b
Compare with similar skills
Campaign Md Orchestration 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 |
|---|---|---|---|---|---|---|
| Campaign Md Orchestration this skillHello-QM/catgo-LRG | 205 | — | ~1.6k | Automated safety check: Pass | AGPL-3.0 | |
| Plannotator Visual Explainerbacknotprop/plannotator | 9.3k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Trellis ContinueROYIANS/foliq-print-template-designer | 136 | 6 repos | ~554 | Automated safety check: Pass | MIT | |
| Trellis StartROYIANS/foliq-print-template-designer | 136 | 6 repos | ~646 | Automated safety check: Pass | MIT | |
| Journal AdaptWantongC/journal-adapt-writing-skill | 796 | 1 repos | ~5.2k | Automated safety check: Pass | MIT | |
| Open Proseopenprose/prose | 1.8k | — | ~7.3k | Automated safety check: Notes | MIT |
Similar skills
Trellis Continue
ROYIANS/foliq-print-template-designer
Resume work on the current task. An agent skill from ROYIANS/foliq-print-template-designer.
Trellis Start
ROYIANS/foliq-print-template-designer
Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/.
Journal Adapt
WantongC/journal-adapt-writing-skill
Dynamic academic writing skill generator. An agent skill from WantongC/journal-adapt-writing-skill.
Open Prose
openprose/prose
Activate when the user types prose ..., opens a .prose.md file with kind: frontmatter, opens a .prose file, or asks for reusable multi-agent orchestration.
AutoRAG Lite Setup
Marker-Inc-Korea/AutoRAG
Bootstraps and repairs the model-free AutoRAG Lite MCP server: installing it, initializing a config with approved search roots, building indexes and verifying discovery.
More from Hello-QM/catgo-LRG
All 75 skills in this repoCatgo Gibbs Pipeline
Hello-QM/catgo-LRG
Compute adsorption/reaction Gibbs free energies, free-energy diagrams, and electrochemical overpotentials (HER/ORR/OER/CO2RR/NRR) with VASP.
Abinit
Hello-QM/catgo-LRG
Generate and manage ABINIT DFT calculations. An agent skill from Hello-QM/catgo-LRG.
Adsorbate Placement
Hello-QM/catgo-LRG
A skill your agent uses when the user asks to place an adsorbate molecule on a surface, find adsorption sites, or set up a surface+adsorbate model for DFT.
Adsorption Energy
Hello-QM/catgo-LRG
A skill your agent uses when the user asks for adsorption energy, binding energy, or wants to compare how strongly a molecule binds to a surface.
Analysis Router
Hello-QM/catgo-LRG
A skill your agent uses when the user asks to analyze computational results: Gibbs free energy, OER/HER/CO2RR overpotentials, adsorption energy, convergence tests, DOS/d-band analysis, or Bader…
Atom Ops
Hello-QM/catgo-LRG
One-shot recipes for adding, deleting, moving, and replacing individual atoms in the active CatGo viewer structure.
Related
Categories
Questions about Campaign Md Orchestration
What does Campaign Md Orchestration do?
Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB). Campaign Md Orchestration is an agent skill from Hello-QM/catgo-LRG. Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB).
When should I use Campaign Md Orchestration?
Campaign Md Orchestration fits situations like: the user opts out of the visual workflow engine.
How do I install Campaign Md Orchestration in Claude Code?
Run `npx skills add Hello-QM/catgo-LRG --skill campaign-md-orchestration -a claude-code`. Or copy the skill folder (server/catgo/workflow/skills/campaign in Hello-QM/catgo-LRG) into .claude/skills/campaign-md-orchestration in your project. Claude Code loads it when a task matches its description.
How do I install Campaign Md Orchestration in Codex?
Run `npx skills add Hello-QM/catgo-LRG --skill campaign-md-orchestration -a codex`. Or copy the skill folder (server/catgo/workflow/skills/campaign in Hello-QM/catgo-LRG) into .agents/skills/campaign-md-orchestration in your project. Codex loads it when a task matches its description.
Can I use Campaign Md Orchestration in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Hello-QM/catgo-LRG --skill campaign-md-orchestration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/campaign-md-orchestration, .gemini/skills/campaign-md-orchestration, .github/skills/campaign-md-orchestration and .opencode/skills/campaign-md-orchestration in your project.
What does Campaign Md Orchestration need to run?
Going by SKILL.md and its folder, Campaign Md Orchestration needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Campaign Md Orchestration access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Campaign Md Orchestration safe to install?
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Campaign Md Orchestration use?
Campaign Md Orchestration is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Campaign Md Orchestration use?
About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 460 tokens, read only when the agent opens those files.
What are the alternatives to Campaign Md Orchestration?
Skills that share tags, products or a category with Campaign Md Orchestration: Plannotator Visual Explainer (backnotprop/plannotator, 9.3k stars), Trellis Continue (ROYIANS/foliq-print-template-designer, 136 stars), Trellis Start (ROYIANS/foliq-print-template-designer, 136 stars) and Journal Adapt (WantongC/journal-adapt-writing-skill, 796 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Campaign Md Orchestration?
Hello-QM (a GitHub user) maintains it in Hello-QM/catgo-LRG, which has 205 GitHub stars. The repository holds 75 skills in this directory. The repository was last updated on September 22, 2026.
Source: Hello-QM/catgo-LRG on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.