Next AI Draw.io
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
The all-in-one AI agent. Build mobile apps, frontend, backend, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels. Zero Telemetry.
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/opencrabs-opencrabs)MCP servers that connect the AI to services for the same work
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
Verified React chart generation: select, validate, repair, render, and inspect charts through MCP.
Same kind of work, ordered like the Skills list
| This one opencrabs | impeccable | diagram-design | frontend-slides | guizang-ppt-skill | |
|---|---|---|---|---|---|
| Maker | opencrabs | pbakaus | cathrynlavery | zarazhangrui | op7418 |
| Skills | – | 1 | 1 | 1 | 1 |
| GitHub stars | 1,031 | 111,852 | 67,796 | 32,458 | 29,958 |
| Last code change | Nov 17, 2026 | Nov 17, 2026 | Nov 13, 2026 | Jun 24, 2026 | Oct 30, 2026 |
| License | MIT | Apache-2.0 | MIT | MIT | AGPL-3.0 |
1 skills (instruction sets) by opencrabs that an AI reads and follows · not an MCP server
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
CodexGitHub CopilotOpenCode
From the maker’s README and the folders in the repo
GitHub account opencrabs (organization) is only 8 months old: take extra care
★ 1,031 stars · code last changed Nov 17, 2026
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit b4e1a66 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
First: which AI do you use?
Pick your app and this page shows only how to install it there
Uploading to claude.ai would fail: the description is over 200 characters (261). Use "Let the AI install it" instead
Copy this sentence and paste it into a Claude Code chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Restart Claude Code, then type /github or ask for a matching task and Claude picks it up
Checked against official docs Nov 12, 2026 · Source: code.claude.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills
Open Codex in the ChatGPT desktop app and paste this sentence into the chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Put the github folder at ~/.agents/skills/github
~ is your home folder ($HOME)
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Skills you install yourself do not work here; only skills that come with a plugin from the directory
To use this skill with ChatGPT, use the ChatGPT desktop app as above
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
Copy this sentence and paste it into a Cursor chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
In Cursor’s Agent chat, type / and pick github
Checked against official docs Nov 12, 2026 · Source: cursor.com
A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.
Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead
This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md
Checking the commands · copy buttons appear once they pass
For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.
Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026
The text below comes from the maker’s repo, not from PopNx MCP
5,826 characters · Open the full file on GitHub
---
name: github
description: Full GitHub CLI control — issues, PRs, code reviews, repo management. Uses gh CLI with auth detection, rate limiting, and templates. Triggers on: github, issue, pull request, PR, code review, repo, branch, label, assignee, milestone, release, workflow, actions.
---
# GitHub Skill
Full GitHub operations via the `gh` CLI. Always check auth first, use templates for consistency, and respect rate limits.
## Step 0: Auth Detection (ALWAYS FIRST)
Before ANY GitHub operation, detect the auth method:
```bash
gh auth status 2>&1
```
**If authenticated:** Proceed. Note the logged-in username for the session.
**If not authenticated:** Check for `GITHUB_TOKEN` env var:
```bash
echo "${GITHUB_TOKEN:+token_set}"
```
**If no token either:** Tell the user:
> GitHub CLI is not authenticated. Run `gh auth login` to authenticate, or set `GITHUB_TOKEN` environment variable with a personal access token.
Do NOT proceed without auth. Do NOT fall back to `curl` or `http_request`.
## Step 1: Rate Limit Check (before bulk operations)
Before operations that issue 5+ API calls (batch triage, bulk label, multi-issue create), check rate limits:
```bash
gh api rate_limit --jq '.resources.core.remaining, .resources.core.limit, .resources.search.remaining, .resources.search.limit'
```
If core remaining < 100 or search remaining < 10, warn the user and ask whether to proceed.
## Issue Operations
### Create Issue
```bash
gh issue create --repo OWNER/REPO --title "TITLE" --body "BODY" --label "LABEL" --assignee "USER"
```
Templates (use unless user provides their own):
**Bug report:**
```markdown
## Description
[What happened]
## Steps to Reproduce
1. [Step 1]
2. [Step 2]
## Expected Behavior
[What should happen]
## Actual Behavior
[What actually happened]
## Environment
- OS: [e.g., macOS 14.3]
- Version: [e.g., v0.3.70]
```
**Feature request:**
```markdown
## Problem
[What problem does this solve?]
## Proposed Solution
[How should it work?]
## Alternatives Considered
[What else was considered?]
## Additional Context
[Screenshots, logs, references]
```
### List Issues
```bash
gh issue list --repo OWNER/REPO --state open --limit 20
gh issue list --repo OWNER/REPO --label "bug" --state open
gh issue list --repo OWNER/REPO --assignee "@me"
```
### View Issue
```bash
gh issue view NUMBER --repo OWNER/REPO
gh issue view NUMBER --repo OWNER/REPO --comments
```
### Comment on Issue
```bash
gh issue comment NUMBER --repo OWNER/REPO --body "COMMENT"
```
### Close Issue
```bash
gh issue close NUMBER --repo OWNER/REPO --reason completed
gh issue close NUMBER --repo OWNER/REPO --comment "Closing because REASON"
```
### Label Issue
```bash
gh issue edit NUMBER --repo OWNER/REPO --add-label "bug,priority:high"
gh issue edit NUMBER --repo OWNER/REPO --remove-label "wontfix"
```
### Assign Issue
```bash
gh issue edit NUMBER --repo OWNER/REPO --add-assignee "username"
gh issue edit NUMBER --repo OWNER/REPO --remove-assignee "username"
```
## Pull Request Operations
### Create PR
```bash
gh pr create --repo OWNER/REPO --title "TITLE" --body "BODY" --base main --head feature-branch
```
PR template:
```markdown
## What
[One-line summary]
## Why
[Why this change is needed]
## How
[What changed and how it works]
## Testing
- [ ] `cargo fmt --all -- --check`
- [ ] `cargo clippy --all-features -- -D warnings`
- [ ] `cargo test --all-features`
## Related Issues
Closes #NUMBER
```
### List PRs
```bash
gh pr list --repo OWNER/REPO --state open
gh pr list --repo OWNER/REPO --author "@me" --state open
```
### View PR
```bash
gh pr view NUMBER --repo OWNER/REPO
gh pr view NUMBER --repo OWNER/REPO --comments
gh pr diff NUMBER --repo OWNER/REPO
```
### Review PR
```bash
gh pr review NUMBER --repo OWNER/REPO --approve
gh pr review NUMBER --repo OWNER/REPO --request-changes --body "Please fix X"
gh pr review NUMBER --repo OWNER/REPO --comment --body "Looks good, one nit"
```
### Merge PR
```bash
gh pr merge NUMBER --repo OWNER/REPO --squash
gh pr merge NUMBER --repo OWNER/REPO --merge
gh pr merge NUMBER --repo OWNER/REPO --rebase
```
### Branch Operations
```bash
gh pr checkout NUMBER --repo OWNER/REPO
git push origin --delete feature-branch # after merge
```
## Repository Operations
### View Repo
```bash
gh repo view OWNER/REPO
gh repo view OWNER/REPO --json name,description,defaultBranchRef,stargazerCount
```
### Clone
```bash
gh repo clone OWNER/REPO
gh repo clone OWNER/REPO /path/to/dir
```
### Fork
```bash
gh repo fork OWNER/REPO
gh repo fork OWNER/REPO --clone=false
```
### Releases
```bash
gh release list --repo OWNER/REPO
gh release view TAG --repo OWNER/REPO
gh release create TAG --repo OWNER/REPO --title "TITLE" --notes "NOTES"
```
## Workflow / Actions
```bash
gh workflow list --repo OWNER/REPO
gh run list --repo OWNER/REPO --limit 5
gh run view RUN_ID --repo OWNER/REPO
gh run watch RUN_ID --repo OWNER/REPO
```
## Code Search
```bash
gh search code "QUERY" --repo OWNER/REPO
gh search issues "QUERY" --repo OWNER/REPO
gh search prs "QUERY" --repo OWNER/REPO
```
## Rules
1. **ALWAYS use `gh` CLI, NEVER `http_request` to api.github.com** — http_request lacks proper headers and gets 403
2. **ALWAYS check auth before first operation** — Step 0 above
3. **ALWAYS use `--repo OWNER/REPO`** — don't rely on working directory detection
4. **NEVER expose tokens** — don't echo GITHUB_TOKEN, don't log it, don't include in bodies
5. **Batch operations check rate limits first** — Step 1 above
6. **Use `--jq` for filtering** — `gh api ... --jq '.field'` to extract specific values
7. **Templates are suggestions** — adapt to the user's actual content, don't force rigid structure
8. **Cross-reference usernames** — when the issue/comment mentions a user, check if they're in USER.md
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.