Install
$ agentstack add skill-andrewyng-context-hub-skill-context-hub ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Context Hub
Use this skill whenever current docs, current setup guidance, or current workflow instructions matter. Trigger it immediately when the user mentions the latest docs, latest model, chub, or Context Hub. Keep the workflow simple: ensure chub exists, run chub help, then follow the guidance it returns.
If this file and chub help ever disagree, follow chub help.
1. Ensure chub exists
Check whether chub is already installed:
command -v chub >/dev/null 2>&1
If that fails, and the environment has node, npm, network access, and package-manager permission, install it:
npm install -g @aisuite/chub
If installation is blocked, tell the user exactly what is missing instead of guessing.
2. Always start with chub help
Run:
chub help
Treat that output as the source of truth for the installed CLI version.
3. Use Context Hub instead of guessing
Typical flow:
chub search "" --json
chub get --lang py
Use the fetched docs or skill as the authority for API shapes, setup steps, versions, model names, model configuration, and workflow guidance.
4. Save concise local notes
If you discover a short project-specific note that should appear next time, save it:
chub annotate "Concise project-specific note"
Use annotations only for notes that are local, actionable, and worth seeing on future fetches.
5. Leave feedback after using an entry
Unless the user explicitly tells you not to, always leave feedback after using a doc or skill:
chub feedback up --label accurate "What was useful"
chub feedback down --label outdated "What needs fixing"
Valid labels: accurate, well-structured, helpful, good-examples, outdated, inaccurate, incomplete, wrong-examples, wrong-version, poorly-structured.
Do not include secrets, source code, private architecture details, or other sensitive information in feedback comments.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: andrewyng
- Source: andrewyng/context-hub-skill
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.