Connectors Directory Browser
Use a lightweight checklist and prompt templates to evaluate a Claude connector from a directory, clarify required permissions, and define safe success criteria before you connect it.
Install
$ agentstack add skill-uygnoey-skills-from-claude-blog-connectors-directory-browser ✓ 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
Instructions
Use this skill when you are about to connect a third-party tool to Claude from a connector directory.
- State the workflow goal in one sentence.
- Identify the connector (name + whether it is remote SaaS vs local desktop extension).
- Ask for access boundaries: what data it can read, what it can write or trigger, and what it cannot do.
- Define success criteria: what output you expect from the connector-enabled workflow.
- Define safety constraints (red lines): sensitive data to avoid, irreversible actions to prohibit, environments to restrict (prod vs sandbox).
- Run a minimal test with non-sensitive data.
- Review and iterate: expand scope only after the minimal test passes.
Use the prompt templates in:
- templates/permission-audit.md
- templates/minimal-test-plan.md
Examples
Example: connecting Linear to draft release notes
1) Fill out templates/permission-audit.md for the Linear connector. 2) Create a small test plan using templates/minimal-test-plan.md. 3) Run the workflow on a single public or low-risk issue.
Example: installing a local desktop extension
Follow the same steps, but explicitly note what local resources the extension can access (files, projects, local APIs) and what it sends to remote services.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: uygnoey
- Source: uygnoey/skills-from-claude-blog
- 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.