skill-aiengkenn-agent-skills-sanity-studio-roles · by Install
$ agentstack add skill-aiengkenn-agent-skills-sanity-studio-roles ✓ 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-aiengkenn-agent-skills-sanity-studio-roles) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Sanity Studio Roles
Give clients enough power to edit, not enough to destroy the project.
Ask first
- How many editors / admins?
- Is Vision required for anyone on the client side? (usually no)
- Multiple datasets (staging/prod)?
Role matrix (typical agency handoff)
| Role | Can do | Cannot | |------|--------|--------| | Viewer | Read content | Edit / publish | | Editor | Edit + publish content | Project settings, billing, delete dataset | | Administrator | Invites, project settings | Still careful with tokens | | Developer (your team) | Tokens, webhooks, schemas via code | — |
Exact capability names evolve in Sanity manage — map to current project roles UI.
Workflow
- Invite client users from sanity.io/manage
- Default new marketers → Editor (or custom role if available)
- One client Administrator max for password resets / invites
- Keep write tokens on the agency side (CI, bootstrap) — never email tokens
- Optionally customize Studio structure / plugin visibility for non-devs
Studio hardening tips
- Prefer custom desk that hides junk types
- Don’t teach Vision in client training
- Separate staging dataset for experiments
- Rotate tokens when freelancers leave
Anti-patterns
- Everyone Administrator “for convenience”
- Sharing one login among the whole marketing team
- Putting
SANITY_API_WRITE_TOKENin Notion
Deliverable
Invite list + roles · who holds tokens · staging vs prod access notes.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: AIEngKenn
- Source: AIEngKenn/agent-skills
- 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.