agentsclimarketplace

Permission scope review

Skill duandigi/duandigi-growth-marketing-skill/skills/permission-scope-review

Use this skill when reviewing OAuth scopes, API permissions, WordPress roles, service-account access, or connector capabilities for least privilege, user trust, and staged read or write access.From its SKILL.md

Install
npx -y skills add duandigi/duandigi-growth-marketing-skill --skill permission-scope-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.3 KB, 542 tokens by cl100k_base, as published. Nobody here has run it

Permission Scope Review

Purpose

Minimize access risk while preserving the exact capabilities required for analysis, preparation, and approved execution.

Inputs

  • Provider, use case, and requested scopes or permissions
  • Current official provider documentation
  • Connection access mode: observe, prepare, or execute with approval
  • Data sensitivity, retention, and organizational role requirements

If a required input is unavailable, label it unknown, state how it limits the decision, and create a collection, mapping, validation, or instrumentation task. Never invent credentials, assets, metrics, permissions, or business outcomes.

Workflow

  1. Translate every requested scope into a concrete user-facing capability.
  2. Remove scopes that do not support an active use case.
  3. Prefer read-only variants and incremental authorization when available.
  4. Identify sensitive, restricted, app-review, developer-token, or business-verification requirements.
  5. Separate provider permission from application-level role and project authorization.
  6. Document re-consent, revocation, token expiry, and degraded-mode behavior.
  7. Return a minimal scope set with an explicit justification for each item.

Required output

Return a concise, decision-oriented result containing:

  • Requested-versus-required scope table
  • Minimal recommended permission set
  • Provider review or verification dependencies
  • Read, prepare, and execute capability boundaries
  • User-facing consent explanation

Label material statements as confirmed, calculated, inferred, assumed, or unknown. Include the data period, last complete period, source lineage, and confidence whenever they can change the decision.

Guardrails

  • Use current official provider documentation for permission names and requirements.

  • Do not request write, messaging, publishing, or ad-management permissions for reporting-only use cases.

  • Do not treat an access token as proof that the user is authorized inside the application.

  • Do not hide broad permissions behind vague consent copy.

  • Do not claim guaranteed growth or present an estimate as observed fact.

  • Do not reveal secrets, personal data, private provider payloads, or cross-project information.

  • When an action can spend money, publish, contact people, alter access, modify production, or delete data, prepare an approval request instead of executing automatically.

Completion check

Before finishing, verify that the output:

  • answers a specific business or implementation decision;
  • uses the correct organization, project, asset, date range, time zone, and currency;
  • separates performance problems from data, connection, and attribution problems;
  • includes evidence, uncertainty, affected scope, and a measurable next step;
  • respects least privilege, approval, audit, and rollback requirements;
  • is no longer than necessary for the decision.

What ships with it: 1 file

886 B alongside SKILL.md

evals/

Keep looking

Skills are one crate of 326,452. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.