Works with the AI Agents you already use
access request approval workflow designer
This skill automates the design of least-privilege approval workflows by programmatically checking requests against role baselines and entitlement catalogues.
$2.99
access request approval workflow designer
Example session with this skill installed
Design an approval workflow for User_88 (Developer) requesting 'Admin' access to the 'Production_DB' for 5 days. Here is the entitlement catalogue and user baseline.
- Read your context and instructions
- Compiled the access request approval
I have processed the access request for User_88 against the provided entitlement catalogue and developer role baseline.
Access Request Approval Workflow Design — Enterprise Ops, 2023-11-15
1. Scope, sources and assumptions
- Sources: E1 (Access Request), E2 (Entitlement Catalogue).
- Scope: Systems 'Production_DB' assessed.
- Requests: 1 assessed, 0 excluded.
- Assumptions: Default SLA hours applied per policy (user_supplied).
2. Request results
| Request | Entitlement | Sensitivity | Requested | Proposed | Basis | Approval hours | Granted days | Expires on | Verdict |
|---|---|---|---|---|---|---|---|---|---|
| REQ-01 | Production_DB | Critical | Admin | Read-Only | Role Baseline | 8 | 5 | 2023-11-20 | Ready (Adjusted) |
3. Approval routes
| Request | Stage | Type | Approver | Hours |
|---|---|---|---|---|
| REQ-01 | 1 | Owner | DB_Owner_ID | 4 |
| REQ-01 | 2 | Security | Sec_Ops_ID | 4 |
4. Findings and exceptions
| Request | Severity | Code | Finding |
|---|---|---|---|
| REQ-01 | Info | BASELINE_EXCEEDED | Requested 'Admin' exceeds 'Developer' baseline of 'Read-Only'. |
5. Proposed actions (drafts)
| Action | Request | Status | Requires human approval | Blocking codes |
|---|---|---|---|---|
| Draft Approval | REQ-01 | PENDING | true | n/a |
6. Warnings and information gaps
- Warning:
MANAGER_ID_MISSINGfor User_88. Organizational validation required.
7. Interpretation and items for human review
- The request was downgraded to 'Read-Only' to match the documented role baseline. (Computed result)
- Management decision required: Approval of 'Admin' level if 'Read-Only' is insufficient for the task.
- Analytical estimate — validation required: The 8-hour SLA assumes immediate availability of the DB Owner.
This analysis supports, and does not replace, the decisions of accountable owners and approvers.
Next steps
- Review the baseline adjustment with the requester's manager.
- Validate the
DB_Owner_IDin the active directory. - Route the draft proposal to Security Operations for final sign-off.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing access requests manually leads to over-provisioned accounts and audit failures. This skill automates the design of least-privilege approval workflows by programmatically checking requests against role baselines and entitlement catalogues.
What it does
- Approval Route Derivation determines the specific sequence of owner and security approvals based on system sensitivity levels.
- Least-Privilege Assessment compares requested access levels against established role baselines to flag unnecessary permissions.
- Conflict Detection identifies potential Segregation of Duties (SoD) issues by checking requests against a user's current entitlements.
- Time-Bound Governance applies expiry limits and calculates approval SLAs to prevent permanent "privilege creep."
- Integrity Checking flags self-approval attempts and non-distinct approvers to ensure independent oversight.
How it works
- Prepare Data by gathering access requests, entitlement catalogues, role baselines, and your approver directory.
- Execute Analysis using the deterministic script to process the data against policy rules.
- Review Findings via the generated report which highlights blocked requests, warnings, and information gaps.
- Human Finalization takes the draft-only proposals to accountable owners for formal sign-off.
Frameworks & tools
The core logic runs via a deterministic Python engine (scripts/run.py) using JSON schemas for data validation.
Why this beats prompting it yourself
Generic prompts often hallucinate approval chains or miss subtle role baseline violations. This skill uses a hard-coded script to ensure every calculation, from expiry dates to SLA hours, is mathematically accurate and repeatable for audit trails.
Use cases
- Designing temporary access workflows for contractors with auto-expiry limits.
- Auditing new access requests for conflicting entitlements before provisioning.
- Calculating total approval time (SLA) for complex, multi-stage access routes.
- Generating draft approval designs for high-sensitivity system requests.
Known limitations
This skill produces draft designs only and cannot grant, revoke, or provision actual system access. It does not verify the identity of approvers or claim compliance with specific ITIL or ISO standards.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Draft-only output; no active provisioning. Requires structured entitlement/role data. Does not verify approver identities. Logic restricted to provided scope.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 days ago