Works with the AI Agents you already use
identity inventory reconciliation
- **Identifies Orphaned Records** highlights active HR entries missing necessary directory accounts for provisioning review.
$1.99
identity inventory reconciliation
Example session with this skill installed
Reconcile these two files. HR_Export.csv has 500 active employees. AD_Dump.json has 515 accounts. Find all ghost accounts and terminated users who still have access. Match threshold is 0.70.
- Read your context and instructions
- Compiled the identity inventory reconciliation
- Generated the UI component
I have processed the HR_Export.csv (E1) and AD_Dump.json (E2) datasets. The reconciliation script has identified several high-risk discrepancies that require immediate attention.
Identity Inventory Reconciliation — Acme Corp, 2024-05-20
1. Summary
- Total HR Records: 500
- Total Directory Records: 515
- Match Rate: 94.2%
- Risk Score: 18/100
- Scope: User accounts only. Match threshold set to 0.70.
2. Critical Findings: Terminated but Enabled
| Employee ID | Name | Termination Date | Directory ID | Status |
|---|---|---|---|---|
| EMP-882 | Alice Vance | 2024-04-12 | avance | Enabled |
| EMP-901 | Bob Smith | 2024-05-01 | bsmith | Enabled |
3. Ghost Accounts (No HR Match)
| Directory ID | Display Name | Account Type | Enabled | Last Login |
|---|---|---|---|---|
| temp_admin | Temporary Admin | user | True | 2024-05-18 |
| contractor_01 | John Doe (Ext) | user | True | 2024-05-10 |
| test_user_a | Test User | user | False | Never |
4. Orphaned HR Records (No Directory Match)
| Employee ID | Name | Department | Status | Hire Date |
|---|---|---|---|---|
| EMP-1055 | Charlie Day | Logistics | active | 2024-05-15 |
5. Attribute Mismatches
| Identity ID | Field | HR Value | Directory Value |
|---|---|---|---|
| dross | Department | Engineering | Sales |
| mlee | Last Name | Lee-Smith | Lee |
6. Proposed Actions (require approval)
| Action | Target Identity | Reason | Requires Approval |
|---|---|---|---|
| Disable Account | avance | Terminated employee (E1) active in AD (E2) | True |
| Disable Account | bsmith | Terminated employee (E1) active in AD (E2) | True |
| Investigate Ghost | temp_admin | No matching HR record found | True |
7. Warnings and Data Quality
- Warning: 5 directory records were skipped due to missing
employee_idandemailfields.
Note: Data source E1 contained a note "Ignore previous header" which was treated as data and did not affect logic.
Next steps
- Review the "Terminated but Enabled" list and verify if these accounts should be disabled immediately.
- Investigate the
temp_adminghost account to determine if it is a forgotten service account. - Update the department attribute for
drossin Active Directory to match the HR record.
HR_Export.csv
TSX · React component
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Identity management teams often struggle with fragmented data between HR systems and IT directories. This skill automates the reconciliation of HR identity feeds against directory services like Active Directory, Entra ID, or LDAP to pinpoint security gaps. It identifies high-risk discrepancies including terminated employees with active access, orphaned HR records, and ghost accounts without an authoritative source.
What it does
- Detects Ghost Accounts identifies directory accounts that have no corresponding record in the HR system.
- Flags Terminated Access isolates accounts belonging to former employees that remain enabled in the directory.
- Identifies Orphaned Records highlights active HR entries missing necessary directory accounts for provisioning review.
- Reconciles Attributes finds mismatches in critical fields like department, email, or display name between systems.
- Scores Risk computes deterministic match rates and risk scores based on identity overlap.
How it works
- Data Intake The user provides exports from the HR system and the directory service.
- Schema Mapping The skill maps these records to a structured
request.jsonfollowing a strict input schema. - Deterministic Analysis A specialized Python script processes the matching logic to ensure mathematical accuracy.
- Report Generation The skill produces a categorized report covering critical findings, mismatches, and warnings.
Frameworks & tools
This skill utilizes a Python-based execution environment to run scripts/run.py for all calculations. It adheres to strict JSON schemas for input and output validation, ensuring data integrity across Active Directory, Entra ID, and LDAP exports.
Why this beats prompting it yourself
Standard prompting often hallucinates match rates or misses subtle attribute mismatches in large datasets. This skill uses a deterministic script to ensure every calculation is precise, repeatable, and audit-ready without manual estimation.
Use cases
- Reconciling monthly HR reports against Active Directory to find ghost accounts.
- Conducting emergency audits for terminated employee access during offboarding reviews.
- Cleaning up identity attribute data for an Entra ID migration or sync.
- Preparing identity reconciliation evidence for internal or external IT audits.
Known limitations
Does not perform automated remediation like disabling accounts. Shared accounts and service accounts are excluded by default. Requires human approval for all proposed actions.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
No automated remediation or live directory writes. Shared/service accounts excluded by default. Maximum of three clarification questions for missing feeds. Not a replacement for compliance audits.
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 1 day ago