Works with the AI Agents you already use
change risk and collision analyzer
This skill identifies scheduling conflicts, freeze window violations, and sequence errors in change management calendars.
$2.99
change risk and collision analyzer
Example session with this skill installed
Check these changes for conflicts and risk: CHG001 (WebSvc, Dec 5 22:00-23:00, Ready), CHG002 (DB-Svc, Dec 5 21:30-22:30, Draft). DB-Svc is a predecessor. Access scope: all services.
- Read your context and instructions
- Compiled the change risk
I have analyzed the provided change records (E1) against the specified access scope. The analysis detected a collision and a sequencing error.
Change Risk and Collision Analysis — DevOps Team, 2026-12-05
1. Scope, sources and assumptions
- Sources: E1 (User supplied change list).
- Access Scope: All services (Authorized).
- Summary: 2 changes analyzed, 0 excluded.
- Assumptions: Times are in local format as provided in E1.
2. Collisions
| ID | Change A | Change B | Relation | Severity | Timing | Overlap min | Gap min |
|---|---|---|---|---|---|---|---|
| COL-01 | CHG001 | CHG002 | Dependency | High | Overlap | 30 | 0 |
3. Window, sequence and approval findings
Dependency Findings
| ID | Change | Detail |
|---|---|---|
| SEQ-01 | CHG001 | Predecessor CHG002 ends after CHG001 starts. |
Approval Findings
| ID | Change | Detail |
|---|---|---|
| APP-01 | CHG002 | Change is in 'Draft' status; missing final approval. |
4. Change risk scores
| Change | Start | End | Score | Band | Downstream | Main factors |
|---|---|---|---|---|---|---|
| CHG001 | 22:00 | 23:00 | 65 | Medium | High | Dependency collision, Service Tier |
| CHG002 | 21:30 | 22:30 | 40 | Low | Medium | Draft status, Logic overlap |
5. Proposed actions (drafts)
| ID | Action | Change ids | Candidate start | Detail |
|---|---|---|---|---|
| ACT-01 | Reschedule | CHG001 | 22:45 | draft, requires human approval. Move after CHG002 completion. |
| ACT-02 | Approve | CHG002 | n/a | draft, requires human approval. Transition from Draft to Ready. |
6. Warnings and data gaps
risk_score_undefined: Rollback plan not provided for CHG002; using default weights.
7. Items for human review
Analytical estimate — validation required: Collision COL-01 suggests a high probability of deployment failure due to shared resource locking.
- Management decision required: Approval of CHG002 is required before CHG001 can proceed.
This analysis supports, and does not replace, the change authority's judgment and decision.
Next steps
- Review the proposed start time for CHG001 to ensure it clears the DB-Svc maintenance window.
- Confirm the rollback procedure for CHG002 to refine the risk score.
- Submit the analysis report to the CAB lead for final sign-off.
Connects securely to your tools. The creator never sees your data.
About this skill
This skill identifies scheduling conflicts, freeze window violations, and sequence errors in change management calendars. It solves the problem of manual, error-prone change advisory reviews where overlapping updates to dependent services are often missed. By processing change records through a deterministic script, it provides rule-based risk scoring and collision detection without manual guesswork.
What it does
- Detects collisions by identifying overlapping change windows for the same or dependent CIs and services.
- Validates windows against maintenance schedules and global freeze periods to prevent unauthorized downtime.
- Analyzes dependencies to spot predecessor sequencing problems where a prerequisite change is scheduled after a dependent one.
- Scores change risk using a rule-based engine that evaluates impact, outage expectations, and rollback plans.
- Flags approval gaps by identifying planned changes that lack the necessary recorded authorizations.
How it works
- Source Registration: The user provides change records and service maps, which are assigned unique source identifiers.
- Scope Validation: The agent confirms the access scope to ensure only authorized services are analyzed.
- Automated Analysis: The agent generates a structured request and executes a Python script to perform the deterministic calculations.
- Report Generation: A structured report is produced, categorizing findings into collisions, window violations, and risk bands.
Frameworks & tools
This skill uses a Python-based analysis engine (scripts/run.py) and follows a strict JSON schema for input and output processing.
Why this beats prompting it yourself
Generic prompts often fail to catch subtle timing overlaps or complex service dependency chains. This skill uses a script to ensure every calculation is precise, repeatable, and follows a consistent scoring logic that doesn't vary between sessions.
Use cases
- Reviewing a weekly change calendar for collisions before a CAB meeting.
- Checking if a high-impact emergency change overlaps with an infrastructure freeze.
- Auditing planned sequences to ensure database updates occur before application deployments.
- Generating draft risk scores for new change requests based on historical service tiers.
Known limitations
Does not support multi-timezone analysis in a single run. Actions are drafts only and cannot edit tickets or approve changes directly. Risk scores require specific data fields or they return as undefined.
Requires local date-times in a single timezone. Does not verify external data. Proposed actions are drafts and cannot modify live ITSM records or bypass human approval.
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 any payment.
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