Works with the AI Agents you already use
change request completeness checker
Low-quality change requests (RFCs) lead to delayed approvals, failed implementations, and Change Advisory Board (CAB) bottlenecks.
$2.99
change request completeness checker
Example session with this skill installed
Review the completeness of RFC-882 and RFC-883. Access is granted for the reviewer role for all services. Lead time is 5 days. Objective for 882: Migrate database. Rollback: Restore from snapshot.
- Read your context and instructions
- Compiled the change request completeness
The completeness check for the requested change records has been finalized using the deterministic audit script.
Change Request Completeness Review — Global Ops, 2024-05-20
1. Scope, sources and assumptions
- Sources: E1 (User provided RFC text).
- Reviewer Role: reviewer_role.
- Access Scope: Granted for all services (
*). - Thresholds:
min_lead_days: 5(default),min_objective_words: 5(default). - Methodology: Rules are based on the skill's original wording and deterministic logic.
2. Completeness summary
| Change | Type | Risk | Score | Readiness | Failed | Not assessed |
|---|---|---|---|---|---|---|
| RFC-882 | Normal | Medium | 0.7450 | Needs Work | 3 | 0 |
| RFC-883 | Normal | Low | 0.4200 | Incomplete | 6 | 0 |
Readiness Counts: Needs Work: 1, Incomplete: 1.
Mean Score: 58.25%
3. Findings by change
RFC-882
| Rule | Severity | Status | Finding |
|---|---|---|---|
| R-102 | Major | Fail | Objective is under 5 words. |
| R-501 | Minor | Fail | Test environment not specified. |
| R-604 | Critical | Fail | Rollback duration exceeds planned window. |
RFC-883
| Rule | Severity | Status | Finding |
|---|---|---|---|
| R-201 | Critical | Fail | Missing business justification. |
| R-405 | Major | Fail | Affected services not found in catalogue. |
4. Records excluded or not assessed
None.
5. Warnings and data quality
invalid_schedule: RFC-882 planned window is shorter than implementation_minutes + rollback_duration.
6. Draft actions and items for human review
- Draft: Request expanded objective for RFC-882 (requires human approval).
- Management decision required: Approval for RFC-883 despite missing service mapping.
- Analytical estimate — validation required: Estimated that RFC-882 requires a 120-minute window extension.
This review supports, and does not replace, the change manager's and the approvers' judgment.
Next steps
- Update RFC-882 with a detailed objective and extended window.
- Provide the service catalogue IDs for the services affected by RFC-883.
- Re-run the audit once mandatory fields are populated.
Connects securely to your tools. The creator never sees your data.
About this skill
Low-quality change requests (RFCs) lead to delayed approvals, failed implementations, and Change Advisory Board (CAB) bottlenecks. This skill enforces structural discipline by auditing change requests against a deterministic 25-rule set before they reach human reviewers.
It eliminates the manual labor of checking for missing rollback plans, insufficient lead times, or invalid test environments. By running a dedicated Python script against your RFC data, the agent produces a weighted completeness score and a readiness classification. It focuses strictly on presence and consistency, ensuring every request has a stated objective, justification, and workable implementation window.
What it does
- Structure auditing validates the presence of objectives, justifications, and success criteria.
- Service verification cross-references affected service IDs against your provided service catalogue.
- Schedule analysis checks for valid lead times and ensures windows accommodate both implementation and rollback.
- Readiness scoring computes a weighted completeness percentage (0-100%) for every change record.
- Gap identification flags specific rule violations with severity levels and rule IDs for easy remediation.
- Multilingual support processes and responds to requests in both English and French.
How it works
- Data Ingestion reads your RFC material and maps it to a standard JSON schema, including access scopes and service catalogues.
- Script Execution runs a deterministic audit via
scripts/run.pyto evaluate the records against 25 specific rules. - Status Handling interprets script outcomes to identify completed audits, data warnings, or access denials.
- Reporting generates a structured Markdown review including completeness tables, findings per change, and draft actions.
Frameworks & tools
This skill utilizes a self-contained Python 3 script (scripts/run.py) and JSON schema validation. It operates on standard ITSM data structures (Change ID, Type, Risk, Service IDs).
Why this beats prompting it yourself
Generic prompts often hallucinate missing data or give inconsistent scores based on the model's "mood." This skill uses a deterministic script to ensure two identical RFCs always receive the exact same score and findings, providing the objective evidence required for CAB audits.
Use cases
- Pre-CAB screening to filter out incomplete requests before they waste the committee's time.
- Request remediation to give developers a clear list of missing fields and schedule gaps.
- Audit readiness to maintain a historical record of change request quality scores.
- Rollback verification to ensure every change includes a feasible, timed recovery plan.
Known limitations
Does not judge technical soundness or business risk. Requires an explicit access scope to process records. Does not integrate directly with ITSM APIs; requires JSON or text input.
Requires manual input of access scope. Does not judge technical feasibility or approve changes. Only checks presence and consistency based on a fixed 25-rule set.
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