Conflict of Interest Review Assistant
Analyzes disclosures to produce evidence-linked conflict assessments and mitigation plans for governance and HR.
$6.99
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsConflict of Interest Review Assistant
Example session with this skill installed
An employee on a 3-person hiring panel for a Senior Engineer role just declared their sibling is a candidate. They declared this before interviews start. Build a conflict review and mitigation plan.
- Read your context and instructions
- Compiled the conflict of interest
I have processed the declaration regarding the Senior Engineer recruitment panel. The assessment below outlines the conflict intersection and proposed safeguards.
Conflict of Interest Assessment
1. Scope and Decision Context
- Case Reference: HR-REC-2024-082
- Decision: Hiring of Senior Engineer (Job Ref: SE-99)
- Role: Interview Panel Member (1 of 3)
- Period: Interviews scheduled Oct 15-20, 2024
- Limits: Internal policy not provided; using provisional governance triage.
2. Evidence and Fact Register
| Ref | Fact or claim | Source/date | Evidence state | Missing verification |
|---|---|---|---|---|
| F1 | Sibling relationship | Employee Disclosure (Oct 10) | Declared | Verified HR link |
| F2 | Panel membership | Recruitment Plan | Documented | None |
| F3 | Candidate status | Application Portal | Confirmed | None |
3. Interest–Decision Intersection
| Interest | Decision touchpoint | Influence/access | Classification | Rationale |
|---|---|---|---|---|
| Family tie | Interview scoring | Direct (33% vote) | Actual/Direct | Sibling relationship creates direct personal interest in outcome. |
| Family tie | Shortlist access | Privileged | Perceived | Access to other candidates' data could yield unfair advantage. |
4. Preliminary Risk Triage
- Inherent Exposure: High. Direct familial link to a competitive process with limited panel size.
- Residual Exposure: Low (Pending mitigation).
- Uncertainty: High until panel substitution is confirmed.
5. Mitigation Options
| Action | Rationale | Owner | Timing | Verification | Approval |
|---|---|---|---|---|---|
| Full Recusal | Remove direct bias risk | HR Manager | Immediate | New panel list | Pending |
| Substitute Member | Maintain 3-person panel | Dept Head | By Oct 14 | Updated invite | Pending |
| Information Barrier | Prevent access to scores | IT Admin | Immediate | Access log | Proposed |
6. Approval and Escalation Record
- Independent Reviewer: HR Compliance Officer
- Decision Authority: Head of Engineering
- Proposed Disposition: Full recusal from all stages of recruitment SE-99.
7. Governance Summary
The disclosed sibling relationship represents a high inherent conflict. To preserve the integrity of the hiring process, the panel member must be replaced by an independent substitute before interviews commence.
8. Limitations and Disclaimer
This is a governance triage draft and does not constitute a legal finding or formal HR disciplinary record.
Next steps
- Appoint an independent substitute panel member.
- Formally document the recusal in the recruitment file.
- Restrict the original employee's access to the candidate management folder.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing conflicts of interest manually is a governance bottleneck that risks compliance breaches and biased decisions. This skill transforms raw disclosures into structured, defensible triage records for procurement, HR, and audit teams. It maps personal and financial interests against specific decision-making powers to identify actual, potential, and perceived conflicts.
What it does
- Evidence-linked assessment creates a formal record connecting disclosed interests to specific decision touchpoints and roles.
- Exposure classification categorizes risks as Low, Moderate, or High based on influence, access to privileged info, and proximity.
- Mitigation design generates proportionate safeguards such as recusal, information barriers, or independent substitute reviewers.
- Audit trail construction builds a fact-and-evidence log that distinguishes between corroborated facts and disputed claims.
- Decision registers produce a structured output for governance committees including approval hierarchies and monitoring plans.
How it works
- Define scope by inputting the specific procurement, hiring, or governance decision and the parties involved.
- Build the register by providing raw disclosures, policy snippets, and role descriptions for mapping.
- Analyze intersection to identify where personal interests overlap with decision authority or scoring influence.
- Generate mitigation to receive a structured table of actions, owners, and verification requirements for the governance file.
Frameworks & tools
This skill is framework-agnostic and processes data from policy documents, declaration forms, meeting minutes, and procurement logs. It adheres to standard governance, risk, and compliance (GRC) principles.
Why this beats prompting it yourself
Generic prompts often fail to distinguish between a disclosed interest and a proven act of misconduct. This skill enforces a strict triage logic that separates inherent from residual risk and ensures recusal happens at the scoring stage, not just at final sign-off.
Use cases
- Reviewing tender panel relationships to ensure bidder integrity.
- Assessing secondary employment disclosures for operational impact.
- Auditing existing conflict records for deficiencies in recusal logic.
- Drafting mitigation plans for board members with external directorships.
Known limitations
Does not make legal determinations or prove corruption. It requires a human professional to verify policy interpretation and issue final approvals. Identifiable sensitive data should be minimized.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Business & Operations.
Requires human professional for final policy approval. Does not prove misconduct or legal breaches. Sensitive private details should be anonymized by the user.
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 8 days ago