- Home
- Skills
- HR & Recruiting
- π Interview Loop Consistency Auditor
More screenshots
Works with the AI Agents you already use
π Interview Loop Consistency Auditor
Audit interview coverage, repeated questions, scorecard gaps and feedback timing against a supplied approved rubric without ranking candidates.
$19
π Interview Loop Consistency Auditor
Example session with this skill installed
Synthetic worked example
{
"as_of": "2026-09-09T12:00:00Z",
"rubric_approved": true,
"skills": [
{
"id": "s1"
},
{
"id": "s2"
}
],
"required_scorecard_fields": [
"conclusion",
"evidence"
],
"interviews": [
{
"id": "i1",
"interviewer": "reviewer-1",
"skill_ids": [
"s1"
],
"questions": [
"Describe a support triage example.",
" Describe a support triage example. "
],
"feedback_due_at": "2026-09-08T12:00:00Z",
"submitted_at": null,
"discussion_at": "2026-09-09T12:00:00Z",
"scorecard": {
"conclusion": "Seems excellent"
}
}
]
}
- Read your context and instructions
- Compiled the interview loop consistency
Interview process consistency
REVIEW β HUMAN REVIEW REQUIRED
Supplied records only; human review required. Not an employment decision.
- CONCLUSION_WITHOUT_EVIDENCE [i1]: Conclusion lacks a source locator; no candidate recommendation made.
- DISCUSSION_BEFORE_SCORING [i1]: Discussion precedes submitted independent scoring; review sequence.
- LATE_FEEDBACK [i1]: Feedback deadline exceeded.
- REPEATED_QUESTION [i1]: Exact normalized repeat of question in i1
- SCORECARD_FIELD_MISSING [i1]: Missing evidence
- UNSUBMITTED_EVALUATION [i1]: Feedback not submitted in supplied records.
- UNCOVERED_COMPETENCY [s2]: No interview covers approved competency.
Connects securely to your tools. The creator never sees your data.
About this skill
Audit interview coverage, repeated questions, scorecard gaps and feedback timing against a supplied approved rubric without ranking candidates. Supply the normalized local JSON described in the included input contract. Run the Python helper to receive coverage and findings tables, a human-review queue, summary and report. Whitespace-only required text is treated as missing; the fixed conclusion/evidence check requires a nonblank evidence locator. Repeated-question detection is exact after case and whitespace normalization. A locator does not authenticate evidence; timestamp order does not prove feedback contamination or unlawful bias. No candidate ranking or hire/no-hire recommendation. Package version 1.0.1 includes synthetic examples, executable tests and actual sample output. The JustHandled Labs paid skill license permits personal and internal organizational use; see LICENSE.txt for full terms.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for HR & Recruiting.
Repeated-question detection is exact after case and whitespace normalization.
Timestamp order does not prove feedback contamination or unlawful bias.
The helper audits the process, never ranks candidates or recommends hire/no-hire.
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 23 days ago
- Software
Python
Permissions
File Scopes
No secrets or provider connections needed by helper.