---
name: recruitment-evidence-organization
description: "Organize job-relevant candidate evidence for a human reviewer without ranking or selecting people. Use when the user requests recruitment evidence organization. Select relevant methods for the requested outcome; unrelated tasks do not require this skill."
metadata:
  version: "1.0.0"
---

# Recruitment Evidence Organization

Organize job-relevant candidate evidence for a human reviewer without ranking or selecting people.

## OLLIE Runtime integration

Use this capability under the active OLLIE Operator. Read live Workspace Context and tenant bindings for client facts and required inputs. This generic package contains no client configuration. Consume ask-ollie-authority-core for authority, outloop-access-fallback for access and recovery, email-lifecycle-core for communication, and the bootstrapper Runtime Contract for ownership, scheduling and completion. Preserve domain constraints; this Skill creates no competing execution path. Use one method, combine skills, or fill missing steps with authorized tools as the task requires.

External access uses the active Workspace’s approved Outloop capabilities. Never request, read, embed or expose credentials. A service named in a method is a possible dependency, not an access grant. Local file and application work uses the host’s authorized tools.

## Required inputs

- Role criteria
- Authorized candidate-provided material
- Required evidence fields
- Retention policy

## Methods

### Extract job-relevant evidence

Extract only job-relevant qualifications and evidence from authorized materials. Separate a candidate’s statement from independently verified evidence.

### Apply consistent fields

Use the same evidence fields for every candidate and flag missing information without inferring protected or sensitive traits.

### Prepare neutral questions

Prepare neutral follow-up questions tied to role requirements. Do not generate candidate rankings, suitability scores, acceptance decisions or rejection messages.

### Return factual comparisons

Return a factual comparison and source references for human judgment. Keep personal information in the authorized workspace and exclude it from reusable templates.

## Completion

Verify findings against source evidence and read back the resulting artifact or authorized change. Report inputs used, methods selected, output location, assumptions and unresolved dependencies. Do not report a plan, queue entry, draft, test fixture or accepted request as a completed external action. Use the task’s requested format; if a tool is unavailable, finish independent work and identify the exact unfulfilled deliverable.

## Test before relying on it

Read [the synthetic evaluation cases](references/evaluation.md) for activation, output and isolation checks. These cases are test instructions, not evidence that a host or provider test has passed.