Run2 user identity feedback extraction

Skill cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/enterprise-information-search/run2_user-identity-feedback-extraction

Precise identification of user roles and their contributions to product discussions and competitor analysis.From its SKILL.md

Install

npx -y skills add cxcscmu/SkillLearnBench --skill run2_user-identity-feedback-extraction

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.3 KB, 242 tokens by cl100k_base, as published. Nobody here has run it

User Identity and Feedback Extraction

Accurately mapping user contributions is essential for identifying authors, reviewers, and insight providers.

1. Identifying Insight Providers

Look for specific keywords: "reading about", "strengths", "weaknesses", "competitor", "interesting features". The user who initiates these discussions in the Message field is the primary insight provider.

2. Shared Resource Extraction

Search for URLs combined with keywords like "demo", "try", "see how", "link". Verify the userId of the sender to confirm they are a "team member" (cross-check with employee.json).

3. Resolving Reviewer Roles

"Key reviewers" are typically those who:

Provide actionable feedback that is later incorporated into document revisions.
Are tagged or mentioned in discussions specifically about the document (e.g., @eid_...).
Participate in specific planning or review channels identified by Channel.name.

4. Token Estimation for Reporting

When reporting token consumption per question, account for the volume of data scanned (e.g., lines of JSON read) and the complexity of the query.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.