Shortlist
Rank screened candidates into a top-5 shortlist with evidence-based reasons and flagged gaps converted to interview questions.
Install
$ agentstack add skill-riggdai-uniqent-shortlist ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Shortlist
- Collect all candidate cards produced by the screen-cv skill.
- Compute a weighted total score: skills 40 %, impact 35 %, culture-add 15 %, growth 10 %.
- Rank candidates by total score descending. Select the top 5 (or fewer if fewer were screened).
- For each shortlisted candidate, write a one-paragraph rationale citing the strongest two or three
evidence points from their CV.
- For each shortlisted candidate, list their must-have gaps as explicit interview questions
(not rejection reasons).
- For candidates not shortlisted, include a one-sentence note on the primary differentiator that
placed them below the cut-off — keep this neutral and evidence-based.
- Output the ranked shortlist table followed by the per-candidate rationale sections.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: RiggdAI
- Source: RiggdAI/uniqent
- License: Apache-2.0
- Homepage: https://uniqent.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.