Screen Cv
Screen a CV against a role brief, scoring evidence on each must-have and nice-to-have while ignoring bias signals.
Install
$ agentstack add skill-riggdai-uniqent-screen-cv ✓ 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
Screen CV
- Read the role brief and extract must-haves (hard requirements) and nice-to-haves.
- Read the CV. Immediately discard any information unrelated to job performance (photo, age, marital
status, school prestige, address).
- For each must-have, locate explicit evidence in the CV. Note the line or section. If absent, mark
as "gap — probe in interview."
- Score four dimensions (0–10 each): relevant skills, demonstrated impact, culture-add signals,
growth trajectory.
- Write a two-to-three sentence evidence summary referencing specific CV content.
- List gaps (must-haves with no evidence found) as targeted interview questions, not disqualifiers.
- Output a structured candidate card: name (as written), scores, summary, gaps-as-questions.
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.