CV Screening
Assesses a CV against a role: interview, maybe or no, with evidence-based reasons and two questions.
HR · produces a Review · built in, ready to run
What you give it
Whatever the job is about — a block of text, a URL, a name. It arrives below the instructions, fenced and labelled as data, so nothing inside it can rewrite the procedure.
Tools it uses
Restricted to these, and nothing else:
read_document
Fewer tools means fewer ways to do the job, which is what makes the result the same next week. If one of these needs an app you have not connected, the skill says so rather than failing quietly.
What it reads
This skill carries material of its own. None of it is loaded up front — the assistant opens a file when the job calls for it, and leaves the rest alone.
| File | What it holds |
|---|---|
references/inputs.md |
What to provide |
references/signals.md |
Evidence, not vocabulary |
The procedure it follows
This is the skill, in full. Add it to your own skills to change any of it.
Read the role first and write down its two or three non-negotiables before opening the CV, so the CV's vocabulary does not set the bar. Judge evidence, not keywords: a named system with its size and what it did counts, a technology list with no project attached does not. Interview means every non-negotiable is evidenced; maybe means one is unproven but not contradicted; no means one is clearly absent. Never let age, gender, nationality, photo, name, school prestige or unexplained date gaps touch the verdict, and do not mention them. Reply with Verdict, up to three Strengths and three Gaps each pointing at a line in the CV, and two questions only this candidate could answer. Mark the verdict provisional if the role was thin.
How to run it
| Where | How |
|---|---|
| Chat | "Run my CV Screening skill", or pick it from the + menu |
| Skills page | Find CV Screening under Library and press Add & Use |
| Automations | Invoke it on every trigger |
| API | POST /v1/skills/{id}/run — add it to your own skills first, then take the id from GET /v1/skills |
In chat, on the Skills page and in automations you do not have to add it first — a library skill runs as it is. Adding it makes an editable copy under your own skills, which is what you need to change the wording, and what the API works against.
New to skills? Start with what a skill is.
Open App