메뉴
Screen job candidates from Greenhouse using AI-powered evaluation. Use when asked to "screen candidates", "review applicants", "run candidate screening", "check new applications", or "evaluate candidates".
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Email triage and organization system for Gmail. Use when user asks to "triage my inbox", "check my email", "process emails", "what needs my attention", "inbox zero", or any request to organize, classify, or act on emails. Provides GTD-style processing with autonomous actions for clear-cut items and surfaced decisions for ambiguous ones. Creates newsletter digests, drafts replies, and suggests bulk unsubscribes.
Review contracts, MSAs, SOWs, and NDAs. Verifies terms against internal context and delivers risk assessment.
Handle investor audit confirmations and quarterly portfolio reporting requests. Use when: (1) Email from auditor (PwC, KPMG, EY, CBIZ, Deloitte) requesting confirmation, (2) Investor asks for quarterly reporting (revenue, runway, cap table), (3) User asks to 'help with audits' or 'process audit requests', (4) Email contains 'audit confirmation' or 'investment confirmation'. Maps requests to standard company data and drafts accurate responses.
Deep verification agent that finds hidden errors in code, analysis, and architecture. Assumes nothing is correct, drills deep, and verifies every claim independently.
Expert advisor and thinking partner for strategic situations. Radically candid coaching.
Create shareable briefing documents from sessions, research, or learnings.
| name | candidate-screening |
| description | Screen job candidates from Greenhouse using AI-powered evaluation. Use when asked to "screen candidates", "review applicants", "run candidate screening", "check new applications", or "evaluate candidates". |
Goal: Identify candidates we'd be thrilled to have on the team. Not "can do the job" — candidates we're excited about.
"Our first 100 people are our cultural co-founders."
These traits apply to EVERY role. A candidate missing any of these is unlikely to be great.
What it is: Takes initiative. Makes things happen. Doesn't wait for permission or perfect conditions.
How to spot it:
Red flags:
What it is: Perseveres through hard things. Doesn't quit when it gets difficult.
How to spot it:
Red flags:
What it is: Demonstrable results. Outcomes, not just activities.
How to spot it:
Red flags:
What it is: Everyone should code, build, or have deep technical understanding.
How to spot it:
Red flags:
What it is: Uses AI tools daily, understands implications, sees opportunities.
How to spot it:
Red flags:
What it is: Writes clearly, explains complex ideas simply, collaborates well.
How to spot it (their APPLICATION is a sample!):
Red flags:
What it is: Top 1% in at least one domain. Demonstrable excellence.
How to spot it:
Red flags:
What it is: Curious, diverse interests, unique perspective. Someone you'd want at dinner.
How to spot it:
Red flags:
Beyond universal traits, each role has specific requirements:
If you have a screening tool (e.g., a Greenhouse integration script):
cd [YOUR_SCREENING_TOOL_PATH] && npm run screen -- --days-back 1 --min-score 70
Common variations:
# Last 7 days, specific role
npm run screen -- --days-back 7 --job-id [JOB_ID]
# Higher bar (80+), tag in Greenhouse
npm run screen -- --min-score 80 --tag-greenhouse
# All options
npm run screen -- --days-back 7 --min-score 75 --tag-greenhouse --send-slack
If you don't have a screening tool, pull candidates from Greenhouse manually or via the Greenhouse API and feed them to Claude for evaluation using the framework below.
cat [YOUR_SCREENING_TOOL_PATH]/output/daily-digest-$(date +%Y-%m-%d).md
For anyone scoring 75+, provide deeper analysis with links always included:
## [Name] — [Score]/100
**Links**: [Greenhouse](https://app4.greenhouse.io/people/[CANDIDATE_ID]/applications/[APP_ID]/redesign) | [LinkedIn](URL or "Not provided")
### Universal Traits Assessment
| Trait | Signal | Evidence |
| ------------- | -------- | ------------------------------- |
| High Agency | ✅/⚠️/🚩 | [specific quote or observation] |
| Grit | ✅/⚠️/🚩 | [specific quote or observation] |
| Impact | ✅/⚠️/🚩 | [specific quote or observation] |
| Technical | ✅/⚠️/🚩 | [specific quote or observation] |
| AI-Native | ✅/⚠️/🚩 | [specific quote or observation] |
| Communication | ✅/⚠️/🚩 | [specific quote or observation] |
| World-Class | ✅/⚠️/🚩 | [specific quote or observation] |
| Interesting | ✅/⚠️/🚩 | [specific quote or observation] |
### Role-Specific Fit
[Assessment against role requirements]
### Why We'd Be Thrilled
- [Specific exceptional signals]
### Questions to Probe
- [Specific areas needing verification]
### Verdict
[Must Interview / Worth Exploring / Pass]
Always conclude with a summary table including clickable links:
## Summary
| Candidate | Score | Verdict | Greenhouse | LinkedIn |
| --------- | ------- | --------- | ----------- | --------------------- |
| [Name] | [Score] | [Verdict] | [View](URL) | [Profile](URL) or N/A |
Add your Greenhouse job IDs here to filter screening by role:
| ID | Role |
|---|---|
| [JOB_ID_1] | [Role Name] |
| [JOB_ID_2] | [Role Name] |
| [JOB_ID_3] | Open Application |
"90% confidence that this person can do a job only 10% of candidates could do."
We're not asking "can they do the job?" We're asking "would we be thrilled to work with them every day?"
When in doubt, pass. Better to miss someone good than hire someone mediocre.