Agent Skills › pollinations/pollinations › candidate-evaluation

candidate-evaluation

GitHub

用于评估 GitHub 贡献者以招聘 MLOps 或工程角色。通过 API 获取用户仓库、PR 及代码数据，分析 Python、DevOps 及 GPU/ML 技能，生成包含评分、优缺点及录用建议的候选人档案。

.claude/skills/candidate-evaluation/SKILL.md pollinations/pollinations

Trigger Scenarios

评估候选人或贡献者研究 GitHub 个人资料用于招聘更新 CONTRIBUTORS.md 中的候选分析提及 'hiring', 'candidate', 'MLOps' 或 'evaluate contributor'

Install

npx skills add pollinations/pollinations --skill candidate-evaluation -g -y

More Options

Non-standard path

npx skills add https://github.com/pollinations/pollinations/tree/main/.claude/skills/candidate-evaluation -g -y

Use without installing

npx skills use pollinations/pollinations@candidate-evaluation

指定 Agent (Claude Code)

npx skills add pollinations/pollinations --skill candidate-evaluation -a claude-code -g -y

安装 repo 全部 skill

npx skills add pollinations/pollinations --all -g -y

预览 repo 内 skill

npx skills add pollinations/pollinations --list

SKILL.md

Frontmatter

{
    "name": "candidate-evaluation",
    "description": "Evaluate GitHub contributors for MLOps\/engineering roles. Use when analyzing candidates, researching GitHub profiles, or updating CONTRIBUTORS.md with hiring assessments.",
    "allowed-tools": "Read, Write, Edit, Grep, Bash(gh api:*), Bash(git:*)"
}

Candidate Evaluation Skill

Evaluate GitHub contributors for engineering roles at Pollinations.

When to Use

User asks to evaluate a contributor or candidate
User wants to research GitHub profiles for hiring
User needs to update CONTRIBUTORS.md with candidate analysis
User mentions "hiring", "candidate", "MLOps", or "evaluate contributor"

Evaluation Criteria

Must-Have Skills (Weight: High)

Python: Primary language proficiency
DevOps: Docker, CI/CD, infrastructure
GPU/ML Deployment: Model serving, inference optimization

Nice-to-Have Skills (Weight: Medium)

Kubernetes, vLLM, TGI
Quantization (GGUF, ONNX)
CI/CD pipelines (GitHub Actions)

Work Style Indicators (Weight: Medium)

PR size preference (small, focused = good)
Response time to reviews
Documentation quality
Test coverage habits

Evaluation Process

Gather Data via GitHub MCP or gh api:

# Get user repos
gh api users/{username}/repos --jq '.[].name'

# Search PRs in pollinations
gh api search/issues -X GET -f q='repo:pollinations/pollinations author:{username}'

# Search code for MLOps keywords
gh api search/code -X GET -f q='user:{username} docker OR kubernetes OR gpu OR vllm'

Analyze Repositories for:
- ML/AI projects (ComfyUI, HuggingFace, PyTorch)
- DevOps tooling (Docker, CI/CD, scripts)
- API/backend experience
- Star counts and activity
Check Pollinations Contributions:
- Merged PRs (high signal)
- Open issues/discussions
- Project submissions
Generate Profile with:
- Fit score (1-10)
- Strengths (bullet points)
- Weaknesses (bullet points)
- Key repositories table
- Hiring recommendation

Output Format

Use ASCII box art for visual appeal:

┌─────────────────────────────────────────────────────────────────────────────┐
│  FIT: X.X/10  │  GitHub: username  │  Repos: N  │  Focus: Area             │
└─────────────────────────────────────────────────────────────────────────────┘

✅ STRENGTHS

Point 1
Point 2

❌ WEAKNESSES

Point 1
Point 2

📦 KEY REPOS

Repo	Tech	What It Does

🎯 VERDICT: Recommendation

Skills Matrix Format

╔═══════════════════╦════════╦════════╦════════╦═══════════════╗
║     CANDIDATE     ║ Python ║ GPU/ML ║ Docker ║   FIT SCORE   ║
╠═══════════════════╬════════╬════════╬════════╬═══════════════╣
║ username          ║ █████  ║ ███    ║ ████   ║     X.X/10    ║
╚═══════════════════╩════════╩════════╩════════╩═══════════════╝

Legend: █ = Skill Level (1-5)