본문으로 건너뛰기
cccskills
무료GitHub에 공개

managing-codeium

Use when working with Codeium — codeium (Windsurf) AI coding assistant management and analytics. Covers team seat management, usage tracking, language analytics, editor adoption metrics, security policy configuration, and enterprise deployment review. Use when managing Codeium/Windsurf licenses, reviewing team adoption, or analyzing AI-assisted coding productivity.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md5.4 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Codeium (Windsurf) AI Coding Assistant Management Skill

Manage Codeium team settings, seats, usage analytics, and security policies.

Core Helper Functions

#!/bin/bash

# Codeium API helper
codeium_api() {
    local method="${1:-GET}"
    local endpoint="$2"
    local data="${3:-}"

    if [ -n "$data" ]; then
        curl -s -X "$method" \
            -H "Authorization: Bearer ${CODEIUM_API_KEY}" \
            -H "Content-Type: application/json" \
            "https://api.codeium.com/v1/${endpoint}" \
            -d "$data"
    else
        curl -s -X "$method" \
            -H "Authorization: Bearer ${CODEIUM_API_KEY}" \
            "https://api.codeium.com/v1/${endpoint}"
    fi
}

MANDATORY: Discovery-First Pattern

Always discover team and subscription info before querying specifics.

Phase 1: Discovery

#!/bin/bash

echo "=== Codeium Team Info ==="
codeium_api GET "team" | jq '{
    team_name: .name,
    plan: .plan,
    member_count: .member_count,
    seat_limit: .seat_limit
}'

echo ""
echo "=== Team Members ==="
codeium_api GET "team/members?limit=30" | jq -r '
    .members[] | "\(.email)\trole=\(.role)\tstatus=\(.status)\tlast_active=\(.last_active_at // "never")"
' | column -t | head -20

echo ""
echo "=== Subscription Details ==="
codeium_api GET "team/subscription" | jq '{
    plan: .plan,
    status: .status,
    seats_used: .seats_used,
    seats_total: .seats_total,
    renewal_date: .renewal_date
}'

Phase 2: Analysis

#!/bin/bash

echo "=== Usage Analytics ==="
codeium_api GET "team/analytics/usage?period=30d" | jq '{
    total_completions: .total_completions,
    total_acceptances: .total_acceptances,
    acceptance_rate: .acceptance_rate,
    active_users: .active_users,
    total_lines_generated: .total_lines_generated
}'

echo ""
echo "=== Language Breakdown ==="
codeium_api GET "team/analytics/languages?period=30d" | jq -r '
    .languages[:10][] | "\(.language)\tcompletions=\(.completions)\tacceptances=\(.acceptances)\trate=\(.acceptance_rate)%"
' | column -t

echo ""
echo "=== Editor Distribution ==="
codeium_api GET "team/analytics/editors?period=30d" | jq -r '
    .editors[] | "\(.editor)\tusers=\(.active_users)\tcompletions=\(.completions)"
' | column -t

echo ""
echo "=== Security Policies ==="
codeium_api GET "team/policies" | jq '{
    telemetry: .telemetry_enabled,
    context_awareness: .context_awareness,
    allowed_domains: .allowed_domains,
    blocked_repos: .blocked_repos
}' 2>/dev/null | head -15

echo ""
echo "=== Inactive Members (30d) ==="
codeium_api GET "team/members?limit=100" | jq -r '
    [.members[] | select(.last_active_at == null or (.last_active_at | fromdateiso8601 < (now - 2592000)))] |
    .[:10][] | "\(.email)\tlast_active=\(.last_active_at // "never")"
' | column -t

Output Rules

  • TOKEN EFFICIENCY: Target 50 lines per output
  • Aggregate usage by period, not individual completions
  • Never expose individual developer productivity rankings

Anti-Hallucination Rules

  • NEVER guess team or member details — always query API
  • NEVER fabricate usage metrics — query actual analytics data
  • NEVER assume API availability — Codeium Teams/Enterprise APIs may differ

Safety Rules

  • NEVER add or remove members without explicit user confirmation
  • NEVER change security policies without user approval
  • NEVER modify context awareness settings without user consent
  • Usage data may be sensitive — respect privacy

Output Format

Present results as a structured report:

Managing Codeium Report
═══════════════════════
Resources discovered: [count]

Resource       Status    Key Metric    Issues
──────────────────────────────────────────────
[name]         [ok/warn] [value]       [findings]

Summary: [total] resources | [ok] healthy | [warn] warnings | [crit] critical
Action Items: [list of prioritized findings]

Target ≤50 lines of output. Use tables for multi-resource comparisons.

Counter-Rationalizations

ShortcutCounterWhy
"I'll skip discovery and check known resources"Always run Phase 1 discovery firstResource names change, new resources appear — assumed names cause errors
"The user only asked for a quick check"Follow the full discovery → analysis flowQuick checks miss critical issues; structured analysis catches silent failures
"Default configuration is probably fine"Audit configuration explicitlyDefaults often leave logging, security, and optimization features disabled
"Metrics aren't needed for this"Always check relevant metrics when availableAPI/CLI responses show current state; metrics reveal trends and intermittent issues
"I don't have access to that"Try the command and report the actual errorAssumed permission failures prevent useful investigation; actual errors are informative

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Cloudflare GraphQL Analytics for zone traffic, firewall events, Workers metrics, and schema exploration. Use when querying Cloudflare analytics data or exploring the GraphQL API.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

cloudthinker-ai/CloudSkills62026년 4월 5일 업데이트

Use when working with Alloydb — google AlloyDB instance analysis, query insights, columnar engine optimization, maintenance windows, and cluster health.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

cloudthinker-ai/CloudSkills62026년 4월 5일 업데이트

Use when working with Aqua — aqua Security platform analysis. Covers container runtime protection, image assurance policies, compliance frameworks, vulnerability management, workload protection, and registry scanning. Use when analyzing container security posture, reviewing image compliance, investigating runtime alerts, or auditing security policies.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

cloudthinker-ai/CloudSkills62026년 4월 5일 업데이트

Use when working with Bigquery — google BigQuery job analysis, slot utilization, cost analysis, dataset management, and query optimization.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

cloudthinker-ai/CloudSkills62026년 4월 5일 업데이트

Use when working with Cassandra — apache Cassandra keyspace analysis, compaction strategies, repair status, nodetool operations, and cluster health monitoring.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

cloudthinker-ai/CloudSkills62026년 4월 5일 업데이트

Use when working with Checkov — checkov infrastructure-as-code security scanning. Covers Terraform, CloudFormation, Kubernetes, and Dockerfile scanning, policy management, custom checks, compliance frameworks, and suppression management. Use when scanning IaC for security misconfigurations, evaluating compliance, managing custom policies, or reviewing scan results.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

cloudthinker-ai/CloudSkills62026년 4월 5일 업데이트

cloudthinker-ai의 스킬 모두 보기

이 스킬의 문제 신고