Skip to content
cccskills
FreePublished on GitHub

managing-daily-co

Use when working with Daily Co — daily.co video and audio API platform management for real-time video calls, rooms, recordings, and usage analytics. Use when monitoring active rooms, analyzing meeting quality, reviewing usage and billing, managing room configurations, or troubleshooting Daily.co video sessions.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md5.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Daily.co Management Skill

Manage and analyze Daily.co video/audio rooms, meetings, recordings, and usage.

API Conventions

Authentication

All API calls use Bearer token authentication, injected automatically.

Base URL

https://api.daily.co/v1

Core Helper Function

#!/bin/bash

daily_api() {
    local method="$1"
    local endpoint="$2"
    local data="${3:-}"

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

Output Rules

  • Target ≤50 lines per script output
  • Use jq to extract only needed fields
  • Never dump full API responses

Phase 1: Discovery

#!/bin/bash
echo "=== Domain Info ==="
daily_api GET "/" | jq '{domain_name: .domain_name, config: .config}'

echo ""
echo "=== Rooms ==="
daily_api GET "/rooms?limit=30" \
    | jq -r '.data[] | "\(.name)\t\(.privacy)\t\(.created_at[0:10])\tmax_participants:\(.config.max_participants // "unlimited")"' \
    | column -t | head -20

echo ""
echo "=== Active Meetings ==="
daily_api GET "/meetings?active=true&limit=20" \
    | jq -r '.data[] | "\(.room)\t\(.ongoing)\tparticipants:\(.max_participants)\tstarted:\(.start_time[0:16])"' \
    | head -15

Phase 2: Analysis

Meeting Analytics

#!/bin/bash
echo "=== Meeting Summary (last 7 days) ==="
daily_api GET "/meetings?timeframe_start=$(date -d '7 days ago' +%s)&timeframe_end=$(date +%s)&limit=100" \
    | jq '{
        total_meetings: (.data | length),
        avg_duration_min: (.data | map(.duration // 0) | if length > 0 then add / length / 60 | floor else 0 end),
        avg_participants: (.data | map(.max_participants // 0) | if length > 0 then add / length | floor else 0 end)
    }'

echo ""
echo "=== Room Usage Breakdown ==="
daily_api GET "/meetings?timeframe_start=$(date -d '7 days ago' +%s)&timeframe_end=$(date +%s)&limit=200" \
    | jq -r '.data[] | .room' | sort | uniq -c | sort -rn | head -15

echo ""
echo "=== Active Recordings ==="
daily_api GET "/recordings?limit=20" \
    | jq -r '.data[] | "\(.room_name)\t\(.duration)s\t\(.status)\t\(.start_ts[0:16])"' \
    | head -15

Room Health

#!/bin/bash
echo "=== Room Configurations ==="
daily_api GET "/rooms?limit=50" \
    | jq -r '.data[] | "\(.name)\t\(.privacy)\teject_at_room_exp:\(.config.eject_at_room_exp // false)\trecording:\(.config.enable_recording // "none")"' \
    | column -t | head -20

echo ""
echo "=== Rooms Without Expiry ==="
daily_api GET "/rooms?limit=100" \
    | jq -r '.data[] | select(.config.exp == null or .config.exp == 0) | "\(.name)\t\(.privacy)\tcreated:\(.created_at[0:10])"' \
    | head -10

Output Format

=== Domain: <domain_name> ===
Rooms: <count>  Active Meetings: <count>

--- Meeting Analytics (7d) ---
Total: <n>  Avg Duration: <n>min  Avg Participants: <n>

--- Room Usage ---
<room_name>: <n> meetings

--- Recordings ---
Total: <n>  Pending: <n>

Anti-Hallucination Rules

  1. NEVER assume resource names — always discover via CLI/API in Phase 1 before referencing in Phase 2.
  2. NEVER fabricate metric names or dimensions — verify against the service documentation or --help output.
  3. NEVER mix CLI commands between service versions — confirm which version/API you are targeting.
  4. ALWAYS use the discovery → verify → analyze chain — every resource referenced must have been discovered first.
  5. ALWAYS handle empty results gracefully — an empty response is valid data, not an error to retry.

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

Common Pitfalls

  • Timestamps: Use Unix epoch seconds for timeframe filters
  • Pagination: Use limit and starting_after cursor; default limit is 50
  • Rate limits: 300 requests/minute for most endpoints
  • Room names: Must be lowercase, alphanumeric with hyphens only

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

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

The English summary is being prepared. Showing the original description.

cloudthinker-ai/CloudSkills6Updated Apr 5, 2026

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

The English summary is being prepared. Showing the original description.

cloudthinker-ai/CloudSkills6Updated Apr 5, 2026

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.

The English summary is being prepared. Showing the original description.

cloudthinker-ai/CloudSkills6Updated Apr 5, 2026

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

The English summary is being prepared. Showing the original description.

cloudthinker-ai/CloudSkills6Updated Apr 5, 2026

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

The English summary is being prepared. Showing the original description.

cloudthinker-ai/CloudSkills6Updated Apr 5, 2026

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.

The English summary is being prepared. Showing the original description.

cloudthinker-ai/CloudSkills6Updated Apr 5, 2026

See all skills by cloudthinker-ai

Report a problem with this skill