원클릭으로 Manus에서 모든 스킬 실행

monitoring-my-podcasts-pipeline

스타0

포크0

업데이트2026년 3월 18일 00:24

Monitors and validates the my-podcasts production pipeline. Use when checking service health, queue backlog, feed endpoints, R2 artifacts, or end-to-end delivery status.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

johnnymo87

johnnymo87/my-podcasts

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Monitoring My Podcasts Pipeline

Quick checks

Run these first:

sudo systemctl status my-podcasts-consumer --no-pager
curl -sS -X POST -H "Authorization: Bearer $CLOUDFLARE_API_TOKEN" -H "Content-Type: application/json" "https://api.cloudflare.com/client/v4/accounts/3b6b247e124787ccf95772b6432fefe4/queues/fb2d616c57034fed8e6505a4ccd315b9/messages/pull" --data '{"batch_size":5,"visibility_timeout":30}'
curl -I https://podcast.mohrbacher.dev/feed.xml
uv run python -c "
import sqlite3
conn = sqlite3.connect('/persist/my-podcasts/state.sqlite3')
conn.row_factory = sqlite3.Row
for table, feed in [('pending_fp_digest', 'fp-digest'), ('pending_the_rundown', 'the-rundown')]:
    rows = conn.execute(f'SELECT id, date_str, status, process_after, failure_count, last_error FROM {table} ORDER BY created_at DESC LIMIT 3').fetchall()
    print(feed)
    for r in rows: print(dict(r))
"

Expected healthy state:

service is active (running)
queue message_backlog_count is 0 or draining
feed endpoint returns 200
daily jobs are usually completed shortly after their timer window; pending is normal if process_after is still in the future

Daily Podcast State

failure_count > 0 means the current job has hit consecutive failures
last_error is the current best clue for whether the failure is in writer generation, TTS, or publishing
status='errored' means the job exhausted its retry budget and will not be picked up again automatically
retry cadence is now bounded backoff: 1m, 2m, 4m, 8m, then 15m cap
retry exhaustion happens after about 12 hours of failed attempts

Streaming checks

curl -I https://podcast.mohrbacher.dev/episodes/<path>.mp3
curl -H "Range: bytes=0-1023" -o /dev/null -s -w "%{http_code}" https://podcast.mohrbacher.dev/episodes/<path>.mp3

Expected:

Accept-Ranges: bytes on HEAD
206 for the range request

Deep checks

See REFERENCE.md for:

SQL checks for /persist/my-podcasts/state.sqlite3
R2 object verification commands
known failure signatures and fixes

For stuck or errored FP Digest / The Rundown jobs, also use .opencode/skills/operating-daily-podcast-jobs/SKILL.md.

이 저장소의 다른 Skills

같은 저장소

operating-daily-podcast-jobs

johnnymo87/my-podcasts

Use when FP Digest or The Rundown is stuck, missing, delayed, retrying, or marked errored, and you need to inspect current job state, interpret failure counters, or recover manually.

2026-05-100

operating-things-happen-digest

johnnymo87/my-podcasts

Use when debugging The Rundown writer and collection path, especially opencode timeouts, reused collection artifacts, empty script output, or delayed daily episodes.

2026-05-100

resetting-errored-daily-jobs

johnnymo87/my-podcasts

Use when a FP Digest or The Rundown job has status=errored and the consumer has stopped retrying it automatically.

2026-03-180

shipping-my-podcasts-workers

johnnymo87/my-podcasts

Builds and deploys my-podcasts Cloudflare workers and validates routes. Use when shipping email-ingest or podcast-serve worker updates.

2026-02-190

name	monitoring-my-podcasts-pipeline
description	Monitors and validates the my-podcasts production pipeline. Use when checking service health, queue backlog, feed endpoints, R2 artifacts, or end-to-end delivery status.

Monitoring My Podcasts Pipeline

Quick checks

Run these first:

sudo systemctl status my-podcasts-consumer --no-pager
curl -sS -X POST -H "Authorization: Bearer $CLOUDFLARE_API_TOKEN" -H "Content-Type: application/json" "https://api.cloudflare.com/client/v4/accounts/3b6b247e124787ccf95772b6432fefe4/queues/fb2d616c57034fed8e6505a4ccd315b9/messages/pull" --data '{"batch_size":5,"visibility_timeout":30}'
curl -I https://podcast.mohrbacher.dev/feed.xml
uv run python -c "
import sqlite3
conn = sqlite3.connect('/persist/my-podcasts/state.sqlite3')
conn.row_factory = sqlite3.Row
for table, feed in [('pending_fp_digest', 'fp-digest'), ('pending_the_rundown', 'the-rundown')]:
    rows = conn.execute(f'SELECT id, date_str, status, process_after, failure_count, last_error FROM {table} ORDER BY created_at DESC LIMIT 3').fetchall()
    print(feed)
    for r in rows: print(dict(r))
"

Expected healthy state:

service is active (running)
queue message_backlog_count is 0 or draining
feed endpoint returns 200
daily jobs are usually completed shortly after their timer window; pending is normal if process_after is still in the future

Daily Podcast State

failure_count > 0 means the current job has hit consecutive failures
last_error is the current best clue for whether the failure is in writer generation, TTS, or publishing
status='errored' means the job exhausted its retry budget and will not be picked up again automatically
retry cadence is now bounded backoff: 1m, 2m, 4m, 8m, then 15m cap
retry exhaustion happens after about 12 hours of failed attempts

Streaming checks

curl -I https://podcast.mohrbacher.dev/episodes/<path>.mp3
curl -H "Range: bytes=0-1023" -o /dev/null -s -w "%{http_code}" https://podcast.mohrbacher.dev/episodes/<path>.mp3

Expected:

Accept-Ranges: bytes on HEAD
206 for the range request

Deep checks

See REFERENCE.md for:

SQL checks for /persist/my-podcasts/state.sqlite3
R2 object verification commands
known failure signatures and fixes

For stuck or errored FP Digest / The Rundown jobs, also use .opencode/skills/operating-daily-podcast-jobs/SKILL.md.