marketingby evolution-foundation
YouTube Report — Channel Analytics
evolution-foundation/social-youtube-report
YouTube analytics report — queries channel stats, recent videos, engagement rates, top content. Generates HTML report.
What it changes
Passed 12 of 19 test cases with the skill, and 6 of 19 without it.
Without skill30%
With skill61%
Checks it passed that the model alone missed
- Selects daily timeframe.
- Replaces {{REPORT_TYPE}} with YouTube Weekly.
- Selects monthly timeframe representing the last 30 days.
and 6 more in the full report
9 fixed5 passed either way7 still failing2 broke
- Pass-rate lift
- +30 pp
- Tokens
- -23%
- Agent turns
- 0%
- Response time
- -64%
Model gemini-3.6-flashMeasured 8/19/2026v114 of 23 cases passed with skill · 19 comparable
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptOur server automation runs 'make youtube-monthly'. What report interval does this command trigger?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Selects monthly timeframe representing the last 30 days. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md61 linessingle file
YouTube Report — Channel Analytics
Routine that pulls data from YouTube via /int-youtube and generates an HTML channel performance report.
Always respond in English.
Workflow
Step 1 — Determine period
Based on the command:
make youtube → período "daily" (snapshot do dia)make youtube-weekly → período "weekly" (últimos 7 dias)make youtube-monthly → período "monthly" (últimos 30 dias)
If called directly, ask or use "daily" as default.
Step 2 — Collect data
For each configured YouTube account:
# Stats do canal
python3 {project-root}/.claude/skills/int-youtube/scripts/youtube_client.py channel_stats
# Últimos vídeos com métricas
python3 {project-root}/.claude/skills/int-youtube/scripts/youtube_client.py recent_videos 1 20
# Resumo de todas as contas
python3 {project-root}/.claude/skills/int-youtube/scripts/youtube_client.py summary
Step 3 — Compare with previous period
Read previous report from workspace/social/reports/youtube/ if it exists. Calculate deltas:
- Inscritos: delta absoluto e %
- Views total: delta
- Engagement rate médio: delta
- Vídeos publicados no período
Track record
Benchmark
12 / 19
test cases passed, vs 6 / 19 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedevolution-foundation / evo-nexus
.claude/skills/social-youtube-report/SKILL.md
License NOASSERTIONImported 8/3/2026Version v1