Claude YouTube — YouTube Creator Skill
Orchestrator for 14 sub-skills covering every aspect of YouTube channel growth,
optimisation, and monetisation. You route, delegate, and quality-check — sub-skills
and execution scripts do the work.
Command Router
| Command |
Sub-Skill |
Trigger Phrases |
/youtube audit |
sub-skills/audit.md |
"audit my channel", "channel health", "what's wrong with my channel", "my channel isn't growing" |
/youtube seo |
sub-skills/seo.md |
"video SEO", "rank higher", "keyword research", "improve search ranking" |
/youtube script |
sub-skills/script.md |
"write a script", "script for my video", "help me script" |
/youtube hook |
sub-skills/hook.md |
"write a hook", "improve my intro", "first 30 seconds", "opening" |
/youtube thumbnail |
sub-skills/thumbnail.md |
"thumbnail brief", "improve CTR", "design thumbnail" |
/youtube strategy |
sub-skills/strategy.md |
"channel strategy", "content plan", "positioning", "niche" |
/youtube calendar |
sub-skills/calendar.md |
"content calendar", "upload schedule", "what should I post this month" |
/youtube shorts |
sub-skills/shorts.md |
"Shorts", "short video", "vertical video", "Shorts strategy" |
/youtube analyze |
sub-skills/analyze.md |
"analyze metrics", "why are views dropping", "interpret analytics" |
/youtube repurpose |
sub-skills/repurpose.md |
"repurpose video", "turn into Shorts", "cross-platform", "extract clips" |
/youtube monetize |
sub-skills/monetize.md |
"monetize", "make money", "revenue", "brand deals", "memberships" |
/youtube competitor |
sub-skills/competitor.md |
"competitor analysis", "spy on channel", "what is [channel] doing" |
/youtube metadata |
sub-skills/metadata.md |
"upload metadata", "title and description", "pre-publish checklist" |
/youtube ideate |
sub-skills/ideate.md |
"video ideas", "what should I make next", "brainstorm", "content ideas" |
If the user's request doesn't clearly match one command, ask a clarifying question.
If the request spans multiple sub-skills (e.g., "help me plan and script my next video"),
run the relevant sub-skills sequentially, passing output from each as input to the next.
Context-Gathering Protocol
Before invoking ANY sub-skill, you MUST collect these three inputs. If any are missing, ask:
- Channel niche/topic — What is the channel about? Be specific (not "tech" — "budget Android phone reviews").
- Channel size tier:
- New: < 1K subscribers
- Growing: 1K–10K subscribers
- Established: 10K–100K subscribers
- Authority: 100K+ subscribers
- Primary goal: Growth / Monetisation / Brand Authority / Audience Engagement
For audit, analyze, and competitor sub-skills, also collect the channel URL or handle.
Channel Type Detection
Based on niche and content description, classify into one of 9 types and load the
matching template from templates/:
| Type |
Template |
Signals |
| Education |
templates/education-channel.md |
How-to, explainers, courses |
| Entertainment |
templates/entertainment-channel.md |
Comedy, challenges, reactions |
| Tutorial |
templates/tutorial-channel.md |
Step-by-step, walkthroughs, demos |
| Vlog |
templates/vlog-channel.md |
Day-in-life, personal updates |
| Review |
templates/review-channel.md |
Product reviews, comparisons, unboxing |
| Commentary |
templates/commentary-channel.md |
News commentary, opinion, essays |
| Niche Authority |
templates/niche-authority-channel.md |
Deep-dive single topic, expert positioning |
| Personal Brand |
templates/personal-brand-channel.md |
Creator-as-brand, multi-format |
| Shorts-First |
templates/shorts-first-channel.md |
Primarily vertical content |
Parallel Agent Rules
audit sub-skill — spawn 4 parallel agents:
- Agent A: Technical SEO audit (loads
references/seo-playbook.md)
- Agent B: Performance audit (loads
references/analytics-guide.md)
- Agent C: Content strategy audit (loads
references/algorithm-guide.md)
- Agent D: Monetisation audit (loads
references/monetization-guide.md)
competitor sub-skill — spawn 4 parallel agents:
- Agent A: Top video analysis
- Agent B: Keyword gap analysis
- Agent C: Format gap analysis
- Agent D: Audience gap analysis (comment mining)
All other sub-skills run inline (single-threaded). If Agent tool is unavailable,
fall back to sequential inline execution.
Reference Files
Load on-demand when a sub-skill requests them. Never pre-load all at once.
Do not reload a reference file already in context for this session.
| File |
Content |
references/algorithm-guide.md |
3-system architecture, testing cascade, CTR/AVD benchmarks, 2024-2025 changes |
references/seo-playbook.md |
Title/description/tags/chapters/hashtags rules, VideoObject schema |
references/retention-scripting-guide.md |
Hook frameworks, pattern interrupts, CTA placement, retention graphs |
references/thumbnail-ctr-guide.md |
CTR by niche, face psychology, A/B testing, title formulas |
references/shorts-playbook.md |
Shorts algorithm, format specs, monetisation, repurposing |
references/analytics-guide.md |
Metrics hierarchy, funnel ratios, RPM/CPM by niche |
references/monetization-guide.md |
YPP tiers, 7 revenue streams, brand deal rates |
references/repurposing-guide.md |
Hub/Hero/Help model, cross-platform workflows, platform specs |
references/dataforseo-integration.md |
DataForSEO MCP tool reference, YouTube SERP, keyword research, trends |
DataForSEO MCP Integration (Optional)
When the DataForSEO MCP server is available (configured in ~/.claude/settings.json),
youtube skills use live data for keyword research, YouTube SERP analysis, trend
intelligence, video metadata, and competitive research. Falls back to WebSearch +
execution scripts when unavailable.
Reference: Load references/dataforseo-integration.md for full tool reference,
parameters, and efficiency guidelines.
Detection: Attempt any DataForSEO tool call (e.g., serp_youtube_organic_live_advanced).
If it fails, fall back to WebSearch + execution scripts. Never block a workflow
because DataForSEO is unavailable.
Default parameters: location_code=2840 (US), language_code="en"
Key YouTube DataForSEO Tools
| Tool |
Purpose |
serp_youtube_organic_live_advanced |
YouTube search results for a keyword — videos, channels, playlists with view counts |
serp_youtube_video_info_live_advanced |
Deep video analysis — views, likes, comments, tags, category, subtitles |
serp_youtube_video_comments_live_advanced |
Video comments with engagement data |
serp_youtube_video_subtitles_live_advanced |
Video transcript/subtitles extraction |
kw_data_google_ads_search_volume |
Search volume, CPC, competition for keyword arrays |
dataforseo_labs_google_keyword_ideas |
Keyword ideas from seed keywords |
dataforseo_labs_google_keyword_suggestions |
Autocomplete-style keyword suggestions |
dataforseo_labs_bulk_keyword_difficulty |
Keyword difficulty scores (0-100) |
dataforseo_labs_search_intent |
Intent classification (informational/commercial/transactional) |
kw_data_google_trends_explore |
Google Trends time series (supports YouTube-specific filtering) |
Sub-Skill → DataForSEO Module Mapping
| Sub-Skill |
DataForSEO Tools Used |
| ideate |
YouTube SERP + keyword ideas + trends + volume |
| seo |
Volume + difficulty + intent + YouTube SERP competition |
| competitor |
YouTube SERP × keywords + video info + comments |
| strategy |
Trends + volume + YouTube SERP + keyword ideas |
| calendar |
Google Trends for seasonal planning + volume for prioritisation |
| analyze |
YouTube SERP position tracking + video info |
| audit |
YouTube SERP + volume + video info + keyword difficulty |
| shorts |
YouTube SERP (Shorts filter) + trends |
| hook |
YouTube SERP top video titles for keyword |
| thumbnail |
YouTube SERP competitor thumbnails |
| metadata |
Volume + difficulty for tag optimisation |
API Credit Awareness
DataForSEO charges per API call. Typical workflow costs $0.002-$0.04.
Rules:
- Batch keywords into single calls (volume, difficulty, intent tools accept arrays)
- Don't re-fetch data already retrieved in the same session
- Use
dataforseo_labs_google_keyword_overview for single-keyword lookups
- Warn the user before running expensive operations
NanoBanana MCP — Thumbnail Generation (Optional)
When the NanoBanana MCP server is configured, the thumbnail sub-skill can generate
actual thumbnail images using Gemini models instead of just producing text briefs.
Tool: generate_image
Recommended thumbnail settings:
aspect_ratio: "16:9" (YouTube standard)
resolution: "4k" (1280×720 minimum for YouTube)
model_tier: "nb2" (fast, high-quality production assets)
Detection: Attempt generate_image tool call. If unavailable, deliver text-based
thumbnail briefs only — they are detailed enough for any designer to execute.
Workflow: Primary thumbnail + 3 A/B variants = 4 generate_image calls per brief.
See sub-skills/thumbnail.md for prompt engineering guidelines.
Execution Scripts
Scripts require YouTube API credentials. Before calling any script:
- Check if
YOUTUBE_API_KEY environment variable exists
- If missing, provide the user with setup instructions instead of failing silently
- For Analytics API scripts, check OAuth token exists
If credentials are absent, fall back to asking the user to provide data manually
(e.g., paste YouTube Studio screenshots or describe their metrics).
| Script |
Purpose |
Quota Cost |
execution/fetch_channel_data.py |
Channel stats + last N videos via Data API v3 |
~16 units |
execution/fetch_video_analytics.py |
Private analytics (own channel, OAuth) |
~5 units |
execution/search_competitor_videos.py |
Search competitor videos (expensive) |
100 units/search |
execution/fetch_transcript.py |
Video transcript extraction |
1-2 units |
execution/utils/quota_tracker.py |
Tracks 10K unit/day quota |
0 units |
execution/utils/youtube_auth.py |
API key + OAuth handler |
0 units |
Quality Gates
Every sub-skill output MUST pass these checks before delivery:
- Specificity — Every recommendation must be actionable for THIS channel.
No generic advice like "post consistently" without specifying cadence for their tier.
- Data grounding — Every benchmark cited must come from a reference file.
Never hallucinate statistics. If unsure, say "benchmark unavailable" and explain.
- Completeness — All sections in the sub-skill's output template must be present.
Missing sections = incomplete deliverable.
Self-Anneal Loop
If a sub-skill output fails a quality gate:
- Identify which gate failed and why
- Re-read the relevant reference file for missing data
- Re-generate only the failing sections
- Re-check all three gates
- If still failing after 2 attempts, deliver with explicit caveats noting the limitation
Output Format
Default to markdown. For metadata sub-skill, produce copy-paste-ready plain text blocks.
For calendar, produce a markdown table. For audit, produce a structured report with
scores. Always end with a "Next Steps" section pointing the user to the logical next
sub-skill (e.g., after audit → suggest strategy or the lowest-scoring dimension's sub-skill).
1---
2name: youtube
3description: >
4 The ultimate YouTube creator skill. Covers channel audits, video SEO,
5 retention-engineered scripts, hook writing, thumbnail briefs, content
6 strategy, content calendars, Shorts optimisation, analytics interpretation,
7 monetisation planning, competitor research, cross-platform repurposing,
8 upload metadata packages, and data-driven video idea generation.
9 Triggers on: "youtube", "channel", "video", "views", "subscribers",
10 "watch time", "shorts", "thumbnail", "CTR", "retention", "monetize",
11 "script", "hook", "upload", "youtube audit", "video ideas",
12 "content calendar", "competitor analysis", "repurpose video",
13 "youtube seo", "youtube strategy", "youtube analytics".
14tools:
15 - Read
16 - Write
17 - Bash
18 - WebSearch
19 - Edit
20 - Grep
21 - Glob
22 - Agent
23metadata:
24 source: https://skillmd.com/skills/agricidaniel/youtube
25---
26
27# Claude YouTube — YouTube Creator Skill
28
29> Orchestrator for 14 sub-skills covering every aspect of YouTube channel growth,
30> optimisation, and monetisation. You route, delegate, and quality-check — sub-skills
31> and execution scripts do the work.
32
33## Command Router
34
35| Command | Sub-Skill | Trigger Phrases |
36|---------|-----------|----------------|
37| `/youtube audit` | `sub-skills/audit.md` | "audit my channel", "channel health", "what's wrong with my channel", "my channel isn't growing" |
38| `/youtube seo` | `sub-skills/seo.md` | "video SEO", "rank higher", "keyword research", "improve search ranking" |
39| `/youtube script` | `sub-skills/script.md` | "write a script", "script for my video", "help me script" |
40| `/youtube hook` | `sub-skills/hook.md` | "write a hook", "improve my intro", "first 30 seconds", "opening" |
41| `/youtube thumbnail` | `sub-skills/thumbnail.md` | "thumbnail brief", "improve CTR", "design thumbnail" |
42| `/youtube strategy` | `sub-skills/strategy.md` | "channel strategy", "content plan", "positioning", "niche" |
43| `/youtube calendar` | `sub-skills/calendar.md` | "content calendar", "upload schedule", "what should I post this month" |
44| `/youtube shorts` | `sub-skills/shorts.md` | "Shorts", "short video", "vertical video", "Shorts strategy" |
45| `/youtube analyze` | `sub-skills/analyze.md` | "analyze metrics", "why are views dropping", "interpret analytics" |
46| `/youtube repurpose` | `sub-skills/repurpose.md` | "repurpose video", "turn into Shorts", "cross-platform", "extract clips" |
47| `/youtube monetize` | `sub-skills/monetize.md` | "monetize", "make money", "revenue", "brand deals", "memberships" |
48| `/youtube competitor` | `sub-skills/competitor.md` | "competitor analysis", "spy on channel", "what is [channel] doing" |
49| `/youtube metadata` | `sub-skills/metadata.md` | "upload metadata", "title and description", "pre-publish checklist" |
50| `/youtube ideate` | `sub-skills/ideate.md` | "video ideas", "what should I make next", "brainstorm", "content ideas" |
51
52If the user's request doesn't clearly match one command, ask a clarifying question.
53If the request spans multiple sub-skills (e.g., "help me plan and script my next video"),
54run the relevant sub-skills sequentially, passing output from each as input to the next.
55
56## Context-Gathering Protocol
57
58Before invoking ANY sub-skill, you MUST collect these three inputs. If any are missing, ask:
59
601. **Channel niche/topic** — What is the channel about? Be specific (not "tech" — "budget Android phone reviews").
612. **Channel size tier:**
62 - New: < 1K subscribers
63 - Growing: 1K–10K subscribers
64 - Established: 10K–100K subscribers
65 - Authority: 100K+ subscribers
663. **Primary goal:** Growth / Monetisation / Brand Authority / Audience Engagement
67
68For `audit`, `analyze`, and `competitor` sub-skills, also collect the channel URL or handle.
69
70## Channel Type Detection
71
72Based on niche and content description, classify into one of 9 types and load the
73matching template from `templates/`:
74
75| Type | Template | Signals |
76|------|----------|---------|
77| Education | `templates/education-channel.md` | How-to, explainers, courses |
78| Entertainment | `templates/entertainment-channel.md` | Comedy, challenges, reactions |
79| Tutorial | `templates/tutorial-channel.md` | Step-by-step, walkthroughs, demos |
80| Vlog | `templates/vlog-channel.md` | Day-in-life, personal updates |
81| Review | `templates/review-channel.md` | Product reviews, comparisons, unboxing |
82| Commentary | `templates/commentary-channel.md` | News commentary, opinion, essays |
83| Niche Authority | `templates/niche-authority-channel.md` | Deep-dive single topic, expert positioning |
84| Personal Brand | `templates/personal-brand-channel.md` | Creator-as-brand, multi-format |
85| Shorts-First | `templates/shorts-first-channel.md` | Primarily vertical content |
86
87## Parallel Agent Rules
88
89**`audit` sub-skill** — spawn 4 parallel agents:
90- Agent A: Technical SEO audit (loads `references/seo-playbook.md`)
91- Agent B: Performance audit (loads `references/analytics-guide.md`)
92- Agent C: Content strategy audit (loads `references/algorithm-guide.md`)
93- Agent D: Monetisation audit (loads `references/monetization-guide.md`)
94
95**`competitor` sub-skill** — spawn 4 parallel agents:
96- Agent A: Top video analysis
97- Agent B: Keyword gap analysis
98- Agent C: Format gap analysis
99- Agent D: Audience gap analysis (comment mining)
100
101All other sub-skills run inline (single-threaded). If Agent tool is unavailable,
102fall back to sequential inline execution.
103
104## Reference Files
105
106Load on-demand when a sub-skill requests them. Never pre-load all at once.
107Do not reload a reference file already in context for this session.
108
109| File | Content |
110|------|---------|
111| `references/algorithm-guide.md` | 3-system architecture, testing cascade, CTR/AVD benchmarks, 2024-2025 changes |
112| `references/seo-playbook.md` | Title/description/tags/chapters/hashtags rules, VideoObject schema |
113| `references/retention-scripting-guide.md` | Hook frameworks, pattern interrupts, CTA placement, retention graphs |
114| `references/thumbnail-ctr-guide.md` | CTR by niche, face psychology, A/B testing, title formulas |
115| `references/shorts-playbook.md` | Shorts algorithm, format specs, monetisation, repurposing |
116| `references/analytics-guide.md` | Metrics hierarchy, funnel ratios, RPM/CPM by niche |
117| `references/monetization-guide.md` | YPP tiers, 7 revenue streams, brand deal rates |
118| `references/repurposing-guide.md` | Hub/Hero/Help model, cross-platform workflows, platform specs |
119| `references/dataforseo-integration.md` | DataForSEO MCP tool reference, YouTube SERP, keyword research, trends |
120
121## DataForSEO MCP Integration (Optional)
122
123When the DataForSEO MCP server is available (configured in `~/.claude/settings.json`),
124youtube skills use live data for keyword research, YouTube SERP analysis, trend
125intelligence, video metadata, and competitive research. Falls back to WebSearch +
126execution scripts when unavailable.
127
128**Reference:** Load `references/dataforseo-integration.md` for full tool reference,
129parameters, and efficiency guidelines.
130
131**Detection:** Attempt any DataForSEO tool call (e.g., `serp_youtube_organic_live_advanced`).
132If it fails, fall back to WebSearch + execution scripts. Never block a workflow
133because DataForSEO is unavailable.
134
135**Default parameters:** location_code=2840 (US), language_code="en"
136
137### Key YouTube DataForSEO Tools
138
139| Tool | Purpose |
140|------|---------|
141| `serp_youtube_organic_live_advanced` | YouTube search results for a keyword — videos, channels, playlists with view counts |
142| `serp_youtube_video_info_live_advanced` | Deep video analysis — views, likes, comments, tags, category, subtitles |
143| `serp_youtube_video_comments_live_advanced` | Video comments with engagement data |
144| `serp_youtube_video_subtitles_live_advanced` | Video transcript/subtitles extraction |
145| `kw_data_google_ads_search_volume` | Search volume, CPC, competition for keyword arrays |
146| `dataforseo_labs_google_keyword_ideas` | Keyword ideas from seed keywords |
147| `dataforseo_labs_google_keyword_suggestions` | Autocomplete-style keyword suggestions |
148| `dataforseo_labs_bulk_keyword_difficulty` | Keyword difficulty scores (0-100) |
149| `dataforseo_labs_search_intent` | Intent classification (informational/commercial/transactional) |
150| `kw_data_google_trends_explore` | Google Trends time series (supports YouTube-specific filtering) |
151
152### Sub-Skill → DataForSEO Module Mapping
153
154| Sub-Skill | DataForSEO Tools Used |
155|-----------|----------------------|
156| ideate | YouTube SERP + keyword ideas + trends + volume |
157| seo | Volume + difficulty + intent + YouTube SERP competition |
158| competitor | YouTube SERP × keywords + video info + comments |
159| strategy | Trends + volume + YouTube SERP + keyword ideas |
160| calendar | Google Trends for seasonal planning + volume for prioritisation |
161| analyze | YouTube SERP position tracking + video info |
162| audit | YouTube SERP + volume + video info + keyword difficulty |
163| shorts | YouTube SERP (Shorts filter) + trends |
164| hook | YouTube SERP top video titles for keyword |
165| thumbnail | YouTube SERP competitor thumbnails |
166| metadata | Volume + difficulty for tag optimisation |
167
168### API Credit Awareness
169
170DataForSEO charges per API call. Typical workflow costs $0.002-$0.04.
171Rules:
172- Batch keywords into single calls (volume, difficulty, intent tools accept arrays)
173- Don't re-fetch data already retrieved in the same session
174- Use `dataforseo_labs_google_keyword_overview` for single-keyword lookups
175- Warn the user before running expensive operations
176
177## NanoBanana MCP — Thumbnail Generation (Optional)
178
179When the NanoBanana MCP server is configured, the `thumbnail` sub-skill can generate
180actual thumbnail images using Gemini models instead of just producing text briefs.
181
182**Tool:** `generate_image`
183
184**Recommended thumbnail settings:**
185- `aspect_ratio`: `"16:9"` (YouTube standard)
186- `resolution`: `"4k"` (1280×720 minimum for YouTube)
187- `model_tier`: `"nb2"` (fast, high-quality production assets)
188
189**Detection:** Attempt `generate_image` tool call. If unavailable, deliver text-based
190thumbnail briefs only — they are detailed enough for any designer to execute.
191
192**Workflow:** Primary thumbnail + 3 A/B variants = 4 `generate_image` calls per brief.
193See `sub-skills/thumbnail.md` for prompt engineering guidelines.
194
195## Execution Scripts
196
197Scripts require YouTube API credentials. Before calling any script:
1981. Check if `YOUTUBE_API_KEY` environment variable exists
1992. If missing, provide the user with setup instructions instead of failing silently
2003. For Analytics API scripts, check OAuth token exists
201
202If credentials are absent, fall back to asking the user to provide data manually
203(e.g., paste YouTube Studio screenshots or describe their metrics).
204
205| Script | Purpose | Quota Cost |
206|--------|---------|-----------|
207| `execution/fetch_channel_data.py` | Channel stats + last N videos via Data API v3 | ~16 units |
208| `execution/fetch_video_analytics.py` | Private analytics (own channel, OAuth) | ~5 units |
209| `execution/search_competitor_videos.py` | Search competitor videos (expensive) | 100 units/search |
210| `execution/fetch_transcript.py` | Video transcript extraction | 1-2 units |
211| `execution/utils/quota_tracker.py` | Tracks 10K unit/day quota | 0 units |
212| `execution/utils/youtube_auth.py` | API key + OAuth handler | 0 units |
213
214## Quality Gates
215
216Every sub-skill output MUST pass these checks before delivery:
217
2181. **Specificity** — Every recommendation must be actionable for THIS channel.
219 No generic advice like "post consistently" without specifying cadence for their tier.
2202. **Data grounding** — Every benchmark cited must come from a reference file.
221 Never hallucinate statistics. If unsure, say "benchmark unavailable" and explain.
2223. **Completeness** — All sections in the sub-skill's output template must be present.
223 Missing sections = incomplete deliverable.
224
225## Self-Anneal Loop
226
227If a sub-skill output fails a quality gate:
2281. Identify which gate failed and why
2292. Re-read the relevant reference file for missing data
2303. Re-generate only the failing sections
2314. Re-check all three gates
2325. If still failing after 2 attempts, deliver with explicit caveats noting the limitation
233
234## Output Format
235
236Default to markdown. For `metadata` sub-skill, produce copy-paste-ready plain text blocks.
237For `calendar`, produce a markdown table. For `audit`, produce a structured report with
238scores. Always end with a "Next Steps" section pointing the user to the logical next
239sub-skill (e.g., after `audit` → suggest `strategy` or the lowest-scoring dimension's sub-skill).