agentleFS
nikhilbhansalinikhilbhansali/youtube-data-skills/skills/youtube-content-strategist/SKILL.md

youtube-content-strategist

Skill4 starsChanged 3 months agoMITView on GitHub

Create a data-driven YouTube content strategy and 30-day content calendar using YouTube Data API v3. Analyzes your channel's performance, cross-references with niche data, identifies content pillars, evaluates Shorts vs long-form split, determines optimal duration and schedule, and finds sequel opportunities. Use when users want to (1) Plan their next 30 days of content, (2) Get a data-backed content calendar, (3) Optimize their content mix, (4) Identify sequel and follow-up opportunities, (5) Compare their strategy against niche benchmarks, (6) Find their best-performing content pillars. Requires user's YouTube Data API v3 key.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a data-driven 30-day content calendar by analyzing your channel + niche benchmarks.

    line 8
  2. Distinctive:

    Check Claude memory for a YouTube Data API v3 key.

    line 29
  3. Very specific:

    Run scripts/analyze_strategy.py — resolve the path relative to this skill's own directory:

    line 34
  4. Distinctive:

    Write to the path the script printed:

    line 56
  5. Very specific:

    Only the niche benchmark needs search.list.

    line 139

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

YouTube Content Strategist

Create a data-driven 30-day content calendar by analyzing your channel + niche benchmarks.

Usage

/youtube-content-strategist @MyChannel --niche "productivity"
/youtube-content-strategist @MyChannel --niche "cooking recipes" --uploads-per-week 3
/youtube-content-strategist UCxxxxxxx --niche "fitness"

Instructions

Step 1: Parse Arguments

  • Channel (required): @handle, URL, or channel ID
  • --niche "keyword" (required): the niche/topic area
  • --uploads-per-week N (optional): target upload frequency (default: auto-detect from history)
  • --max-videos N (optional): how many recent uploads to analyze (default: 200)

Step 2: Get the API Key

Check Claude memory for a YouTube Data API v3 key. If not found, ask:

"I need a YouTube Data API v3 key. You can get one from the Google Cloud Console. Please paste your key."

Step 3: Run the Bundled Script

Run scripts/analyze_strategy.py — resolve the path relative to this skill's own directory:

YT_API_KEY=API_KEY python3 <skill-dir>/scripts/analyze_strategy.py "@CHANNEL" --niche "NICHE" [--uploads-per-week N]

Dependency: pip3 install google-api-python-client.

The script resolves the channel with channels.list (1 unit), pages the uploads playlist, classifies every video into a content type and duration bucket, measures Shorts vs long-form performance, derives the upload cadence and preferred days/hours, finds sequel candidates (2x average views and older than 60 days), samples the niche for benchmarks, and lists the channel's playlists.

Step 4: Read the Data

reports/data/content-strategy-<channel-slug>-<YYYY-MM-DD>.json

Step 5: Write the Strategy Report

Write to the path the script printed:

reports/content-strategy-<channel-slug>-<YYYY-MM-DD>.md
# Content Strategy: [Channel Name]
*Niche: [Niche] | Analyzed [date] | [N] videos analyzed*

## Channel Position Assessment
Where does this channel stand? Subscribers, total views, video count.
How does it compare to niche benchmarks?

## Content Mix Analysis
### Current Mix
| Content Type | Count | % | Avg Views | Avg Engagement |
|-------------|-------|---|-----------|----------------|
What's working best? What's underperforming?

### Optimal Mix Recommendation
Based on performance data, recommend shifting the mix.

## Shorts vs Long-Form Strategy
| Metric | Shorts | Long-Form |
|--------|--------|-----------|
Which is performing better for this channel?
Recommendation on Shorts strategy.

## Optimal Video Duration
| Duration Bucket | Count | Avg Views |
|----------------|-------|-----------|
What duration sweet spot should this channel target?

## Upload Schedule
| Metric | Current | Recommended |
|--------|---------|-------------|
Best days and times based on historical data.
Upload frequency recommendation with reasoning.

## Content Pillars (Ranked by Impact)
For each content pillar:
- Performance metrics
- Strategic role (growth, engagement, authority, etc.)
- Recommendation (double down / maintain / reduce / try)

## Sequel & Follow-Up Opportunities
Videos that outperformed and deserve sequels.
| Original Video | Views | Age | Suggested Follow-Up |
|---------------|-------|-----|---------------------|

## Playlist Strategy
Current playlists and their sizes.
Recommendations for new playlists or series.

## 30-Day Content Calendar
Generate a concrete calendar:
| Week | Day | Video Title Idea | Type | Duration | Rationale |
|------|-----|------------------|------|----------|-----------|
| 1 | Mon | ... | tutorial | 12 min | Top-performing format |
| 1 | Thu | ... | tips | 8 min | High engagement topic |
...

Base every recommendation on actual data from the analysis.

## Growth Levers (Ranked by Impact)
1. **[Lever]** - Data backing - Expected impact
2. **[Lever]** - Data backing - Expected impact
...

## Quota Usage
| Operation | Calls | Units |
|-----------|-------|-------|
Use the `quota_used.breakdown` block from the JSON.

Step 6: Report Completion

Tell the user the report path, the channel position summary, the top content pillar finding, the upload schedule recommendation, a 30-day calendar overview, and the quota consumed.

Quota Estimate

Only the niche benchmark needs search.list; everything about the user's own channel goes through channels.list + playlistItems.list.

OperationCallsUnits
channels.list (resolve handle/ID/URL)11
playlistItems.list (200 uploads)44
videos.list (200 videos, batches of 50)44
search.list (niche benchmark)1100
videos.list (benchmark details)11
playlists.list11
Total~111

Resolving an @handle previously fell back to search.list (100 units) when the first lookup missed; forHandle/forUsername now handles every input form for 1 unit. Daily default allowance is 10,000 units, resetting at midnight Pacific Time.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.