Content Idea Scorer
Content eval

Generate and score content ideas using an expert panel.
--- ## Preamble (runs on skill start) ```bash # Version check (silent if up to date) python3 telemetry/version_check.py 2>/dev/null || true # Telemetry opt-in (first run only, then remembers your choice) python3 telemetry/telemetry_init.py 2>/dev/null || true ``` > **Privacy:** This skill logs usage locally to `~/.ai-marketing-skills/analytics/`. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. See `telemetry/README.md`. --- name: content-eval description: >- Generate and score content ideas using an expert panel. Pulls from podcast
Overview
name: content-eval description: >- Generate and score content ideas using an expert panel. Pulls from podcast transcripts, meeting notes, competitor analysis, and trending topics to produce a ranked content menu with production schedule. Use when asked to: "content eval", "score content ideas", "weekly content menu", "what should I film", "content ideas", "rate these video ideas". ---
Manual install (npx, ZIP)
npx skills add ericosiu/ai-marketing-skills --skill content-eval -g -a claude-codenpx degit ericosiu/ai-marketing-skills/content-eval#main ~/.claude/skills/content-evalConnects with Agent Alley MCP · agentalley.io/mcp
Files included
SKILL.md8.1 KB
Read SKILL.md here
Show the full text217 lines
name: content-eval description: >- Generate and score content ideas using an expert panel. Pulls from podcast transcripts, meeting notes, competitor analysis, and trending topics to produce a ranked content menu with production schedule. Use when asked to: "content eval", "score content ideas", "weekly content menu", "what should I film", "content ideas", "rate these video ideas".
Content Eval
Content ideation + expert panel scoring pipeline. Ingests raw material, generates ideas across your messaging pillars, scores them via a 7-expert panel, and outputs a ranked list with production schedule.
Step 1: Gather Raw Material
Collect signal from all available sources. Skip any source that's unavailable.
Podcast episodes
- Read recent episodes from your podcast transcript directory (last 7 days)
- Extract: topics covered, guest insights, audience questions, contrarian takes
- Note episode titles for dedup against new ideas
Meeting notes
- Check your meeting notes directory for recent notes
- Extract: client questions, recurring themes, interesting moments, pain points
- Focus on what your target buyers are actually asking about
Sales call insights
- Check your call recording platform data for recent calls
- Extract: objection patterns, recurring questions, competitor mentions
- Note what prospects are confused about or struggling with
Trending topics
- Note any topics the user mentions directly
- Check competitor scan results (Step 2) for trending formats/topics
- Look for news hooks or industry shifts you could react to
Step 2: Competitive Scan (if not provided)
If the user hasn't supplied competitive data, run a scan using your YouTube competitive analysis tool.
Channel sets are defined in references/competitors.md (same directory as this skill).
Analyze results
- Outlier videos: Identify any video with >2x the channel's average views
- Topic patterns: What subjects are multiple creators covering?
- Format patterns: What formats are performing (listicles, reactions, tutorials, story-driven)?
- Content gaps: Topics where NO competitor is covering something you could own
- Especially gaps at the intersection of your unique expertise areas
- Or gaps where you have unique data (revenue numbers, internal metrics, tool costs)
If your competitive analysis tool is not available, skip this step and note it was skipped.
Step 3: Generate Ideas
Generate 20-30 content ideas across three formats. Read references/pillars.md for
pillar definitions and references/voice-rules.md for content voice rules.
Format targets
| Format | Count | Details |
|---|---|---|
| YouTube Long-form (10-20 min) | 8-10 ideas | Deep dives, screen recordings, frameworks |
| YouTube Shorts (<60 sec) | 8-10 ideas | One punch, one insight, one hook |
| X / LinkedIn Articles | 5-7 ideas | Manifesto-style, data-heavy, contrarian takes |
Pillar requirement
Every idea MUST connect to at least one pillar defined in references/pillars.md.
Ideas that don't clearly serve a pillar get killed.
Idea format
Each idea needs:
- Title — specific, hook-driven, follows voice-rules.md
- Description — 1-2 sentences on the content and angle
- Format — Long-form / Short / Article
- Pillar(s) — which pillar(s) it serves
- Source signal — what raw material inspired it (podcast topic, competitor gap, client question, etc.)
Dedup check
- Check recent published content (last 30 days)
- If a similar angle was covered recently, either kill it or document a genuinely new hook
- Apply the dedup rule from
references/voice-rules.md
Manual override
If the user passes specific ideas to score (e.g., "score these content ideas: [list]"), skip idea generation and go directly to Step 4 with the provided ideas.
Step 4: Expert Panel Scoring
Run each idea through the 7-expert panel defined in references/panel.md.
Panel summary
| # | Expert | Lens |
|---|---|---|
| 1 | Viral Hook Expert | Curiosity gap, scroll-stopping power, title strength |
| 2 | Algorithm Expert | CTR potential, watch time, search demand, recommendation likelihood |
| 3 | Founder Brand Strategist | Pillar alignment, authenticity to founder's voice/experience |
| 4 | B2B Buyer Persona Expert | Would a CMO/VP/CEO watch and want what you're selling? |
| 5 | Content Differentiation Expert | Is anyone else making this? Unique angle? |
| 6 | Short-form Adaptation Expert | Can it clip into 3+ viral Shorts? Quotable moments? |
| 7 | Debate/Engagement Expert | Comments, shares, disagreements potential |
Scoring rules
- Each expert scores 0-100
- Pass threshold: 85+ average
- For each idea, output:
- Average score across all 7 experts
- PASS / FAIL
- Top expert comment (the most insightful feedback)
- Biggest weakness (the lowest-scoring dimension and why)
Output table per idea
### [Idea Title] — [Format]
**Pillar(s):** [pillar names]
**Description:** [1-2 sentences]
| Expert | Score | Comment |
|--------|-------|---------|
| Viral Hook | [score] | [one-line] |
| Algorithm | [score] | [one-line] |
| Brand Strategist | [score] | [one-line] |
| B2B Buyer | [score] | [one-line] |
| Differentiation | [score] | [one-line] |
| Short-form | [score] | [one-line] |
| Debate/Engagement | [score] | [one-line] |
**Average: [score] — [PASS / FAIL]**
**Top insight:** [best expert comment]
**Biggest weakness:** [lowest dimension + why]
Scoring integrity
- Be brutally honest. No grade inflation.
- Generic ideas that anyone could make should score <70 on Differentiation.
- Ideas without personal receipts/data should score <75 on Brand Strategist.
- If an idea is genuinely great, let it score high. The threshold exists so only the best survive.
Step 5: Rank and Schedule
Rank passing ideas
Sort all ideas scoring 85+ by average score, highest first.
Create 4-week production schedule
Assign passing ideas to weeks based on effort vs impact:
| Week | Focus | Typical content |
|---|---|---|
| Week 1 | Low effort, high impact | Shorts that can ship same day, reaction clips |
| Week 2 | Medium effort, highest ceiling | Long-form with screen recordings, tutorials |
| Week 3 | High effort, strategic anchors | Articles, manifesto pieces, deep-dive frameworks |
| Week 4 | Compounding content | Reference pieces, reaction content, series starters |
Kill list
List all ideas that scored <85 with:
- Title
- Average score
- Primary reason for failure (the expert dimension that killed it)
Step 6: Output
Create a document with the full results.
Document structure:
- Executive Summary — Total ideas generated, pass rate, top 5
- Competitive Gaps Found — What no one else is covering
- Ranked Ideas (Passing) — Full scoring tables for each
- 4-Week Production Schedule — Visual calendar layout
- Kill List — Failed ideas with reasons
- Raw Material Summary — Sources used (podcasts, meetings, calls, trends)
Optionally post a summary to your team channel with:
- Top 5 ideas (title, score, format, pillar)
- Competitive gaps found (2-3 bullets)
- Week 1 production schedule (what to film/write this week)
- Link to the full document
Reference Files
| File | Purpose | When to read |
|---|---|---|
references/pillars.md |
Messaging pillar definitions | Step 3 (idea generation) |
references/panel.md |
7-expert panel with scoring criteria | Step 4 (scoring) |
references/competitors.md |
YouTube competitor channel sets | Step 2 (competitive scan) |
references/voice-rules.md |
Content voice/style rules | Step 3 (idea generation) |
| 1 | |
| 2 | |
| 3 | ## Preamble (runs on skill start) |
| 4 | |
| 5 | |
| 6 | # Version check (silent if up to date) |
| 7 | python3 telemetry/version_check.py 2>/dev/null || true |
| 8 | |
| 9 | # Telemetry opt-in (first run only, then remembers your choice) |
| 10 | python3 telemetry/telemetry_init.py 2>/dev/null || true |
| 11 | |
| 12 | |
| 13 | > **Privacy:** This skill logs usage locally to `~/.ai-marketing-skills/analytics/`. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. See `telemetry/README.md`. |
| 14 | |
| 15 | |
| 16 | name: content-eval |
| 17 | description: >- |
| 18 | Generate and score content ideas using an expert panel. Pulls from podcast |
| 19 | transcripts, meeting notes, competitor analysis, and trending topics to |
| 20 | produce a ranked content menu with production schedule. Use when asked to: |
| 21 | "content eval", "score content ideas", "weekly content menu", "what should |
| 22 | I film", "content ideas", "rate these video ideas". |
| 23 | |
| 24 | |
| 25 | # Content Eval |
| 26 | |
| 27 | Content ideation + expert panel scoring pipeline. Ingests raw material, generates |
| 28 | ideas across your messaging pillars, scores them via a 7-expert panel, and |
| 29 | outputs a ranked list with production schedule. |
| 30 | |
| 31 | |
| 32 | |
| 33 | ## Step 1: Gather Raw Material |
| 34 | |
| 35 | Collect signal from all available sources. Skip any source that's unavailable. |
| 36 | |
| 37 | ### Podcast episodes |
| 38 | Read recent episodes from your podcast transcript directory (last 7 days) |
| 39 | Extract: topics covered, guest insights, audience questions, contrarian takes |
| 40 | Note episode titles for dedup against new ideas |
| 41 | |
| 42 | ### Meeting notes |
| 43 | Check your meeting notes directory for recent notes |
| 44 | Extract: client questions, recurring themes, interesting moments, pain points |
| 45 | Focus on what your target buyers are actually asking about |
| 46 | |
| 47 | ### Sales call insights |
| 48 | Check your call recording platform data for recent calls |
| 49 | Extract: objection patterns, recurring questions, competitor mentions |
| 50 | Note what prospects are confused about or struggling with |
| 51 | |
| 52 | ### Trending topics |
| 53 | Note any topics the user mentions directly |
| 54 | Check competitor scan results (Step 2) for trending formats/topics |
| 55 | Look for news hooks or industry shifts you could react to |
| 56 | |
| 57 | |
| 58 | |
| 59 | ## Step 2: Competitive Scan (if not provided) |
| 60 | |
| 61 | If the user hasn't supplied competitive data, run a scan using your YouTube |
| 62 | competitive analysis tool. |
| 63 | |
| 64 | Channel sets are defined in `references/competitors.md` (same directory as this skill). |
| 65 | |
| 66 | ### Analyze results |
| 67 | **Outlier videos:** Identify any video with >2x the channel's average views |
| 68 | **Topic patterns:** What subjects are multiple creators covering? |
| 69 | **Format patterns:** What formats are performing (listicles, reactions, tutorials, story-driven)? |
| 70 | **Content gaps:** Topics where NO competitor is covering something you could own |
| 71 | Especially gaps at the intersection of your unique expertise areas |
| 72 | Or gaps where you have unique data (revenue numbers, internal metrics, tool costs) |
| 73 | |
| 74 | If your competitive analysis tool is not available, skip this step and note it was skipped. |
| 75 | |
| 76 | |
| 77 | |
| 78 | ## Step 3: Generate Ideas |
| 79 | |
| 80 | Generate 20-30 content ideas across three formats. Read `references/pillars.md` for |
| 81 | pillar definitions and `references/voice-rules.md` for content voice rules. |
| 82 | |
| 83 | ### Format targets |
| 84 | | Format | Count | Details | |
| 85 | |--------|-------|---------| |
| 86 | | YouTube Long-form (10-20 min) | 8-10 ideas | Deep dives, screen recordings, frameworks | |
| 87 | | YouTube Shorts (<60 sec) | 8-10 ideas | One punch, one insight, one hook | |
| 88 | | X / LinkedIn Articles | 5-7 ideas | Manifesto-style, data-heavy, contrarian takes | |
| 89 | |
| 90 | ### Pillar requirement |
| 91 | Every idea MUST connect to at least one pillar defined in `references/pillars.md`. |
| 92 | Ideas that don't clearly serve a pillar get killed. |
| 93 | |
| 94 | ### Idea format |
| 95 | Each idea needs: |
| 96 | **Title** — specific, hook-driven, follows voice-rules.md |
| 97 | **Description** — 1-2 sentences on the content and angle |
| 98 | **Format** — Long-form / Short / Article |
| 99 | **Pillar(s)** — which pillar(s) it serves |
| 100 | **Source signal** — what raw material inspired it (podcast topic, competitor gap, client question, etc.) |
| 101 | |
| 102 | ### Dedup check |
| 103 | Check recent published content (last 30 days) |
| 104 | If a similar angle was covered recently, either kill it or document a genuinely new hook |
| 105 | Apply the dedup rule from `references/voice-rules.md` |
| 106 | |
| 107 | ### Manual override |
| 108 | If the user passes specific ideas to score (e.g., "score these content ideas: [list]"), |
| 109 | skip idea generation and go directly to Step 4 with the provided ideas. |
| 110 | |
| 111 | |
| 112 | |
| 113 | ## Step 4: Expert Panel Scoring |
| 114 | |
| 115 | Run each idea through the 7-expert panel defined in `references/panel.md`. |
| 116 | |
| 117 | ### Panel summary |
| 118 | | # | Expert | Lens | |
| 119 | |---|--------|------| |
| 120 | | 1 | Viral Hook Expert | Curiosity gap, scroll-stopping power, title strength | |
| 121 | | 2 | Algorithm Expert | CTR potential, watch time, search demand, recommendation likelihood | |
| 122 | | 3 | Founder Brand Strategist | Pillar alignment, authenticity to founder's voice/experience | |
| 123 | | 4 | B2B Buyer Persona Expert | Would a CMO/VP/CEO watch and want what you're selling? | |
| 124 | | 5 | Content Differentiation Expert | Is anyone else making this? Unique angle? | |
| 125 | | 6 | Short-form Adaptation Expert | Can it clip into 3+ viral Shorts? Quotable moments? | |
| 126 | | 7 | Debate/Engagement Expert | Comments, shares, disagreements potential | |
| 127 | |
| 128 | ### Scoring rules |
| 129 | Each expert scores 0-100 |
| 130 | **Pass threshold: 85+ average** |
| 131 | For each idea, output: |
| 132 | Average score across all 7 experts |
| 133 | PASS / FAIL |
| 134 | Top expert comment (the most insightful feedback) |
| 135 | Biggest weakness (the lowest-scoring dimension and why) |
| 136 | |
| 137 | ### Output table per idea |
| 138 | |
| 139 | ### [Idea Title] — [Format] |
| 140 | **Pillar(s):** [pillar names] |
| 141 | **Description:** [1-2 sentences] |
| 142 | |
| 143 | | Expert | Score | Comment | |
| 144 | |--------|-------|---------| |
| 145 | | Viral Hook | [score] | [one-line] | |
| 146 | | Algorithm | [score] | [one-line] | |
| 147 | | Brand Strategist | [score] | [one-line] | |
| 148 | | B2B Buyer | [score] | [one-line] | |
| 149 | | Differentiation | [score] | [one-line] | |
| 150 | | Short-form | [score] | [one-line] | |
| 151 | | Debate/Engagement | [score] | [one-line] | |
| 152 | |
| 153 | **Average: [score] — [PASS / FAIL]** |
| 154 | **Top insight:** [best expert comment] |
| 155 | **Biggest weakness:** [lowest dimension + why] |
| 156 | |
| 157 | |
| 158 | ### Scoring integrity |
| 159 | Be brutally honest. No grade inflation. |
| 160 | Generic ideas that anyone could make should score <70 on Differentiation. |
| 161 | Ideas without personal receipts/data should score <75 on Brand Strategist. |
| 162 | If an idea is genuinely great, let it score high. The threshold exists so only the best survive. |
| 163 | |
| 164 | |
| 165 | |
| 166 | ## Step 5: Rank and Schedule |
| 167 | |
| 168 | ### Rank passing ideas |
| 169 | Sort all ideas scoring 85+ by average score, highest first. |
| 170 | |
| 171 | ### Create 4-week production schedule |
| 172 | Assign passing ideas to weeks based on effort vs impact: |
| 173 | |
| 174 | | Week | Focus | Typical content | |
| 175 | |------|-------|-----------------| |
| 176 | | Week 1 | Low effort, high impact | Shorts that can ship same day, reaction clips | |
| 177 | | Week 2 | Medium effort, highest ceiling | Long-form with screen recordings, tutorials | |
| 178 | | Week 3 | High effort, strategic anchors | Articles, manifesto pieces, deep-dive frameworks | |
| 179 | | Week 4 | Compounding content | Reference pieces, reaction content, series starters | |
| 180 | |
| 181 | ### Kill list |
| 182 | List all ideas that scored <85 with: |
| 183 | Title |
| 184 | Average score |
| 185 | Primary reason for failure (the expert dimension that killed it) |
| 186 | |
| 187 | |
| 188 | |
| 189 | ## Step 6: Output |
| 190 | |
| 191 | Create a document with the full results. |
| 192 | |
| 193 | Document structure: |
| 194 | **Executive Summary** — Total ideas generated, pass rate, top 5 |
| 195 | **Competitive Gaps Found** — What no one else is covering |
| 196 | **Ranked Ideas (Passing)** — Full scoring tables for each |
| 197 | **4-Week Production Schedule** — Visual calendar layout |
| 198 | **Kill List** — Failed ideas with reasons |
| 199 | **Raw Material Summary** — Sources used (podcasts, meetings, calls, trends) |
| 200 | |
| 201 | Optionally post a summary to your team channel with: |
| 202 | Top 5 ideas (title, score, format, pillar) |
| 203 | Competitive gaps found (2-3 bullets) |
| 204 | Week 1 production schedule (what to film/write this week) |
| 205 | Link to the full document |
| 206 | |
| 207 | |
| 208 | |
| 209 | ## Reference Files |
| 210 | |
| 211 | | File | Purpose | When to read | |
| 212 | |------|---------|--------------| |
| 213 | | `references/pillars.md` | Messaging pillar definitions | Step 3 (idea generation) | |
| 214 | | `references/panel.md` | 7-expert panel with scoring criteria | Step 4 (scoring) | |
| 215 | | `references/competitors.md` | YouTube competitor channel sets | Step 2 (competitive scan) | |
| 216 | | `references/voice-rules.md` | Content voice/style rules | Step 3 (idea generation) | |
| 217 |
Details
- License
- MIT
- Stars on the repo
- ★ 3,615
- Checked
- Source
- ericosiu/ai-marketing-skills ↗
- Creator
- ericosiu · 34 listings
Similar skills
See all →
SkillCross-Platform Reverse Engineer
SkillBrainstorm Ideas
SkillCode Review Feedback Analyzer
SkillBug Diagnosis Framework
SkillImplement Spec
SkillPR Description WriterMore from ericosiu
SkillVideo Moment Extraction Agent
SkillConversion Operations
SkillFinance Operations
SkillRevenue Intelligence Dashboard
SkillSales Pipeline Manager
SkillValue-Based Sales Playbook