comp-scout-analyze
Generate strategic analysis for competition entries and auto-persist to GitHub issue. Identifies winning tone, themes, and angles based on sponsor type and brand voice.
What this skill does
# Competition Strategy Analyzer
Generate strategic analysis for "25 words or less" competition entries and **automatically add to GitHub issue**.
## Execution Modes
| Mode | Behavior |
|------|----------|
| **Interactive** (default) | Ask clarifying questions about brand voice, tone preferences |
| **Unattended** | Use defaults based on sponsor category, no prompts |
The `comp-scout-daily` workflow always invokes this skill in **unattended mode**.
### Interactive Mode
When run interactively, this skill may ask:
- "What tone would you prefer? (sincere/humorous/mix)"
- "Any specific themes you want to emphasize?"
- "Should we focus on any particular angle?"
### Unattended Mode
When invoked with `--unattended` or by `comp-scout-daily`:
- Uses sponsor category to determine default tone
- Generates standard set of 5 angle ideas
- No user prompts - runs end-to-end automatically
## What This Skill Does
1. Analyzes the competition's brand, sponsor type, and prompt
2. Determines winning tone and approach
3. Generates angle ideas and themes
4. **Auto-persists strategy as comment on the competition's GitHub issue**
**No manual "please save to issue" step required.**
## Input
Competition data (from GitHub issue or `comp-scout-scrape`):
- url, title, brand
- prize_summary, prize_value
- prompt, word_limit
- closing_date
- **issue_number** (for auto-persist)
Optional flags:
- `--unattended` - Skip all interactive prompts, use defaults
## Workflow
### Step 1: Identify Sponsor Category
Classify the brand/sponsor into one of these categories:
| Category | Examples | Indicators |
|----------|----------|------------|
| **Wellness/luxury** | Spas, skincare, premium travel, health retreats | Premium language, self-care themes, aspirational imagery |
| **Tech/gaming** | Electronics, gaming, apps, software | Features, specs, community, innovation |
| **Food/beverage** | Grocery, restaurants, drinks, snacks | Sensory language, recipes, family moments, occasions |
| **Travel** | Airlines, hotels, destinations, experiences | Adventure, discovery, escape, bucket-list |
| **Retail/general** | Department stores, homewares, fashion | Lifestyle, value, everyday convenience |
| **Rural/agricultural** | Farm supplies, outdoor equipment, regional brands | Practical language, weather, land, hard work |
### Step 2: Determine Winning Tone
Based on sponsor category, identify the likely winning tone:
| Sponsor Type | Likely Winning Tone |
|--------------|---------------------|
| Wellness/luxury | Sincere, aspirational, emotional honesty. Judges want to feel you genuinely need/deserve this. |
| Tech/gaming | Knowledgeable enthusiasm, self-aware humour. Show you understand the product without being a fanboy. |
| Food/beverage | Relatable moments, sensory details. Specific tastes, smells, family traditions. |
| Travel | Discovery, bucket-list energy, specific memories. What makes this destination special to YOU? |
| Retail/general | Personality, memorability, genuine need. Stand out from generic "I'd love to win" entries. |
| Rural/agricultural | Practical, financially savvy, honest about habits. Down-to-earth authenticity wins. |
### Step 3: Assess Brand Voice
Analyze how the brand communicates:
**Questions to answer:**
- Is the brand formal or casual?
- Do they use humour or stay serious?
- What values do they emphasize? (family, adventure, quality, value, sustainability)
- What language patterns appear in their marketing?
- Who is their target audience?
**Output example:**
> "Casual and friendly, emphasizes family moments and everyday joy. Uses warm, approachable language. Target audience is parents/families."
### Step 4: Analyze the Prompt
Break down what the prompt is really asking:
**Questions to answer:**
- What's the surface-level question?
- What's the emotional response they're hoping for?
- What generic answers will judges see hundreds of times?
- What would make an entry memorable?
**Example:**
> Prompt: "Tell us in 25 words or less why you love our coffee"
>
> Surface: Why do you like coffee?
> Real ask: What specific, personal moment makes our coffee special?
> Generic answers: "I love the taste", "It wakes me up", "Best coffee ever"
> Memorable: Specific sensory detail, unexpected moment, personal ritual
### Step 5: Generate Angle Ideas
Create 3-5 distinct approaches, each with:
- Different emotional hook
- Different arc structure (sincere, comedic, self-deprecating, list-pivot)
- Brief description of the strategy
**Format:**
```
1. **Sincere - The morning ritual**
Focus on a specific moment when the product is part of your routine.
Arc: Honest admission → Sensory detail → Warm landing
2. **Self-deprecating - The confession**
Admit to a relatable "flaw" that the product addresses.
Arc: Confession → Constraint → Resolution
3. **Comedic - The unexpected angle**
Find an unusual perspective that subverts expectations.
Arc: Setup → Pivot → Callback
4. **Sensory - The specific detail**
Zero in on one vivid sensory moment.
Arc: Scene-setting → Sensory detail → Emotional resonance
5. **List-pivot - The credentials**
Quick list establishing context, then pivot to the real point.
Arc: List → Gap → Aspiration
```
### Step 6: Identify What to Avoid
Common pitfalls for this type of competition:
**Always avoid:**
- Generic superlatives ("amazing", "best ever", "fantastic")
- Begging or desperation ("please pick me", "I really need this")
- Lies or fabricated stories
- Clichés the judges will see hundreds of times
- Empty enthusiasm without specificity
**Category-specific pitfalls:**
| Category | Avoid |
|----------|-------|
| Wellness/luxury | Sounding entitled, over-the-top drama |
| Tech/gaming | Being too technical, gatekeeping |
| Food/beverage | Generic taste descriptions, "yummy" |
| Travel | Bucket-list clichés, generic wanderlust |
| Retail/general | "I want free stuff" energy |
| Rural/agricultural | City-slicker posturing, romanticism |
### Step 7: Auto-Persist to GitHub Issue
Add strategy as a comment on the competition's issue:
```bash
gh issue comment $ISSUE_NUMBER -R "$TARGET_REPO" --body "$(cat <<'EOF'
## Strategy Analysis
**Sponsor Category:** {sponsor_category}
**Brand Voice:** {brand_voice}
**Recommended Tone:** {recommended_tone}
### Approach
{approach}
### Themes to Use
{themes_list}
### Angle Ideas
{angle_ideas_list}
### Avoid
{avoid_list}
---
*Generated: {date}*
EOF
)"
```
### Step 8: Report Completion
```
✅ Strategy analysis complete and saved to issue #42!
**Summary:**
- Sponsor Category: Food/beverage
- Recommended Tone: Relatable with sensory details
- Generated 5 angle ideas
(In interactive mode: "Ready to compose entries?")
```
## Output Format
```yaml
strategy:
competition_url: "https://..."
issue_number: 42
brand: "Example Brand"
brand_voice: "Casual and friendly, emphasizes family moments"
sponsor_category: "food/beverage"
recommended_tone: "Relatable with sensory details, warm and specific"
approach: |
Focus on a specific moment when the product is part of your life.
Avoid generic taste descriptions - instead, anchor to a memory,
ritual, or unexpected moment. The best entries will make judges
nod in recognition.
themes_to_use:
- "Family traditions"
- "Sensory memories"
- "Everyday rituals"
- "Unexpected moments"
words_to_consider:
- "ritual"
- "moment"
- "discover"
- "finally"
angle_ideas:
- "Sincere: The Sunday morning ritual that wouldn't be complete without it"
- "Self-deprecating: Confessing to hiding the good stuff from the family"
- "Sensory: The specific smell that triggers childhood memories"
- "Comedic: The unexpected place/time you've enjoyed the product"
- "List-pivot: All the things you've tried, but this is the one that stuck"
avoid:
- "I love [brand]"
- "Best [product] ever"
- "Please pick me"
- "My family would love this"
- "Delicious" / "Yummy" / "Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".