skills/content-creator/SKILL.md
Use when creating written content: blog posts, articles, case studies, whitepapers, social media posts, email copy, landing pages, or newsletters. Use when user asks to write, draft, create content, needs copywriting, or mentions content strategy. NEVER for code documentation, technical specs, or API docs -- those are developer-writing tasks, not content creation.
npx skillsauth add sharkitect-solutions/sharkitect-claude-toolkit content-creatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Expert decision layer for producing content that engages, converts, and ranks. This skill exists because Claude's default content output is structurally correct but engagement-dead -- it follows templates without understanding WHY certain structures work for certain goals. The knowledge here closes that gap.
Before writing a single word, match the request to the right content vehicle. Getting this wrong wastes the entire piece.
What is the PRIMARY goal?
|
+-- Educate/Inform
| +-- Technical audience --> How-To Guide or Tutorial
| +-- Business audience --> Whitepaper or Industry Report
| +-- General audience --> Blog Post (explainer format)
| +-- Quick consumption --> Listicle or Infographic script
|
+-- Persuade/Convert
| +-- Top of funnel --> Blog Post (problem-aware)
| +-- Middle of funnel --> Case Study or Comparison
| +-- Bottom of funnel --> Landing Page or Sales Email
| +-- Re-engagement --> Newsletter or Retargeting Email
|
+-- Build Authority
| +-- Industry positioning --> Thought Leadership Article
| +-- Social proof --> Case Study or Customer Story
| +-- Community presence --> LinkedIn/Social Posts
| +-- Media coverage --> Press Release
|
+-- Engage/Retain
| +-- Community building --> Social Media Series
| +-- Subscriber retention --> Email Newsletter
| +-- Audience growth --> Platform-native content (Reels, Threads, Carousels)
Why this matters: A case study written when a how-to guide was needed fails regardless of writing quality. Content that underperforms most often does so because of format mismatch, not execution quality.
Before drafting, chain these decisions in order. Skipping steps is the #1 cause of rewrites.
references/brand_guidelines.md to set formality x energy x authority dimensions. If no brand guidance exists, use the inference heuristics.references/content_frameworks.md for architecture decisions by content type. Select structure based on goal + audience, not habit.references/content_frameworks.md.references/social_media_optimization.md for channel selection, cross-channel coordination, and repurposing schedule.Each step narrows options for the next. By step 6, the hook practically writes itself because goal, audience, voice, angle, and structure are already locked.
The first 50 words determine whether anyone reads the rest. Claude defaults to "In today's fast-paced world..." or "Have you ever wondered..." -- both are engagement killers. Use these patterns instead.
| Pattern | When to Use | Example | |---------|------------|---------| | Contrarian Open | Challenging industry assumptions | "Most SEO advice is backwards. Here's why keyword density stopped mattering in 2024." | | Specificity Hook | Data-driven content | "We analyzed 2,847 blog posts. The ones that ranked had one thing in common -- and it's not what you think." | | Story Open | Case studies, thought leadership | "Three months ago, our client was spending $40K/month on content that generated zero leads." | | Direct Problem | How-to guides, tutorials | "Your landing page converts at 2%. Here's the structural flaw causing it." | | Before/After Gap | Transformation content | "Companies using this framework went from 3% to 18% email open rates in 6 weeks." |
Why these fail: Each one signals to the reader that what follows is generic. Readers give you 8 seconds. Spend them on value, not throat-clearing.
Different content types have different structural requirements. See references/content_frameworks.md for architecture selection decisions by content type. The execution-level decisions are here.
Structure: Hook > Context (why now) > Core Value (3-5 sections) > Action Step > CTA
Critical decisions:
Structure: Result First > Challenge > Solution > Evidence > Takeaway
Critical decisions:
Structure: Subject Line > Preview Text > Opening Line > Single Value Block > CTA
Critical decisions:
Platform-specific social media tactics live in the social-content skill. Distribution strategy in references/social_media_optimization.md. Expert decisions here:
Raw research does not become good content by summarizing it. The pipeline:
Why "angle" matters: There are 7.5 million blog posts published every day. Content without a clear angle is invisible. The angle is the answer to: "Why should someone read THIS piece instead of the other 50 on this topic?"
| Audience | Formality | Jargon Level | Proof Type | Sentence Length | |----------|-----------|-------------|------------|-----------------| | C-Suite | Professional | Industry-standard terms only | ROI, revenue, competitive advantage | 15-20 words avg | | Practitioners | Conversational-professional | Technical terms OK with context | How-to, step-by-step, time savings | 12-18 words avg | | General/Consumer | Conversational | Zero jargon | Stories, social proof, before/after | 10-15 words avg | | Technical | Professional | Domain-specific expected | Benchmarks, specifications, code examples | 15-25 words avg | | Social Media | Casual-conversational | Platform-native language | Screenshots, results, personal stories | 8-12 words avg |
Calibration error to watch for: Claude tends to write everything at "conversational-professional" regardless of audience. Force the adjustment. If writing for C-Suite, cut the friendliness. If writing for social, cut the formality.
These are the shortcuts Claude will be tempted to take. Recognize them and refuse.
| Rationalization | When It Appears | Why It's Wrong | |----------------|-----------------|----------------| | "I'll add a compelling introduction later" | Drafting body first | The hook determines if anyone reads the body. Write it first, refine it last. | | "This template structure is sufficient" | Following a generic format | Templates are starting points. Every piece needs structural decisions based on goal + audience + platform. | | "More information is always better" | Padding word count | Length without density is punishment. Every paragraph must earn its space. | | "The reader will understand the context" | Skipping the 'why now' framing | Content without urgency gets bookmarked and never read. | | "I'll use a professional tone since I'm unsure" | Default tone selection | Wrong tone alienates the actual audience. Ask or infer from context clues. | | "The CTA at the end is fine" | Putting CTA only at bottom | 60% of readers never reach the bottom. Place primary CTA after value delivery. |
| Signal | AI Slop | B+ Content | |--------|---------|------------| | Opening | Generic ("In today's...") | Specific (data point, story, contrarian claim) | | Structure | Template-following | Goal-driven architecture | | Examples | Hypothetical ("Imagine a company...") | Specific ("When Stripe launched...") | | Claims | Unsupported ("Studies show...") | Cited ("McKinsey's 2024 report found...") | | Voice | Uniform corporate-pleasant | Calibrated to audience + platform | | Transitions | "Furthermore," "Additionally," | Logical flow that doesn't need connective tissue | | CTA | "Contact us today!" | Specific next action tied to content value | | Length | Padded to target | Exactly as long as the value requires |
SEO is not a post-writing optimization step. It is a pre-writing structural decision.
Before writing:
During writing:
After writing: Run scripts/seo_optimizer.py to verify structural compliance. Fix gaps before publishing.
For structural pre-publishing checks after SEO optimization, see the Pre-Publishing Quality Gate in references/content_frameworks.md.
scripts/brand_voice_analyzer.py <file> [json|text] -- Analyze content for voice consistency. Use on first draft to check tone calibration against target audience.scripts/seo_optimizer.py <file> [keyword] [secondary,keywords] -- Analyze SEO structural compliance. Use after final draft, before publishing.references/brand_guidelines.md -- Voice calibration framework (formality x energy x authority), consistency tests, miscalibration fixes, platform adaptation rules, voice inference heuristics. Consult before any draft to lock voice dimensions.references/content_frameworks.md -- Content architecture decisions by type (blog, case study, whitepaper, email), repurposing strategy, pre-publishing quality gate. Consult to select structure, not for fill-in-the-blank templates.references/social_media_optimization.md -- Distribution channel selection, paid vs organic decisions, content lifecycle management, cross-channel coordination, performance benchmarks. Consult after drafting to plan distribution.assets/content_calendar_template.md -- Monthly planning template. Copy and customize per engagement.development
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.
testing
--- name: using-sharkitect-methodology description: Use when starting any conversation in a Sharkitect workspace OR before any task involving NEW pricing, positioning, proposal, strategy, plan-execution, or schema-design work — mandates invocation of Sharkitect-specific methodology skills (pricing-strategy, marketing-strategy-pmm, smb-cfo, hq-revenue-ops, executing-plans, brainstorming) under the same anti-rationalization discipline as using-superpowers. Documentation has failed 4 times across H
testing
Use when user says 'end session', 'wrap up', 'stop for the day', 'done for today', 'close out', 'save session', 'wrapping up', or invokes /end-session. Runs the full 9-step end-of-session protocol: resource audit, MEMORY.md update, lessons capture, plan status, pending items, workspace checklist, .tmp/ audit, git commit+push, Supabase brain sync, session brief, summary. Final step schedules a detached self-kill of the current session ONLY (3s delay) so the window closes cleanly. Other claude.exe processes (active workspaces) are NOT touched -- orphan cleanup is handled separately by Claude-Orphan-Cleanup-Hourly with proper age safeguards. Do NOT use for: mid-session quick saves (use session-checkpoint), skill syncing (use sync-skills.py), brain memory queries (use supabase-sync.py pull), document freshness reviews (use document-lifecycle), resource gap detection (use resource-auditor).
testing
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.