Voice Builder
charlie947/social-media-skills
Build a personalised voice profile inside a Codex or Claude project from a short interview plus 3 to 5 sample pieces of writing.
Create SEO-optimized marketing content with consistent brand voice, using a brand voice analyzer, SEO optimizer, and content frameworks.
$ npx skills add borghei/Claude-Skills --skill content-creator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install borghei/Claude-Skills content-creator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/marketing/content-creator .claude/skills/content-creator && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "content-creator" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/content-creator into .claude/skills/content-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-creator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/borghei/Claude-Skills/tree/main/marketing/content-creatorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add borghei/Claude-Skills --skill content-creator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install borghei/Claude-Skills content-creator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/marketing/content-creator .agents/skills/content-creator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "content-creator" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/content-creator into .agents/skills/content-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-creator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add borghei/Claude-Skills --skill content-creator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install borghei/Claude-Skills content-creator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/marketing/content-creator .cursor/skills/content-creator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "content-creator" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/content-creator into .cursor/skills/content-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-creator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/borghei/Claude-Skills.git --path marketing/content-creator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add borghei/Claude-Skills --skill content-creator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install borghei/Claude-Skills content-creator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/marketing/content-creator .gemini/skills/content-creator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "content-creator" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/content-creator into .gemini/skills/content-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-creator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install borghei/Claude-Skills content-creatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add borghei/Claude-Skills --skill content-creator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/marketing/content-creator .github/skills/content-creator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "content-creator" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/content-creator into .github/skills/content-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-creator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add borghei/Claude-Skills --skill content-creator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install borghei/Claude-Skills content-creator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/marketing/content-creator .opencode/skills/content-creator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "content-creator" agent skill from https://github.com/borghei/Claude-Skills/tree/main/marketing/content-creator into .opencode/skills/content-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "content-creator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
content-creatorCreate SEO-optimized marketing content with consistent brand voice, using a brand voice analyzer, SEO optimizer, and content frameworks.
Content Creator is an agent skill from borghei/Claude-Skills. Create SEO-optimized marketing content with consistent brand voice, using a brand voice analyzer, SEO optimizer, and content frameworks. Use when writing blog posts, creating social content, or analyzing brand voice.
Its SKILL.md is about 4.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts, reference files and assets (for example `assets/content_calendar_template.md`, `examples/brand_voice_analysis_example.md` and `examples/seo_optimization_example.md`).
It sits in Writing & Content, covering Blog and article writing, Brand voice and tone and Social media posts. The repository describes itself as: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit… The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit c9a1487. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Content Creator loads about 4.6k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 58 tokens; SKILL.md has 2,007 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from borghei/Claude-Skills at commit c9a1487, republished under its MIT licence (© borghei). 2,007 words, ~4,603 tokens.
.claude/skills/content-creator/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.Professional-grade brand voice analysis, SEO optimization, and platform-specific content frameworks.
content creation, blog posts, SEO, brand voice, social media, content calendar, marketing content, content strategy, content marketing, brand consistency, content optimization, social media marketing, content planning, blog writing, content frameworks, brand guidelines, social media strategy
Before creating the content, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
scripts/brand_voice_analyzer.py on existing content to establish baselinereferences/brand_guidelines.md to select voice attributesreferences/content_frameworks.mdscripts/seo_optimizer.py [file] [primary-keyword] to optimizereferences/social_media_optimization.mdreferences/content_frameworks.mdassets/content_calendar_template.mdFor new brands or clients:
Step 1: Analyze Existing Content (if available)
python scripts/brand_voice_analyzer.py existing_content.txtStep 2: Define Voice Attributes
references/brand_guidelines.mdStep 3: Create Voice Sample
Step 1: Keyword Research
Step 2: Content Structure
references/content_frameworks.mdStep 3: Optimization Check
python scripts/seo_optimizer.py blog_post.md "primary keyword" "secondary,keywords,list"Step 4: Apply SEO Recommendations
Step 1: Platform Selection
references/social_media_optimization.mdStep 2: Content Adaptation
references/content_frameworks.mdStep 3: Optimization Checklist
Step 1: Monthly Planning
assets/content_calendar_template.mdStep 2: Weekly Distribution
Step 3: Batch Creation
Analyzes text content for voice characteristics, readability, and consistency.
Usage:
# Human-readable output
python scripts/brand_voice_analyzer.py content.txt
# JSON output for integrations
python scripts/brand_voice_analyzer.py content.txt jsonParameters:
| Parameter | Required | Description |
|---|---|---|
file | Yes | Path to content file |
format | No | Output format: text (default) or json |
Output:
Analyzes content for SEO optimization and provides actionable recommendations.
Usage:
# Basic analysis
python scripts/seo_optimizer.py article.md "main keyword"
# With secondary keywords
python scripts/seo_optimizer.py article.md "main keyword" "secondary,keywords,list"
# JSON output
python scripts/seo_optimizer.py article.md "keyword" --jsonParameters:
| Parameter | Required | Description |
|---|---|---|
file | Yes | Path to content file (md or html) |
primary_keyword | Yes | Main target keyword |
secondary_keywords | No | Comma-separated secondary keywords |
--json | No | Output in JSON format |
Output:
references/brand_guidelines.md
references/content_frameworks.md
references/social_media_optimization.md
references/analytics_guide.md
This skill works best with:
references/analytics_guide.md)| Problem | Likely Cause | Solution |
|---|---|---|
| SEO score is low despite keyword inclusion | Keywords present but not in strategic positions (title, H1, first paragraph, H2s) | Place primary keyword in the first paragraph, at least one H2, and the page title. Keyword density alone is no longer a ranking factor -- placement and natural integration matter more in 2026 |
| Brand voice analyzer shows inconsistent results across content | Multiple authors writing without shared voice guidelines | Establish a baseline by running brand_voice_analyzer.py on your best-performing content. Document the formality score, tone, and perspective as your target profile. Have all authors reference this baseline |
| Content ranks initially then drops | Thin content or lack of E-E-A-T signals | Google's December 2025 core update and helpful content system penalize shallow content. Add first-person experience, original data (3+ fresh statistics per 1,000 words), expert quotes, and case studies. Content must demonstrate Experience that AI cannot replicate |
| AI-generated content flagged or not ranking | Unedited AI output lacking human oversight, expertise, or originality | Google does not penalize AI-assisted content per se, but mass-produced AI content without human review, original perspective, or expertise signals will underperform. Always add personal experience, proprietary data, and fact-checked claims. Layer in E-E-A-T signals: author bylines with credentials, cited sources, real examples |
| SEO optimizer recommends increasing keyword density above 3% | Legacy recommendation conflicting with current best practice | Override any density target above 2%. A 2026 study of 1,500+ Google results found no correlation between keyword density and ranking. Pages in the top 10 have 50% lower keyword density than two years ago. Focus on topical coverage and semantic relevance instead |
| Content not winning featured snippets | Missing concise answer format near the top of the page | Provide a 2-3 sentence direct answer to the core question within the first 120-150 words. Use short paragraphs (2-4 sentences), bulleted lists, and clear H2/H3 subheadings. Featured snippets have 42.9% CTR -- the highest of any SERP feature |
| Social media content underperforming despite good blog content | Direct copy-paste without platform adaptation | Each platform requires format-specific adaptation. LinkedIn favors 1,300-character posts with carousel documents (21.77% median engagement rate). Instagram prioritizes visual-first carousel posts. TikTok requires short-form video. Use the repurposing matrix in references/content_frameworks.md |
brand_voice_analyzer.py. Variance of more than 15 points in formality score between pieces indicates inconsistencyIn Scope:
Out of Scope:
| Integration | Purpose | How to Connect |
|---|---|---|
| Google Search Console | Monitor indexing, search queries, CTR, and position data | Use Search Console data to identify underperforming pages, then run seo_optimizer.py to diagnose and fix issues. Track position changes after optimization |
| Google Analytics 4 (GA4) | Content performance measurement, engagement metrics | Measure page views, time on page, bounce rate, and conversions per content piece. Feed insights back into content strategy decisions |
| SEO Tools (Ahrefs, SEMrush, Moz) | Keyword research, backlink data, competitive analysis | Export target keywords from SEO tools to use as input for seo_optimizer.py. Use competitive gap analysis to inform content topics |
| CMS Platforms (WordPress, Webflow, Ghost) | Content publishing and meta tag implementation | Apply meta tag suggestions from seo_optimizer.py directly to CMS fields. Implement heading structure recommendations in post editor |
| social-media-analyzer skill | Social content performance tracking | Analyze which content formats and topics perform best on social, then use findings to inform content creation priorities |
| campaign-analytics skill | Content ROI measurement | Track content-attributed conversions through campaign analytics. Identify which content pieces drive the most pipeline or revenue |
| app-store-optimization skill | App description writing | Apply SEO writing principles and brand voice consistency to app store descriptions using shared voice guidelines |
Type: CLI script (positional arguments, no argparse flags)
Usage:
python brand_voice_analyzer.py <file> [format]| Argument | Position | Required | Default | Description |
|---|---|---|---|---|
file | 1st | Yes | -- | Path to text content file to analyze |
format | 2nd | No | text | Output format: text (human-readable) or json (machine-readable) |
Output Fields:
word_count -- Total words in contentreadability_score -- Flesch Reading Ease (0-100). Below 30 = difficult, 30-60 = moderate, 60-70 = standard, 70+ = easyvoice_profile -- Per-dimension analysis:formality -- Dominant: formal or casual (based on keyword matching)tone -- Dominant: professional or friendlyperspective -- Dominant: authoritative or conversationalsentence_analysis -- Average sentence length (words), variety (low/medium/high), total countrecommendations -- Actionable suggestions for readability, sentence variety, and voice consistencyType: CLI script (positional arguments with one optional flag)
Usage:
python seo_optimizer.py <file> [primary_keyword] [secondary_keywords] [--json]| Argument | Position/Flag | Required | Default | Description |
|---|---|---|---|---|
file | 1st | Yes | -- | Path to content file (markdown or HTML) |
primary_keyword | 2nd | No | None | Main target keyword for density and placement analysis |
secondary_keywords | 3rd | No | None | Comma-separated secondary keywords (e.g., "seo,content,optimization") |
--json | Flag | No | text output | Output raw JSON instead of human-readable format |
Output Fields:
optimization_score -- Overall SEO score (0-100). Scoring: content length (20 pts), keyword optimization (30 pts), structure (25 pts), readability (25 pts)content_length -- Word countkeyword_analysis:primary_keyword -- Count, density (0-1 scale), in_first_paragraph (bool), in_headings (bool)secondary_keywords -- Per-keyword count and densitylsi_keywords -- Top 10 semantically related terms extracted from contentstructure_analysis -- Heading counts (h1/h2/h3), paragraph count, average paragraph length, list count, internal/external link countsreadability -- Score (0-100), level (Easy/Moderate/Difficult/Very Difficult), average sentence lengthmeta_suggestions -- Generated title, meta description, URL slug, Open Graph tagsrecommendations -- Prioritized list of specific improvement actions© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 9 other files (scripts, references, assets) in marketing/content-creator of borghei/Claude-Skills.
Open the folder on GitHubat commit c9a1487
Content Creator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Content Creator this skillborghei/Claude-Skills | 874 | — | ~4.6k | Automated safety check: Pass | MIT | |
| Voice Buildercharlie947/social-media-skills | 3.8k | — | ~3.3k | Automated safety check: Pass | MIT | |
| Content Writerchrispangg/deepagentsdk | 128 | — | ~3.3k | Automated safety check: Pass | MIT | |
| Content Creatorthatrebeccarae/claude-marketing | 162 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Content Creatorsickn33/agentic-awesome-skills | 47k | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Writewaynesutton/markdown-site | 628 | — | ~3k | Automated safety check: Pass | MIT |
charlie947/social-media-skills
Build a personalised voice profile inside a Codex or Claude project from a short interview plus 3 to 5 sample pieces of writing.
chrispangg/deepagentsdk
Writing content across different platforms and styles. An agent skill from chrispangg/deepagentsdk.
thatrebeccarae/claude-marketing
Comprehensive content marketing toolkit with brand voice analysis, SEO optimization scripts, content frameworks, social media strategy, and content calendar planning.
sickn33/agentic-awesome-skills
Drafts and reviews audience-specific content from supplied brand examples, with local scripts for brand voice and SEO diagnostics, channel templates and a content calendar.
waynesutton/markdown-site
Writing style guide for technical content, social media, blog posts, READMEs, git commits, and developer documentation.
indranilbanerjee/digital-marketing-pro
Draft marketing content in brand voice — blog posts, ad copy, email sequences, social posts, landing pages, and brand-voice guides — through a gated pipeline (research, outline, draft, fact-check…
borghei/Claude-Skills
Run delivery when AI coding and ops agents take tickets. An agent skill from borghei/Claude-Skills.
borghei/Claude-Skills
Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies.
borghei/Claude-Skills
Idea to AI-generated prototype to customer validation to engineering handoff.
borghei/Claude-Skills
Analytics engineering across data modeling, dbt, transformation, and semantic layers.
borghei/Claude-Skills
Ansoff Matrix — 4-quadrant framework for growth options: market penetration, market/product development, and diversification.
borghei/Claude-Skills
OKR brainstorming and validation using the Radical Focus framework — outcome objectives, measurable key results, counter-metrics.
Categories
Create SEO-optimized marketing content with consistent brand voice, using a brand voice analyzer, SEO optimizer, and content frameworks. Content Creator is an agent skill from borghei/Claude-Skills. Create SEO-optimized marketing content with consistent brand voice, using a brand voice analyzer, SEO optimizer, and content frameworks.
Content Creator fits situations like: writing blog posts; creating social content; analyzing brand voice.
Run `npx skills add borghei/Claude-Skills --skill content-creator -a claude-code`. Or copy the skill folder (marketing/content-creator in borghei/Claude-Skills) into .claude/skills/content-creator in your project. Claude Code loads it when a task matches its description.
Run `npx skills add borghei/Claude-Skills --skill content-creator -a codex`. Or copy the skill folder (marketing/content-creator in borghei/Claude-Skills) into .agents/skills/content-creator in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add borghei/Claude-Skills --skill content-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/content-creator, .gemini/skills/content-creator, .github/skills/content-creator and .opencode/skills/content-creator in your project.
Going by SKILL.md and its folder, Content Creator needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Content Creator is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.6k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Content Creator: Voice Builder (charlie947/social-media-skills, 3.8k stars), Content Writer (chrispangg/deepagentsdk, 128 stars), Content Creator (thatrebeccarae/claude-marketing, 162 stars) and Content Creator (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
borghei (a GitHub user) maintains it in borghei/Claude-Skills, which has 874 GitHub stars. The repository holds 364 skills in this directory. The repository was last updated on October 7, 2026.
Source: borghei/Claude-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.