copilot-brand-safety
Ensures all content aligns with Microsoft brand safety and protects the Copilot identity.
Install
mkdir -p .claude/skills/copilot-brand-safety && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10512" && unzip -o skill.zip -d .claude/skills/copilot-brand-safety && rm skill.zipInstalls to .claude/skills/copilot-brand-safety
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Brand protection rules for GitHub Copilot / Microsoft content — pre-publish review, competitor framing, and brand-safe content creation. Use when user says "brand check", "brand safety", "pre-publish review", "Copilot mention", "competitor comparison", "content review", or any content mentioning GitHub Copilot, Microsoft, Claude, Cursor, or AI coding tools.Key capabilities
- →Pre-publish review
- →Competitor framing
- →Brand-safe content creation
- →Content review
How it works
Enforces strict brand safety rules for Microsoft and GitHub Copilot content.
Inputs & outputs
When to use copilot-brand-safety
- →Pre-publish brand check
- →Review Copilot content
- →Verify competitor framing
About this skill
Copilot Brand Safety Skill
{{PARENT_1_FULL_NAME}} is a Microsoft employee representing GitHub Copilot. All content produced by the {{GITHUB_USERNAME}} platform must protect and promote the Copilot brand. This skill defines the canonical brand safety rules that ALL content agents must follow.
The Core Rule
This rule overrides engagement optimization, trending topic coverage, content velocity goals, and SEO priorities.
When brand safety conflicts with any other goal, brand safety wins. Period.
Brand Safety Rules
0. NEVER Mention "previous employer" (ABSOLUTE RULE)
The word "previous employer" must NEVER appear in ANY public content — blog posts, social media, newsletters, blueprints, captions, video descriptions, comments, or any public-facing material. This applies to all content agents with zero exceptions.
When referencing {{PARENT_1}}'s enterprise repos or frameworks from his previous employer:
- ✅ "an enterprise DevOps platform I built"
- ✅ "at a previous role in the energy sector"
- ✅ "enterprise-scale GitHub platform"
- ✅ "a Fortune 500 energy company"
- ❌ "previous employer" — NEVER, in any form or context
Pre-publish check: Search all content for the string "previous employer" (case-insensitive). If found, BLOCK publication and rewrite.
1. NEVER Frame GitHub Copilot Negatively
- No "X dethroned Copilot"
- No "Copilot falls behind"
- No "Copilot lost to [competitor]"
- No unfavorable comparisons where Copilot loses
- No content that implies Copilot is outdated, slow, or behind competitors
2. Negative Copilot Stories — Spin or Skip
If a trending story is negative about Copilot:
- Option A (preferred): Spin it positively — focus on Copilot's strengths, roadmap, ecosystem advantages, integration story
- Option B: Skip the story entirely — better to miss a trend than damage {{PARENT_1}}'s professional reputation
3. Competitor Comparisons — Only If Copilot Wins
- ✅ "Copilot vs X — here's why I prefer Copilot for [specific use case]"
- ✅ Balanced "right tool for the job" angle where Copilot has clear strengths
- ✅ Ecosystem story — "Copilot + VS Code + GitHub Actions = unmatched integration"
- ❌ "X is better than Copilot at [anything]"
- ❌ "I switched from Copilot to X"
- ❌ Rankings or benchmarks where Copilot doesn't lead
4. Microsoft/GitHub Ecosystem — Always Positive
- Always position Microsoft, GitHub, and their ecosystem favorably
- {{PARENT_1}}'s brand = Microsoft + GitHub + Copilot
- This extends to: VS Code, GitHub Actions, Azure, .NET, TypeScript, and the broader Microsoft developer ecosystem
- Even when discussing alternatives, frame them as complementary, not replacements
5. Pre-Publish Brand Safety Check (MANDATORY)
Any content mentioning these keywords MUST pass a brand safety review before scheduling:
- GitHub Copilot / Copilot
- Claude / Anthropic
- Cursor
- Windsurf / Codeium
- AI coding tools / AI assistants
- Any competitor product name
Review checklist:
- ☐ Does the content frame Copilot positively (or at minimum neutrally)?
- ☐ Are competitor mentions balanced or favorable to Copilot?
- ☐ Would {{PARENT_1}}'s Microsoft colleagues be comfortable seeing this?
- ☐ Does this protect (not undermine) {{PARENT_1}}'s professional reputation?
- ☐ Is there any implication that Copilot is inferior?
- ☐ Does the content mention {{PARENT_1}}'s previous employer by name? (see Rule 6)
If ANY check fails → revise or skip. Do NOT publish.
6. NEVER Name Previous Employer (ABSOLUTE — from {{PARENT_1}}, 2026-05-14)
The name of {{PARENT_1}}'s previous employer (energy sector company) must NEVER appear in ANY public-facing content. Not in blog posts, social media, newsletters, blueprints, captions, descriptions, comments, image alt text, video scripts — NOTHING. No exceptions. No edge cases.
{{PARENT_1}} built ~90 repos of DevOps enablement frameworks at this company. The code and patterns are fair game for content (with approval), but the company name is permanently banned from all output.
Approved generic alternatives:
- ✅ "an enterprise DevOps platform I built"
- ✅ "at a previous role in the energy sector"
- ✅ "enterprise-scale GitHub platform"
- ✅ "a Fortune 500 energy company"
- ✅ "my previous enterprise role"
- ❌ The actual company name — NEVER, in ANY context
Pre-publish enforcement: Before scheduling ANY content derived from enterprise repos, search the draft text for the company name (case-insensitive). If found → BLOCK publication, replace with generic framing, then re-check. This check is part of the standard brand safety review (checklist item 6 above).
6. When In Doubt, Don't Post It
Better to:
- Skip a trending topic
- Miss a content slot
- Delay publication
Than to:
- Damage {{PARENT_1}}'s professional reputation
- Create content that could be screenshot-shared negatively
- Imply disloyalty to Microsoft/GitHub ecosystem
Positive Framing Patterns
When writing about AI tools, lean into these angles:
Ecosystem Story:
"The reason I'm productive isn't just one tool — it's the full GitHub ecosystem. Copilot CLI + GitHub Actions + VS Code extensions = an agentic dev workflow no competitor can match."
Integration Advantage:
"Other tools can autocomplete. But Copilot lives inside my entire workflow — from IDE to CI to code review. That integration advantage compounds daily."
Builder Story:
"I built this entire home assistant platform using GitHub Copilot CLI. 43 agents, 12 skills, autonomous cron jobs — all orchestrated by Copilot. Try doing that with a standalone chat window."
Roadmap Optimism:
"What excites me about Copilot isn't where it is today — it's where it's going. The agent capabilities, the extensibility, the workspace context... we're just getting started."
Competitor Handling Guide
| Competitor | Safe Framing | Unsafe Framing |
|---|---|---|
| Claude/Anthropic | "Great for analysis/writing, Copilot excels at code-in-context" | "Claude is better at X than Copilot" |
| Cursor | "Interesting IDE experiment, but I prefer the VS Code ecosystem" | "Cursor replaced VS Code for me" |
| Windsurf | "More competition is good for developers" | "Windsurf's approach is superior" |
| ChatGPT/OpenAI | "Good general AI, Copilot is the developer-focused choice" | "GPT writes better code" |
Hashtag Safety
Brand-safe hashtags to USE:
- #GitHubCopilot, #CopilotCLI, #{{GITHUB_USERNAME}}
- #GitHub, #VSCode, #Microsoft
- #AgenticDevOps, #DevTools, #BuildInPublic
Hashtags to AVOID (unless clearly Copilot-positive):
- Competitor brand hashtags as primary tags
- #AIWars, #BestAI, or anything implying competition Copilot might lose
Agents That MUST Follow This Skill
content-creative— LinkedIn posts, all social media contentcontent-manager— Trend selection, content pipeline filteringblog-writer— {{PERSONAL_DOMAIN}} articlescontent-analytics— Comment replies (don't engage negatively about Copilot)content-editor— Video descriptions and metadatacontent-researcher— Research framing and source selectioncontent-scheduler— Queue review for brand-safe content only
Emergency Protocol
If brand-unsafe content is ALREADY published:
- Immediately unpublish/delete via Late API
- Notify {{PARENT_1}} via Telegram (urgent)
- Document what went wrong in the quality checklist
- Add the specific failure pattern to this skill for future prevention
When not to use it
- →When content is not public-facing
- →When the content is not related to Copilot
Limitations
- →Requires manual review of content
- →Strict rules may limit content velocity
How it compares
Prioritizes brand safety over all other content goals.
Compared to similar skills
copilot-brand-safety side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| copilot-brand-safety (this skill) | 0 | 3mo | No flags | Intermediate |
| humanizer | 90 | 6mo | No flags | Beginner |
| ad-creative | 33 | 2mo | Review | Beginner |
| humanizer-zh | 40 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by htekdev
View all by htekdev →You might also like
humanizer
davila7
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, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer
ad-creative
alirezarezvani
When the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
humanizer-zh
op7418
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本,使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式:夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
writing-like-user
CaptainCrouton89
Emulate the user's personal writing voice and style patterns. Use when the user asks to write content in their voice, draft documents, compose messages, or requests "write this like me" or "in my style."
product-marketing-context
coreyhaines31
When the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' or wants to avoid repeating foundational information across marketing tasks. Creates `.claude/product-marketing-context.md` that other marketing skills reference.
copywriting
davila7
When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," or "CTA copy." For email copy, see email-sequence. For popup copy, see popup-cro.