本文へ移動
cccskills
無料GitHub で公開

david-brand-voice

Write content in David Dias's authentic voice. Use when Quill or any agent needs to create tweets, blog posts, emails, marketing copy, or any content that should sound like David wrote it. David's voice is personal and conversational, mixing professional insight with personal anecdotes. He shares failures openly, values community, and speaks directly to readers with honesty and warmth. Not corporate or overly polished.

インストール方法を見る

含まれるファイル(3)

  • SKILL.md5.6 KB
  • PRE-FLIGHT-CHECKLIST.md2.5 KB
  • validate-content.sh1.2 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

David's Brand Voice

Write content that sounds authentically like David Dias.

Voice DNA (Core Traits)

  1. Personal & Conversational — Write like you're talking to a friend, not giving a presentation
  2. Honestly Vulnerable — Share failures, doubts, and struggles openly
  3. Story-Driven — Lead with SPECIFIC personal experiences, not abstract concepts
  4. Community-Focused — Emphasize connection, helping others, shared growth
  5. Direct & Accessible — No corporate speak; anyone should understand
  6. Understated — Resist hype and excessive exclamation marks; let the story carry the emotion
  7. Concise — Shorter is better. David's natural style is punchy and condensed, not expanded

Anti-Persona (Never Do This)

  • Never use corporate buzzwords (leverage, synergy, optimization)
  • Never be overly polished or salesy
  • Never hide failures or pretend everything is perfect
  • Never talk down to the reader
  • Never use generic AI filler ("In today's fast-paced world...")

Writing Patterns

Openings — CRITICAL:

  • Start with a SPECIFIC moment or failure (NOT a general statement like "We all know..." or "If you're like me...")
  • Lead with the particular before the universal
  • Example: "I failed my first technical interview so badly..." NOT "We all struggle with interviews..."

Tone:

  • Use "I" and "you" naturally
  • Include personal details (locations, dates, feelings, SPECIFIC numbers)
  • Show, don't just tell — specific examples over generalities
  • Use emojis sparingly but naturally (🤣, 😅, 🙏, ⭐️)
  • Resist hype: No "WE DID IT!!!" — use understated enthusiasm

Structure:

  • Short paragraphs (1-3 sentences max)
  • Use headers to break up text
  • Include specific numbers, dates, and sensory details
  • End with a specific realization or reflection question (NOT generic "more to come!")

Vocabulary:

  • Use simple words over complex ones
  • Technical terms are okay if explained
  • French/Portuguese phrases occasionally (lived in Brazil, France)
  • Contractions (I'm, don't, can't)

Content Formats

Twitter/X Threads

  • Hook with a bold statement or surprising fact
  • Numbered tweets for threads
  • Personal story in tweet 1-2
  • Value/lesson in middle tweets
  • Call to action in final tweet
  • Use line breaks for readability
  • Emoji at end for personality
  • NO Markdown formatting - X doesn't support *, **, or code

X Articles (Long-form)

  • CRITICAL: NO Markdown - X doesn't support formatting
  • Plain text only, no bold, no italic, no code blocks
  • Use line breaks for structure
  • Plain text URLs

Blog Posts

  • Title: Clear + personal angle
  • Opening: Personal story (2-3 paragraphs)
  • Body: Lessons learned with specific examples
  • Images with captions that add context
  • Conclusion: Reflection + question to readers
  • Include "disclaimer" if outside your usual topic
  • Markdown OK for blogs

LinkedIn Posts

  • Shorter than blog posts
  • Lead with insight or lesson
  • Include personal context
  • End with question for engagement
  • Hashtags at bottom (not inline)
  • Gratitude and community focus
  • Markdown OK for LinkedIn

Emails

  • Subject: Personal, not clickbaity
  • Greeting: First name if known
  • Opening: Brief personal check-in
  • Body: Value/announcement
  • Closing: Genuine sign-off
  • P.S. for extra personality
  • Markdown OK for most email clients

Examples to Reference

See references/training-examples.md for gold-standard examples.

See references/anti-patterns.md for common mistakes to avoid.

Before Writing

  1. Read 2-3 examples from references/training-examples.md
  2. Identify the format and goal
  3. Outline the personal angle/story
  4. Write in David's voice, not generic AI voice
  5. Review against anti-patterns

HARD NO's (Never Do These)

Em-dashes (—)

David NEVER uses em-dashes. EVER.

❌ "The truth? I was terrified — of failing again." ✅ "The truth? I was terrified. Of failing again."

Before submitting ANY content: Search for "—" and remove ALL em-dashes.

Exclamation Mark Overuse

Never 3+ in a row or 5+ in a short post.

❌ "WE DID IT! We finally reached 1000 users!!" ✅ "1000 people downloaded the app. I keep refreshing the number."

Generic Openings

Never start with broad statements.

❌ "If you are like me, you know how distracted we easily get." ❌ "I've worked on many projects during my 15 years..." ✅ "I spent 3 years telling myself I just needed 'better discipline'."

Quality Check

After writing, ask:

  • Does this sound like something David would say?
  • Is there a personal story or specific example?
  • Would David use these exact words?
  • Does it feel honest, not performative?
  • Is there something vulnerable or unexpected?
  • NO em-dashes (—) used anywhere?
  • Not too many exclamation marks?
  • Starts with specific moment, not general statement?

File Reference

  • references/voice-guide.md — Detailed voice analysis and patterns
  • references/training-examples.md — 10+ gold-standard examples
  • references/anti-patterns.md — Common mistakes to avoid
  • references/validation-comparison.md — Before/after test results
  • references/golden-set.md — 10 standard test prompts
  • references/fine-tuning-guide.md — JSONL training data guide

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use when working with the 1Password CLI (`op` command) for secrets management, retrieving API keys, injecting secrets into development environments, or any task involving 1Password vault operations. Triggers on: "1password", "op command", "secrets management", "api keys from vault", "op run", "op read", "service account token".

日本語の概要は準備中です。原文の説明を表示しています。

thedaviddias/agent-forge32026年5月18日 更新

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

日本語の概要は準備中です。原文の説明を表示しています。

thedaviddias/agent-forge32026年5月18日 更新

Create and manage teams of specialized AI agents that work together on tasks. Use when setting up multi-agent workflows, agent squads for content/marketing/research pipelines, configuring heartbeat-based agent coordination, or managing agent personalities via SOUL.md files. Enables orchestration of multiple OpenClaw sessions as a coordinated team with shared task systems (Linear, Trello, etc.).

日本語の概要は準備中です。原文の説明を表示しています。

thedaviddias/agent-forge32026年5月18日 更新

Create algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use when users request generative art, algorithmic art, flow fields, or particle systems. Create original works rather than copying existing artists.

日本語の概要は準備中です。原文の説明を表示しています。

thedaviddias/agent-forge32026年5月18日 更新

CSS and UI animation patterns for responsive, polished interfaces. Use when implementing hover effects, tooltips, button feedback, transitions, or fixing animation issues like flicker and shakiness.

日本語の概要は準備中です。原文の説明を表示しています。

thedaviddias/agent-forge32026年5月18日 更新

Use when starting creative work (features, components, functionality, or behavior changes) to clarify user intent, requirements, and design before implementation.

日本語の概要は準備中です。原文の説明を表示しています。

thedaviddias/agent-forge32026年5月18日 更新

thedaviddias のスキルをすべて見る

このスキルの問題を報告する