Communitygithub.com

AlemTuzlak/skills

Use when the user wants to write a product update email, feature announcement newsletter, or digest email for users or subscribers

skills 是什么?

skills is a Claude Code agent skill that use when the user wants to write a product update email, feature announcement newsletter, or digest email for users or subscribers.

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/AlemTuzlak/skills/tree/HEAD/skills/newsletter

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Newsletter Writer

Write product update emails and feature announcement newsletters. Handles subject lines, preview text, email structure, and audience-appropriate content.

Input Resolution

Resolve the argument (if provided) in this order:

  1. Path to an existing marketing brief (.md containing "Executive Summary" or "Key Messages") -> marketing brief
  2. Path to an existing blog post (.md with blog post structure) -> blog post
  3. Path to an existing changelog (.md with Added/Fixed/Changed sections or CHANGELOG.md) -> changelog
  4. Matches GitHub URL or #\d+ pattern -> PR
  5. Contains ... or .. -> git ref range
  6. Resolves to existing file/directory -> codebase feature
  7. Otherwise -> freeform text

If no argument is provided, ask: "What should the newsletter cover? You can provide a marketing brief, blog post, changelog, PR URL/number, git ref range, file/directory path, or just describe the update."

If multiple interpretations match, confirm with the user.

Process Flow

digraph newsletter {
    rankdir=TB;
    "Resolve input" [shape=box];
    "Phase 1: Discovery" [shape=box];
    "Phase 2: Configure" [shape=box];
    "Phase 3: Write" [shape=box];
    "Phase 4: Review" [shape=box];
    "Approved?" [shape=diamond];
    "Phase 5: Output" [shape=box];

    "Resolve input" -> "Phase 1: Discovery";
    "Phase 1: Discovery" -> "Phase 2: Configure";
    "Phase 2: Configure" -> "Phase 3: Write";
    "Phase 3: Write" -> "Phase 4: Review";
    "Phase 4: Review" -> "Approved?";
    "Approved?" -> "Phase 3: Write" [label="revisions"];
    "Approved?" -> "Phase 5: Output" [label="yes"];
}

Do NOT skip phases. Ask questions at a natural pace. If the user answers multiple questions at once, accept bundled answers and skip ahead.

If the user says "just pick defaults", "you choose", or similar, pick reasonable defaults based on context, state what you chose, and ask for a single confirmation before proceeding.

Never assume without confirming.

Phase 1: Discovery

Step 1 - Analyze the input

Input typeWhat to read
Marketing briefExtract problem statement, value prop, audience, key messages. Skip to Step 3. Still do Step 2 if brief lacks product context.
Blog postExtract headline, key points, audience, CTA. Skip to Step 3. Still do Step 2 if lacking product context.
ChangelogExtract all entries. Use as the basis for a digest email. Skip to Step 3.
PRDiff, PR description, review comments, commit messages (gh pr view, gh pr diff). For large PRs (20+ files), focus on user-facing changes.
Git refsgit diff and git log between refs. For large ranges, prioritize commit messages and user-facing changes.
Codebase featureRead the specified files/directories.
Freeform textParse the user's description. If it lacks specifics, ask the user to provide more detail or point to a specific file/PR. Fall back to open-ended questions only if they can't.

User-facing changes include: new features, UI changes, API changes, performance improvements, bug fixes, and documentation updates. Internal changes include: refactors, test additions, CI changes, and dependency bumps. When uncertain, list what you found and ask the user which are relevant.

Error handling:

  • gh not available -> inform user, suggest gh auth login, offer alternative input
  • Invalid PR/ref -> ask user to verify
  • File not found -> ask for correct path

Step 2 - Read broader product context

Read if they exist: README, docs/, package.json (or equivalent).

If nothing found, ask: "I couldn't find product context in the repo. Can you briefly describe the product and who it's for?"

Step 3 - Present understanding and determine format

Present a structured summary:

"Here's what I'll base the newsletter on:"

  • Update A - short description
  • Update B - short description

"Anything to add, remove, or correct?"

Then determine the email format based on the number of updates:

  • Single major update -> single feature email (focused, deep)
  • Multiple updates -> digest email (prioritized list, most important expanded)

Confirm the format with the user.

If no user-facing changes are found in the input, tell the user and stop: "No user-facing changes found in this input. Nothing to write a newsletter about."

Do NOT proceed until the user confirms scope and format.

Phase 2: Configuration

Ask these questions:

Q1 - Audience: "Who is this email going to?" (all users, power users, new users, specific plan tier, developers, non-technical users, other)

Q2 - Output format: "What format do you want the email in?"

  • Copy only - subject line, preview text, body text, CTA text (drop into your email tool)
  • Markdown - formatted markdown that most email tools can import

Q3 - Tone: Read existing repo content (README, docs, blog posts) to detect the product's voice. Then confirm:

"Based on your existing content, the tone seems [e.g. conversational and developer-friendly]. Should I match that or go a different direction?"

If no existing content to analyze, ask directly what tone the user wants.

Q4 - CTA: Infer the most appropriate call to action from context:

  • New feature -> "Try it now", "See what's new"
  • Improvement -> "Check it out", "See the difference"
  • Open source -> "Update now", "See the release"

"I'd suggest the CTA be: [inferred CTA]. Want to go with that or something different?"

Phase 3: Write

Subject lines

Generate 3-5 subject line options with different approaches:

  • Benefit-driven ("Your reports now export to PDF")
  • Curiosity ("We rebuilt how search works")
  • Specific feature name ("Introducing dark mode")
  • Question ("Still waiting for exports to finish?")
  • Urgency/timeliness ("New this week: 3 features you asked for")

Recommend one and explain why it works best. Also explain the trade-offs of the others.

Rules:

  • 30-50 characters optimal (avoid truncation on mobile)
  • Be specific, not generic ("New: PDF exports" beats "Product Update - March 2026")
  • No spam trigger words (Free, Buy Now, Act Now)

Preview text

Generate preview text for each subject line option. Preview text is the secondary line visible in inbox previews.

Rules:

  • 40-130 characters
  • Expand on the subject line, don't repeat it
  • Include the key benefit or outcome

Email body

Single feature email structure:

  1. Problem statement - one sentence describing the pain point this solves
  2. What changed - 2-3 sentences describing the update in user-benefit language ("Reports load faster" not "Optimized SQL query execution")
  3. Visual placeholder - <!-- TODO: Add screenshot or GIF showing the feature in action --> with a description of what to capture
  4. CTA button - single clear action

Digest email structure:

  1. Lead update - the most important update gets the full single-feature treatment (problem, what changed, visual, CTA)
  2. Secondary updates - brief bullets with one-line descriptions and links
  3. Quick fixes / improvements - grouped list of smaller changes
  4. Closing CTA - single action or "See all updates"

Writing rules

  • Lead with user benefit, not what you built
  • Conversational tone, not corporate
  • Short paragraphs (2-3 sentences max)
  • One idea per paragraph
  • Never use em-dashes in the generated content. No "---" characters. Use commas, colons, periods, or parentheses instead.
  • No jargon. "Reports load faster" beats "Optimized SQL query execution plan"
  • Bold key phrases for scannability
  • Keep it scannable. Shorter is better. If the email takes more than 60 seconds to read, it's too long.

Segment variants

After generating the primary email, ask:

"Want me to generate variants for different audience segments? (e.g. a more technical version for developers, a simpler version for non-technical users)"

If yes, generate the requested variants, adjusting tone, depth, and feature emphasis per segment.

Phase 4: Review

Present the complete email:

"Here's the newsletter:"

Subject line options: (with recommendation and preview text for each)

  1. Subject: "..." / Preview: "..."
  2. Subject: "..." / Preview: "..."
  3. Subject: "..." / Preview: "..."

Body: [full email content]

"Pick a subject line and let me know if you want any changes."

Wait for the user to select a subject line and approve or request revisions. Only proceed to output once approved.

Phase 5: Output

Always print the final approved email to terminal.

Then ask: "Want me to save this to emails/<slug>.md? Or a different path?"

Create the directory if it doesn't exist. If file already exists, ask whether to overwrite or create a versioned copy.

Error Handling

  • gh not available -> inform user, offer alternative input
  • Invalid PR/ref -> ask user to verify
  • No product context -> ask user to describe the product
  • No existing email directory -> default to emails/, create it

What this skill does NOT do

  • Send or schedule emails
  • Manage subscriber lists or segmentation logic
  • Create email templates or design systems
  • Generate blog posts or social copy (use /blog-post or /social-copy)

Individual skills in this repo

This repo contains 10 individual skills — each has its own dedicated page.

AlemTuzlak/skills

Use when the user wants to write a blog post about a feature, product change, PR, git diff, or any technical topic - accepts marketing briefs, PRs, git refs, codebase paths, or freeform descriptions as input

AlemTuzlak/skills

Use when the user wants to generate a changelog, release notes, or document what changed between versions, tags, or PRs

AlemTuzlak/skills

Use when writing, editing, or organizing documentation, when planning what docs a feature needs, and whenever planning or implementing a new feature or change in a repo (docs ship with the code). Also use when tempted to write docs without showing the discovered readers to the user, without asking for tone, or without loading simple-english and i-have-adhd. Triggers on "write docs for X", "document this feature", "add a guide", "update the docs", "reorganize the docs", "plan feature X", "implement X", or /docs.

AlemTuzlak/skills

Use when a bug is in play: a test fails, CI is red, an API returns the wrong result, a stack trace appears, or the user says it is broken or fix this. Don't use for a new feature with no failure, for types-only work, or for docs.

AlemTuzlak/skills

Use when the user invokes /i-have-adhd, says they have ADHD, or asks for ADHD-friendly output. Also used as a required writing filter by the docs skill. Don't use for marketing copy or after the user says "stop adhd mode" or "normal mode".

AlemTuzlak/skills

Use when a settled change must be turned into an ordered stack of small blocks before anyone implements. Don't use for unsettled intent, typos, comments, formatting, docs-only work, or writing the implementation itself.

AlemTuzlak/skills

Use when the user runs /prove-it or says prove it, prove the changes, show me in the browser, or asks to prove a UI or API change. Don't use only because the agent is about to say done, for types-only work, or for docs with no behavior to prove.

AlemTuzlak/skills

Use when the user wants to write, draft, or author an RFC (Request for Comments) / technical design doc for a feature, change, or architectural decision. Interactively interviews the user, grounds the proposal in the actual codebase, presents 2-3 concrete API/code-snippet approaches to choose from, then writes a review-ready RFC. Triggers on "write an RFC", "draft an RFC", "RFC for X", "design doc for X", or /rfc.

AlemTuzlak/skills

Use when the user wants to deeply learn a new topic from scratch. Runs a pre-interview (current knowledge, end-goal proficiency, depth, practice load, background, scope), researches online (articles, niche-influencer blogs, canonical docs, subtopic landscape), then produces a structured markdown course with mandatory visual diagrams, evidence-based learning-science features (retrieval practice, spaced callbacks, worked-example fading, concept ledger, jargon gate, analogy hygiene), and a self-contained interactive HTML mini-course. Triggers on /teach-me, "teach me about X", "I want to learn X", "deep dive on X", "create a course on X", "study X with me".

AlemTuzlak/skills

Use when the change intent is already settled and the agent must map what a behavior change touches before an implementation plan or any code. Use for new features, bug fixes, and refactors that move a boundary. Don't use for typos, comments, formatting, lockfile-only diffs, docs with no code, or while the user is still deciding what they want.

相关技能