From sentry-skills
Writes, reviews, and improves blog posts for Sentry engineering blog using specific voice, banned language rules, opening guidelines, and quality standards.
npx claudepluginhub joshuarweaver/cascade-code-devops-misc-1 --plugin getsentry-skillsThis skill uses the workspace's default tool permissions.
This skill enforces Sentry's blog writing standards across every post — whether you're helping an engineer write their first blog post or a marketer draft a product announcement.
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
This skill enforces Sentry's blog writing standards across every post — whether you're helping an engineer write their first blog post or a marketer draft a product announcement.
The bar: Every Sentry blog post should be something a senior engineer would share in their team's Slack, or reference in a technical decision.
What follows are the core principles to internalize and apply to every piece of content.
We sound like: A senior developer at a conference afterparty explaining something they're genuinely excited about — smart, specific, a little irreverent, deeply knowledgeable.
We don't sound like: A corporate blog, a press release, a sales deck, or an AI-generated summary.
Be technically precise, opinionated, and direct. Humor is welcome but should serve the content, not replace it. Sarcasm works. One good joke per post is plenty.
Use "we" (Sentry) and "you" (the reader). This is a conversation, not a paper.
Never use these. They are automatic red flags:
The opening must do one of two things: state the problem or state the conclusion. Never start with background, company history, or hype.
Good: "Two weeks before launch, we killed our entire metrics product. Here's why pre-aggregating time-series metrics breaks down for debugging, and how we rebuilt the system from scratch."
Bad: "At Sentry, we're always looking for ways to improve the developer experience. Today, we're thrilled to share some exciting updates to our metrics product that we think you'll love."
Structure every post around what the reader is actually wondering, not your internal narrative:
For engineering deep-dives, also address: 5. What did we try that didn't work? (Builds trust) 6. What are the known limitations? (Shows intellectual honesty)
People scroll. Shorter paragraphs are almost always better for keeping people reading.
Break paragraphs at contrast points. When a sentence introduces a "but," "however," or shifts perspective, start a new paragraph. Don't bury the turn inside a block of text.
Bad:
Traditional monitoring tracks requests and latency. That works for stateless HTTP services. AI agents are different. A single run might involve multiple LLM calls, tool executions, and handoffs.
Good:
Traditional monitoring tracks requests and latency. That works for stateless HTTP services.
AI agents are different. A single run might involve multiple LLM calls, tool executions, and handoffs.
The line break before the contrasting point creates visual emphasis. This is standard in online writing even though it breaks traditional paragraph rules.
One idea per paragraph. If a paragraph covers two distinct points, split it. Three-sentence paragraphs are fine. One-sentence paragraphs are fine for emphasis.
No em dashes. Use commas, periods, or line breaks instead. Em dashes are fine in print but create visual clutter in blog formatting.
When targeting a competitive search query:
Lead generic, close specific. The first 50-60% of the post should be tool-agnostic educational content (definitions, concepts, metrics, best practices). Introduce your product as an implementation example in the second half. Google ranks guides higher than product pages for informational queries.
Put keywords in H2s. Generic headings are invisible to search. "Key metrics for AI agent monitoring" beats "What to measure." (See Section Headings below for good/bad examples.)
Include a definitional section. For any head term ("agent observability", "error monitoring"), top-ranking pages almost always have a "What is X?" section. Include one even if it feels basic.
Add an FAQ. 3-4 questions targeting long-tail keywords at the bottom of the post. These can win featured snippets and People Also Ask boxes.
LLM-generated prose has tells. Flag and rewrite these:
Staccato dramatic fragments.
Bumper-sticker aphorisms.
Three-beat reveals.
Smug simplicity.
Parallel structure ad copy.
Personality only in the bookends. AI drafts open with a personal anecdote, go impersonal for 80% of the post, then close with a CTA. The author's voice should persist throughout.
Weak: "Background," "Architecture," "Results," "Conclusion"
Strong: "Why time-series pre-aggregation destroys debugging context," "The scatter-gather approach to distributed GROUP BY," "Where this breaks down: the cardinality wall"
Numbers over adjectives. If you make a performance claim, include the number.
Code must work. If a post includes code, test it. Include imports, configuration, and context. Comments should explain why, not what.
Diagrams for systems. If you describe a system with more than two interacting components, include a diagram. Label with real service names, not generic boxes.
Honesty over hype. Never overstate what a feature does. Acknowledge limitations. If something is in beta, say so. If a competitor does something well, it's okay to note that. Do not claim AI features are more capable than they are — "Seer suggests a likely root cause" ≠ "Seer finds the root cause."
The title is the highest-leverage sentence in the post. It must stop a developer scrolling through their RSS feed or Twitter.
Strong titles make a specific claim, tell a story, or promise a specific payoff:
Weak titles are vague announcements:
End with something useful: a link to docs, source code, a way to try it, or a call to give feedback. Never end with generic hype ("We can't wait to see what you build!"), recaps of what you just said, or product-page CTAs ("Try Sentry for free. Included on all plans."). Connect back to the story you opened with, or give the reader something concrete to do next.
Here's the quick map by post type:
| Type | Goal | Byline |
|---|---|---|
| Engineering Deep Dive | Explain a technical system/decision so other engineers learn | The engineer(s) who built it. Always. |
| Product Launch | Explain what shipped, why it matters, how to use it | PM, engineer, or DevEx. Not PMM unless marketing built it. |
| Postmortem | Transparent failure analysis with timeline and fixes | Engineering leadership |
| Data / Research | Original insights from Sentry's unique data position | Data team, engineering, or research |
| Tutorial / Guide | Help a developer accomplish something specific | DevEx, engineer, or community contributor |
Before publishing, ask: Would a developer share this post? Does it have a shot at getting on Hacker News? If the answer is no, the post either needs more depth, more original insight, or it belongs in the changelog instead.
Posts worth sharing contain at least one of:
Run through both checklists:
Technical Review:
Editorial Review:
Final Check:
When providing feedback, be specific and constructive. Quote the weak passage, explain why it's weak, and rewrite it to show the standard.