email-adaptation
Skill5.9k starsChanged 4 days agoApache-2.0View on GitHub
Use when turning existing copy, a blog post, an announcement, or a brief into an email that works in an inbox, including deciding what to cut and what to link out to.
1 other project uses a version of this.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- vercel-labs/marketing-team-eve-templateword for word, first seen Nov 12, 2026
Who's talking about vercel/eve
- @qdrddr.bsky.social“@vercel.com Eve #Agentic #framework uses #filesystem as interface for tools, just drop a #TypeScript code …”Bluesky · Oct 16, 2026 · 8 likes
- @projectnothing.bsky.social“When frameworks like eve break out, it’s a sign: AI agents are no longer side projects—they’re becoming a …”Bluesky · Jun 17, 2026 · 3 likes
- @github-trending-js.bsky.social“📦 vercel / eve ⭐ 5,184 (+40) 🗒 TypeScript The Open Framework for Building Agents”Bluesky · Sep 17, 2026 · 2 likes
- DataDog/dd-trace-js“feat(llmobs): add external experiment recorder”GitHub · Jul 31, 2026 · 2 reactions
- byronwade/rebuzzle.byronwade.com“Bump the production-dependencies group across 1 directory with 13 updates”GitHub · Nov 9, 2026 · 1 reactions
The biggest 5 of 57 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 57
Talked about on GitHub and Bluesky (57 times).
On GitHub · 50
- Jul 31, 2026feat(llmobs): add external experiment recorder — DataDog/dd-trace-js2 reactions · 5 comments
- Nov 9, 2026Bump the production-dependencies group across 1 directory with 13 updates — byronwade/rebuzzle.byronwade.com1 reaction · 5 comments
- Nov 3, 2026chore(deps-dev): bump the npm-development group across 1 directory with 8 updates — ComposioHQ/composio1 reaction · 6 comments
- Oct 30, 2026Bump the production-dependencies group across 1 directory with 11 updates — byronwade/rebuzzle.byronwade.com1 reaction · 6 comments
- Oct 30, 2026chore(deps-dev): bump the npm-development group with 7 updates — ComposioHQ/composio1 reaction · 6 comments
45 more on GitHub
- Oct 16, 2026chore(deps-dev): bump the npm-development group across 1 directory with 8 updates — ComposioHQ/composio1 reaction · 6 comments
- Oct 16, 2026chore(deps-dev): bump the npm-development group with 4 updates — ComposioHQ/composio1 reaction · 6 comments
- Oct 13, 2026chore(deps-dev): bump the npm-development group with 3 updates — ComposioHQ/composio1 reaction · 5 comments
- Oct 9, 2026chore(deps-dev): bump the npm-development group across 1 directory with 7 updates — ComposioHQ/composio1 reaction · 6 comments
- Sep 25, 2026chore(deps-dev): bump the npm-development group with 8 updates — ComposioHQ/composio1 reaction · 4 comments
- Sep 14, 2026chore(deps): bump the production-dependencies group across 1 directory with 13 updates — byronwade/rebuzzle.byronwade.com1 reaction · 5 comments
- Sep 11, 2026chore(deps-dev): bump the npm-development group with 5 updates — ComposioHQ/composio1 reaction · 4 comments
- Sep 7, 2026chore(deps): bump the production-dependencies group across 1 directory with 12 updates — byronwade/rebuzzle.byronwade.com1 reaction · 4 comments
- Sep 1, 2026@nuxt/kit missing @nuxt/schema dependency breaks TypeScript with pnpm 12 GVS — nuxt/nuxt1 reaction
- Aug 31, 2026chore(deps): bump the production-dependencies group with 11 updates — byronwade/rebuzzle.byronwade.com1 reaction · 4 comments
- Aug 26, 2026Add conversational Discord agent template — vercel/eve-examples1 reaction · 2 comments
- Aug 13, 2026基于 vercel/eve 实现 agents demo 切片 — SawanaLabs/agent-demos1 reaction · 3 comments
- Jul 28, 2026fix(nitro): vercel function rules - preserve relative symlinks — nitrojs/nitro1 reaction · 4 comments
- Jul 3, 2026Add Eve adapter (eve_gateway + eve_local) — paperclipai/paperclip1 reaction · 6 comments
- Jun 30, 2026Install eve skill from vercel/eve — TommyBez/evex1 reaction · 2 comments
- Jun 19, 2026[codex] Read downloads from the sandbox stream — remiconnesson/eve-single-user-agent-starter1 reaction · 1 comment
- Nov 11, 2026feat: fully replace duplicated Bot/Frontend agent infrastructure with eve + ambient Slack — alexj11324/Mikka0 reactions · 24 comments
- Nov 9, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Nov 3, 2026[ARCHITECTURE ASSESSMENT] Eve.dev adoption — no control-plane replacement; bounded comparative pilot — mastermindx-market-intelligence/Mastermind0 reactions
- Nov 2, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 27, 2026Telegram HITL: при нажатии кнопки подтверждения теряется нажавший (auth: null) — в вендоренном eve 0.51.1 нет фикса vercel/eve#4241 — smixs/iva-agent0 reactions · 2 comments
- Oct 26, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 19, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 18, 2026T2: Preserve authenticated attachments when continuing copied history — FranciscoMoretti/chat-js0 reactions
- Oct 18, 2026T1/T2: Adopt upstream structured history imports with completed tools and attachments — FranciscoMoretti/chat-js0 reactions
- Oct 12, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Oct 11, 2026`vercel dev` stalls silently (no port, no error) when the Next.js dev-manifest config loader exits non-zero — vercel/vercel0 reactions
- Oct 6, 2026Research: custom SPARQL-generation model + separate review layer (prior art: eve + Qwen + Jev data analyst) — wazootech/wazoo-memorybench0 reactions
- Oct 3, 2026[Add] eve (vercel/eve) — PyTorchKR/landscape0 reactions
- Sep 23, 2026research(eve): isoler les contextes et garder le root CStack compact en multi-agent — charlescstpierr/cstack0 reactions
- Sep 19, 2026未対応のカードの効果の翻訳を、会話の中で Pull Request として足せるようにする — mokosystem/pokemon-tcg-buddy0 reactions
- Sep 1, 2026sep 2026 — kimtth/azure-openai-llm-notes0 reactions
- Aug 12, 2026Ship an eve and AI SDK memory integration guide — Studio-Moser/Advisaur-MCP0 reactions
- Aug 12, 2026Evaluate eve as a seventh distribution channel — tartinerlabs/skills0 reactions · 2 comments
- Aug 10, 2026epic(ai): the agent harness -- vision, prior art, and the plan to stand behind "or the agent harness itself" — routecraftjs/routecraft0 reactions · 4 comments
- Jul 14, 2026Epic: publish TypeScript SDK and durable Eve approval channel — asiraky/mayi0 reactions · 2 comments
- Jul 13, 2026@ai-sdk/openai: support ordered additional_tools after a normal tool result — vercel/ai0 reactions · 4 comments
- Jul 4, 2026test(eve): run eve evals as fak parity and regression witnesses — anthony-chaudhary/fak0 reactions · 7 comments
- Jul 4, 2026feat(eve): lease-gate shared-sandbox subagent fan-out from child session streams — anthony-chaudhary/fak0 reactions · 1 comment
- Jul 4, 2026feat(eve): preflight MCP/OpenAPI connections for scoped auth, allowlists, and approval gates — anthony-chaudhary/fak0 reactions · 1 comment
- Jul 4, 2026feat(eve): compile agent/ directories into fak policy and mount manifests — anthony-chaudhary/fak0 reactions · 1 comment
- Jul 4, 2026epic(eve): Vercel eve integration bridge - filesystem agents, policy lint, evals, and observability — anthony-chaudhary/fak0 reactions
- Jun 23, 2026@vercel/connect/eve: support context-aware Slack installation selection — vercel/vercel0 reactions
- Jun 19, 2026Remove sandbox stream compatibility fix after Eve #117 is released — remiconnesson/eve-single-user-agent-starter0 reactions
- Jun 19, 2026Add Vercel Eve sandbox backend adapter support — sandbox0-ai/sandbox00 reactions
On Bluesky · 7
- Oct 16, 2026@vercel.com Eve #Agentic #framework uses #filesystem as interface for tools, just drop a #TypeScript code into a folder, the filename… — @qdrddr.bsky.social8 likes and reposts · 1 reply
- Jun 17, 2026When frameworks like eve break out, it’s a sign: AI agents are no longer side projects—they’re becoming a new pillar of mainstream software… — @projectnothing.bsky.social3 likes and reposts
- Sep 17, 2026📦 vercel / eve ⭐ 5,184 (+40) 🗒 TypeScript The Open Framework for Building Agents — @github-trending-js.bsky.social2 likes and reposts
- Sep 20, 2026github.com/vercel/eve GitHub - vercel/eve: The Open Framework for Building Agents — @technews4869.bsky.social1 likes and repost
- Aug 11, 2026Cloudflare OS blog: blog.cloudflare.com/cloudflare-os/, github.com/cloudflare/cloudflare-os Vercel eve: vercel.com/blog/introducing-eve ·… — @akash-bhatia.bsky.social1 likes and repost
2 more on Bluesky
- Jul 2, 2026Vercel's eve is a filesystem-first framework for durable AI agents: an agent is a directory of instructions, tools, skills, channels, and… — @agentpalisade.bsky.social1 likes and repost
- Jun 17, 2026The Framework for Building Agents https://github.com/vercel/eve — @laxima-tech.bsky.social1 likes and repost
Other versions1 project uses a version of this.
Word for word · 1
- vercel-labs/marketing-team-eve-template★ 456100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository115 other files it gives its agents.
- AGENTS.mdAGENTS.md
- apps/docs/AGENTS.mdAGENTS.md
- apps/templates/eve-agent-python-template/AGENTS.mdAGENTS.md
- apps/templates/eve-agent-python-template/apps/web/AGENTS.mdAGENTS.md
- apps/templates/eve-chat-template/AGENTS.mdAGENTS.md
- apps/templates/eve-coding-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-content-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-contentful-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-data-analyst-template/AGENTS.mdAGENTS.md
- apps/templates/eve-discord-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-llm-council-template/AGENTS.mdAGENTS.md
- apps/templates/eve-mem0-template/AGENTS.mdAGENTS.md
- apps/templates/eve-memory-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-slack-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-software-factory-template/AGENTS.mdAGENTS.md
- apps/templates/eve-sre-agent-template/AGENTS.mdAGENTS.md
- apps/templates/eve-tanstack-start-template/AGENTS.mdAGENTS.md
- apps/templates/eve-vercel-drives-starter/AGENTS.mdAGENTS.md
- apps/templates/eve-voice-template/AGENTS.mdAGENTS.md
- apps/templates/kody-eve-template/AGENTS.mdAGENTS.md
- apps/templates/marketing-team-eve-template/AGENTS.mdAGENTS.md
- apps/templates/openinstinct/AGENTS.mdAGENTS.md
- apps/templates/personal-agent-template/AGENTS.mdAGENTS.md
- apps/templates/sanity-copilot-eve-template/AGENTS.mdAGENTS.md
- apps/templates/slack-company-brain-template/AGENTS.mdAGENTS.md
- packages/eve-agent-desktop/AGENTS.mdAGENTS.md
- packages/eve-code/AGENTS.mdAGENTS.md
- packages/eve-computer-use/AGENTS.mdAGENTS.md
- packages/eve-custom-skills/AGENTS.mdAGENTS.md
- packages/eve-git/AGENTS.mdAGENTS.md
- packages/eve/src/internal/nitro/AGENTS.mdAGENTS.md
- apps/templates/eve-agent-python-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-chat-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-coding-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-content-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-contentful-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-data-analyst-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-discord-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-llm-council-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-mem0-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-memory-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-slack-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-software-factory-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-sre-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-tanstack-start-template/CLAUDE.mdCLAUDE.md
- apps/templates/eve-vercel-drives-starter/CLAUDE.mdCLAUDE.md
- apps/templates/eve-voice-template/CLAUDE.mdCLAUDE.md
- apps/templates/kody-eve-template/CLAUDE.mdCLAUDE.md
- apps/templates/marketing-team-eve-template/CLAUDE.mdCLAUDE.md
- apps/templates/openinstinct/CLAUDE.mdCLAUDE.md
- apps/templates/personal-agent-template/CLAUDE.mdCLAUDE.md
- apps/templates/sanity-copilot-eve-template/CLAUDE.mdCLAUDE.md
- apps/templates/slack-company-brain-template/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- gh-pr-descriptionSkill
- pr-shepherdSkill
- technical-writingSkill
- test-auditSkill
- create-payment-credentialSkill
- dashboard-chat-best-practicesSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Before you cut a single sentence, answer three questions.
- Distinctive: line 62
Do not harden a hedged claim while compressing it.
- Distinctive: line 63
Do not invent specifics to make a sentence tighter.
- Distinctive: line 64
When you cut something substantial, changed the emphasis, or dropped a caveat on purpose, say so in your handback.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Adapting copy into an email
Someone hands you words that were written for a page and wants them sent as mail. The job is not to shorten them. It is to work out what the email is for, which is almost never the same as what the page was for.
A page answers a question someone already had. An email interrupts someone who did not ask. So the page can afford to build an argument, and the email has to earn the click to the page.
How email gets read
Attention is brief and it sits at the top. Nielsen Norman Group's 2006 eyetracking study found participants fully read 19% of the newsletters they opened, gave an opened one 51 seconds on average, and 67% of them recorded no eye fixations at all inside the newsletter's introduction, even though those introductions averaged about three lines. NN/g's 2010 round turns that into the rule to follow: lead with the content the reader values, because they rarely read far past it.
That same round also found readers arrive in different modes, some with a minute and some with ten, and advised committing to a brief mail or a leisurely one rather than a compromise that serves neither. That is the reason for the two shapes below.
Word count targets are the weakest part of the published advice. The figures in circulation disagree with each other, trace back to secondary citations rather than to studies, and the publishers printing them say scannability matters more than the count. So treat length as a consequence of what has to fit, not as a target to hit.
Decide the email's job first
Before you cut a single sentence, answer three questions. If the brief does not settle them, ask rather than assuming.
- What is the one action you want? Read the post, book the call, reply, upgrade, show up. One, not three. A mail that asks for three things has not decided what it is for, and it makes the reader do that work in the seconds they have given you.
- What does this reader already know? A list of existing customers and a list of cold signups need different first lines, and the same email cannot serve both.
- What happens if they do nothing? If the honest answer is nothing, this may not need to be an email, and saying so is more useful than sending it.
The two shapes
Most adaptations are one of these. Pick deliberately, because mixing them produces an email that is too long to read and too thin to be useful.
The pointer. The email exists to get the click. Give the reader the single most interesting idea from the piece, enough context to know why it matters to them, and the link. Keep it short enough that the idea and the link are both there before any scrolling. This is the right shape for a blog post, a guide, or anything long: the piece is the destination, so do not reproduce it.
The whole thing. The email is the deliverable and there is nothing to click through to. An announcement, a short essay, a set of release notes, a personal note. It can run longer, but every paragraph still has to earn its place, and it still ends with one action.
The mistake to avoid is the third shape that happens by accident: two thirds of a blog post pasted into an email, ending in "read the rest". You have spent the reader's attention on the part you included and you are still asking them to leave to get the rest, so neither half of the mail is doing its job.
What to cut
Cutting for email is not proportional trimming. Whole categories go.
- Setup, background, and the history of the problem. This is the part the eyetracking work found readers skipping outright, so it is the first thing to lose. The page needed to establish relevance; the email establishes it in the first line or loses the reader anyway.
- Anything hedged, caveated, or qualified at length. Nuance survives on a page and dies in a preview pane. If a claim needs three sentences of qualification, either state it plainly and link to the qualification, or cut it.
- Supporting arguments after the first. A page can make a case three ways; an email makes it once.
- Section headings that were navigational. The email is short enough not to need a map.
- Secondary calls to action. Move them to the page, or drop them.
What survives: the specific claim, the number or example that makes it concrete, the reason this reader should care, and the action.
What to add
Adaptation is not only subtraction. An email needs things a page does not.
- A reason this arrived now. "Because you signed up for X" or "you asked about Y last month" or simply what changed. Unexplained mail reads as bulk.
- Subject line and preview text, written as a pair. See
email-stylefor how they work together. - The plain text version.
- A sign-off from a person rather than from a department, where the brand allows it.
Keep the source honest
You are editing someone else's work, usually the content marketer's, and they made choices you cannot see from the copy alone.
- Do not harden a hedged claim while compressing it. "Early results suggest a 20% reduction" becoming "cuts costs 20%" is the single easiest error to make in this pass, and it is the one that causes real problems.
- Do not invent specifics to make a sentence tighter. A number that was not in the source does not go in the email.
- When you cut something substantial, changed the emphasis, or dropped a caveat on purpose, say so in your handback. The person who wrote it should get the chance to disagree.
References
references/patterns.md: worked shapes for the recurring email types, including the newsletter, the announcement, the nurture sequence, and the re-engagement mail, with what each one gets wrong most often.
Layers on top of
email-style carries the voice and the format limits, and writing-quality carries the word-level rules. This skill only covers the decisions about structure and scope.
Sources
- Nielsen Norman Group, "Email Newsletters: Surviving Inbox Congestion", June 11 2006, https://www.nngroup.com/articles/email-newsletters-inbox-congestion/ . Eyetracking plus field study, 42 participants and 117 newsletters. Source for 19% fully read, 35% skimmed or glanced at only part, 51 seconds average on an opened newsletter, and 67% of participants with zero fixations in the introduction.
- Nielsen Norman Group, "E-Mail Newsletters: Increasing Usability", November 28 2010, https://www.nngroup.com/articles/e-mail-newsletters-usability/ . Five rounds of research, 270 newsletters across 124 participants. Source for leading with high-value content because readers rarely go further, and for committing to a brief or a leisurely message rather than a compromise.
- The share of a newsletter that gets read varies a lot between NN/g's rounds: 23% read thoroughly in 2002, 11% in the 2004 diary study (https://www.nngroup.com/articles/targeted-email-newsletters/), 19% in the 2006 eyetracking study. Read these as "most of it goes unread" rather than as a stable figure.
- Depth-of-attention research on web pages points the same way but is not email: NN/g's 2018 eyetracking analysis (https://www.nngroup.com/articles/scrolling-and-attention/, 120 participants, over 130,000 fixations) found 57% of viewing time above the fold and 74% within the first two screenfuls, down from 80% above the fold in its 2010 measurement. Do not quote these numbers as email findings.
- Deliberately not used: the widely repeated claim that a single call to action produces 371% more clicks and 1617% more sales. Campaign Monitor's page carrying it links to a WordStream stats roundup rather than to a study, and no primary source, sample size, or date is findable. The one-action rule above is editorial judgment, not that number.
- No verifiable primary source exists for an ideal email word count either. The most quoted band, 50 to 125 words, appears on Campaign Monitor (February 27 2020, https://www.campaignmonitor.com/blog/email-marketing/email-length-best-practices-for-email-marketers-and-email-newbies/) sourced to a magazine article rather than to research, and the same page contradicts itself on the range and concludes that scannability matters more than length.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

