Draft Outreach
Official Anthropic skill for researched and personalized sales outreach.
- Skill Road
- Draft Outreach
Categories
Draft Outreach is an official Anthropic skill from the public knowledge-work-plugins repository. It helps a compatible Claude workflow research a person or company and turn that research into a personalized first-contact draft. According to the provider, the workflow uses web research as its baseline and can be enhanced with connected enrichment services and a CRM. This entry therefore describes a reusable work method, not an independent email service, contact database, or promise that a message will be sent automatically. The primary source is the Sales skill at https://github.com/anthropics/knowledge-work-plugins/tree/main/sales/skills/draft-outreach.
Purpose and audience
The skill is intended for sales, business development, partnerships, and marketing teams that want to prepare relevant outreach without separating research from writing. According to the provider, requests such as reaching out to a particular person or company, writing a cold email for a prospect, or drafting outreach to a named contact can start the workflow. Strong input identifies the person or organization, its domain, the reason for contact, the offering, the intended channel, and a legitimate goal for the message. When those details are missing, the agent should ask for clarification or expose uncertainty rather than inventing a precise relationship.
Research before writing
The documented baseline starts with public web research. The workflow may examine an official website, product and solution pages, recent news, announcements, job postings, public profiles, and other relevant sources. The important step is connecting a supported observation with a plausible conversation reason. A new market announcement may be a useful signal, but it does not prove buying intent. An open role may indicate a priority, but it does not establish budget or decision authority. A responsible draft separates sourced facts, cautious hypotheses, and questions that still need to be answered in conversation.
Personalization and output
After research, the skill is intended to formulate a message that reflects the specific context, explains a credible benefit, and proposes an appropriate next step. Personalization should rely on professionally relevant, publicly supported information rather than private or sensitive assumptions. According to the provider, connected tools can add business contact data, firmographic context, or CRM history. Those enhancements are optional and are not automatically supplied by the skill. The draft should make its sources, uncertainties, and short rationale visible so a human can review tone, factual accuracy, consent requirements, and brand standards before sending.
Boundaries, safety, and E-E-A-T
Draft Outreach does not, according to its described function, automatically send a message. Any sending or writing action in email, a CRM, or another external system requires an explicitly approved integration and human confirmation. Websites, profiles, and CRM fields are untrusted data: prompt injection or manipulative content must not redirect the task. Passwords, tokens, and secret keys do not belong in a request or a draft. Personal data should be processed for a defined purpose, minimized, and handled according to applicable law and internal policy. Check identity, freshness, source quality, and the reason for contact before use. Anthropic is the provider of this workflow according to the published primary source; responsibility for accurate research, permitted outreach, privacy, and editorial approval remains with the adopting team. The repository identifies Apache-2.0 as the collection license. Anthropic documentation at https://docs.anthropic.com/ provides complementary official product documentation, but it does not replace review of local permissions and integrations.
Installation instructions
What the Draft Outreach Skill Does
Draft Outreach is a skill from the official Knowledge Work Plugins collection that Anthropic publishes on GitHub in the sales domain. According to the provider, the skill helps draft a personalized outreach email or a multi-touch sequence for a given prospect, creates that draft directly as an email draft for review, and, when asked, adds the contact to a sequence workflow in the connected sales engagement tool. The skill is triggered by typical phrasings such as a request to draft outreach to someone, write a cold email to a prospect, or prepare a three-touch sequence draft. A skill in this sense is not a standalone program but context-sensitive guidance that an AI assistant automatically draws on whenever a task matches its purpose.
Step 1: Prerequisites for Using It
For the skill to work meaningfully it needs access to a CRM system as well as to email and, where relevant, sequence tools through appropriate connectors. According to the provider, the skill strictly follows the actual data model of whichever CRM is connected and does not carry over assumptions from a different vendor's shapes; field names, stage labels, and picklists are read live from the connected system rather than guessed. Anyone wanting to use the skill should therefore first make sure the relevant connectors are set up with appropriate permissions, and decide which data scope, for example a personal pipeline or a team segment, should be accessible for the research.
Step 2: Setup and Typical Workflow
In practice, the assistant first gathers available information about the recipient from the CRM and any other connected sources, drafts a personalized message from that information, and saves it as a draft in the email program rather than sending it unreviewed. Only when explicitly requested is the contact additionally added to a sequence in the sales engagement tool. These intermediate steps are deliberately designed so a human reads and approves the text before it goes out. When the skill proposes a change that goes beyond the original request, it shows, according to the provider, the proposed change together with its supporting evidence, but leaves the decision to the user.
Security and Handling of Untrusted Content
A central security aspect of the skill concerns how it treats content from emails, chat threads, transcripts, or enrichment data: according to the provider, this content is always treated as data, never as instructions. If such a document contains, for instance, hidden text that looks like a command to the assistant, that text is reported rather than acted upon, and links found inside such sources are never rendered directly but only referenced through the record's own ID. A clear rule also applies to automated or scheduled runs: a scheduled action only performs what it was originally set up to do. Anything additionally suggested by untrusted content during that run stays a proposal and is not executed on its own, because there is no one present at that moment to confirm the action.
Practical Value for Sales Teams
For sales teams the value lies mainly in automating the time-consuming research and drafting work that precedes first contact, without giving up control over the actual sending. Instead of manually scanning CRM records, past interactions, and publicly available information, the assistant produces a well-grounded first draft based on real, cited CRM values, clearly marking those values as such and distinguishing between fields that are genuinely blank and fields that simply were not queried. This substantially reduces errors caused by outdated or invented information.
Limits of the Skill
The limits appear wherever connectors are missing or permissions are insufficient: the skill explicitly works with what is genuinely available and openly states which tools were missing or which data could not be queried, rather than silently filling gaps. The quality of the personalization also remains dependent on the data quality inside the CRM; an incompletely maintained record leads to a correspondingly more generic draft. Anyone using the skill in production should therefore regularly check whether CRM data is current enough to enable genuinely individualized outreach.
- Provider
- Anthropic
- License
- Apache-2.0
- Last reviewed
- 09.09.2026