Dataverse Business Skills is a collection of natural-language instructions that teach AI agents how to follow business processes, policies, and domain knowledge for Microsoft Dataverse. Organizations use the skills with Dataverse environments connected to products such as Power Apps, Dynamics 365, or Power Platform. The catalogue entries are skills from this collection.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/dataverse-business-skills --skill draft-outreachgit clone --depth 1 https://github.com/microsoft/dataverse-business-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/dataverse-business-skills/draft-outreach)<a href="https://agentmods.dev/skills/microsoft/dataverse-business-skills/draft-outreach"><img src="https://agentmods.dev/badge/skills/microsoft/dataverse-business-skills/draft-outreach/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/dataverse-business-skills/draft-outreach"><img src="https://agentmods.dev/badge/skills/microsoft/dataverse-business-skills/draft-outreach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.03490 |
| Opus 5 | $0.00044 | $0.01745 |
| Sonnet 5 | $0.00018 | $0.00698 |
| Haiku 4.5 | $0.00009 | $0.00349 |
Grade A, and why
draft-outreach scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Outreach
Generic outreach gets ignored. Personalized messages that reference real context — a recent interaction, a known pain point, or a relevant product already owned — get responses. This skill eliminates the blank-page problem by pulling Dataverse data to craft contextually relevant outreach, saving reps time while improving reply rates. It works within Dataverse without requiring external enrichment tools.
Instructions
Step 1: Identify Target Contact and Outreach Trigger
Accept input from the user:
- Target: Contact name, lead name, or account name
- Outreach type: New intro, re-engagement, follow-up, cross-sell, renewal, or event-based
- Goal: Meeting request, proposal follow-up, demo invite, check-in, etc.
- Tone: Formal, conversational, or brief (default: conversational)
Step 2: Retrieve Contact or Lead Record
If contact:
SELECT contactid, fullname, firstname, jobtitle, accountid, emailaddress1,
telephone1, description, createdon, modifiedon
FROM contact
WHERE fullname LIKE '%[name]%'
If lead:
SELECT leadid, fullname, firstname, jobtitle, companyname, emailaddress1,
telephone1, description, leadsourcecode, leadqualitycode, createdon
FROM lead
WHERE statecode = 0
AND fullname LIKE '%[name]%'
Present matches if multiple found. Confirm the target with the user before proceeding.
Step 3: Gather Account Context
If a contact was found, retrieve their account:
SELECT accountid, name, industrycode, revenue, numberofemployees,
description, address1_city, address1_stateorprovince,
customertypecode, accountcategorycode
FROM account
WHERE accountid = '[accountid]'
Step 4: Review Relationship History
Recent activities (last 90 days):
SELECT activityid, activitytypecode, subject, actualend, description,
statecode, regardingobjectid
FROM activitypointer
WHERE regardingobjectid = '[contactid or accountid]'
AND statecode = 1
ORDER BY actualend DESC
Limit to 10 most recent. Note:
- Days since last interaction
- Last activity type and topic
- Any commitments made (from description)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 457 lines · 88 tokens per session scan A 15a17353b35a
draft-outreach is a skill published in the GitHub repository microsoft/dataverse-business-skills (50 stars, last pushed 6mo ago), licensed MIT. It adds 88 tokens to every session and 3,490 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…