Microsoft Discovery is an extensible platform for scientific research and research-and-development workflows that combines agent orchestration, reasoning, graph-based knowledge, and high-performance computing. Researchers, partners, and product users use its Azure enterprise platform or local Windows app to explore and build research workflows. The catalogue entries provide skills and instructions for working with the Discovery community and platform.
Borrowing it
Nothing to install: this file belongs to microsoft/discovery. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/discovery/main/.github/skills/discovery-services-starter-kit-deployer/SKILL.mdgit clone --depth 1 https://github.com/microsoft/discoveryWrote 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/discovery/discovery-services-starter-kit-deployer)<a href="https://agentmods.dev/skills/microsoft/discovery/discovery-services-starter-kit-deployer"><img src="https://agentmods.dev/badge/skills/microsoft/discovery/discovery-services-starter-kit-deployer/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/discovery/discovery-services-starter-kit-deployer"><img src="https://agentmods.dev/badge/skills/microsoft/discovery/discovery-services-starter-kit-deployer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.03229 |
| Opus 5.5 | $0.00031 | $0.01292 |
| Sonnet 5.5 | $0.00015 | $0.00646 |
| Haiku 4.5 | $0.00008 | $0.00323 |
Grade A, and why
discovery-services-starter-kit-deployer 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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery Starter-Kit Deployer
Compatibility
Runs on Windows, macOS, and Linux through PowerShell 7+ (pwsh). Requires git, python with pip, and Azure CLI (az). Docker is optional because the runner can use Azure Container Registry Tasks when local Docker is unavailable.
What this skill does
Deploy a starter-kit from starter-kits\ as individual Discovery prompt agents:
pwsh -NoProfile -ExecutionPolicy Bypass -File .github\skills\discovery-services-starter-kit-deployer\scripts\deploy-discovery-starter-kit.ps1 <starter-kit-name>
The runner reads starter-kits\<starter-kit>\kit.json, validates every top-level agentRefs[].ref resolves to an existing agents\<agent>\ folder, builds every tool from those agents, deploys the tool resources in parallel, patches each referenced source agent with its own deployed tool resource ids, deploys all referenced agents in parallel, and prints a summary of deployed agents, deployed tools, and all top-level samplePrompts the customer can run manually.
When to use
Use this skill for requests like:
- "/discovery-services-starter-kit-deployer
drug-discovery" - "Deploy the
protein-structure-analysisstarter-kit" - "Deploy the agents in this starter-kit"
- "Deploy all agents referenced by this starter-kit kit.json"
If the user only wants one agent deployed, use discovery-services-agent-deployer instead. If the user only wants inventory, use discovery-catalog.
Customer inputs
| Parameter | Purpose |
|---|---|
<starter-kit-name> or -StarterKitName <name> |
Starter-kit folder name directly under starter-kits/. Required for init and -WhatIfPlan. |
-PublisherName <name> |
Deprecated. Tolerated for backwards compatibility but ignored — kits live in the flat starter-kits/<kit-name>/ layout with no publisher folder. The deployer prints a one-line deprecation notice when the flag is supplied. |
-BuildMode remote|local |
Required for every new starter-kit deployment during init; ask the customer to choose. remote queues ACR builds; local uses local Docker and pushes to ACR. Do not store build mode in config.json. |
-Stage init|build-tools|deploy-tools|deploy-agent|summary|stop |
Runs exactly one stage so Copilot TODOs can advance between commands. |
-RunDir <RunDir> |
Required with -Stage after init. |
-KnowledgeBasesJson <json-or-path> |
Required during init when any referenced agent declares discoveryExtensions.knowledgeBases. Pass either inline JSON or a path to a JSON file keyed by agent name. |
-ConfirmSupercomputerNodepools |
Run-scoped confirmation that the customer chose Proceed for the current run's tool/SKU plan. Pass it to init if the confirmation was collected before the run directory is created, or to the rerun of build-tools if the runner requested confirmation there. Do not store this in config.json. |
-WhatIfPlan |
Prints kit discovery, agentRefs, and stage plan without Azure calls. |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 126 lines · 77 tokens per session scan A 4b559cad4f59
discovery-services-starter-kit-deployer is a skill published in the GitHub repository microsoft/discovery (267 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 3,229 once invoked, about $0.0003 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…