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-design-tasks/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-design-tasks)<a href="https://agentmods.dev/skills/microsoft/discovery/discovery-design-tasks"><img src="https://agentmods.dev/badge/skills/microsoft/discovery/discovery-design-tasks/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-design-tasks"><img src="https://agentmods.dev/badge/skills/microsoft/discovery/discovery-design-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 2 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high YARA Match · line 2 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Excessive Agency · line 206 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.07721 |
| Opus 5.5 | $0.00000 | $0.03088 |
| Sonnet 5.5 | $0.00000 | $0.01544 |
| Haiku 4.5 | $0.00000 | $0.00772 |
Grade A, and why
discovery-design-tasks 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
--- name: discovery-design-tasks description: "Generate a Microsoft Discovery task design (markdown only) for a user-specified local-app or cloud-service Foundry agent set using one (or all) of the three advanced investigation patterns: Deterministic, Guided Exploration, and Autonomous Research. For cloud-service task design or task creation, first look for a Discovery MCP server or Discovery proxy to resolve cloud workspaces, projects, agents, investigations, and tasks; if none is available, try Azure CLI before asking the user for another access route. Use when asked to plan a Discovery investigation, draft task trees, or choose an investigation pattern for an existing agent set." argument-hint: "Optional: --target local|cloud --agents all|select --pattern deterministic|guided|autonomous|all --out " user-invocable: true
Discovery Task Design
This skill produces a markdown task design file and must never overwrite an existing
task-design.md.
What This Skill Does
Generates a task-design.md document that describes a Discovery investigation using one or all of the three patterns from the Microsoft Discovery advanced investigation patterns documentation:
- Deterministic Investigation — fully specified parent + numbered subtasks with explicit agents and dependencies.
- Guided Exploration — high-level phases with broad validation; cognition picks agents inside each phase.
- Autonomous Research — single root-task prompt with validation requirements only.
The full canonical markdown example is embedded in Appendix A at the bottom of this file — use it as the byte-for-byte structural reference.
Inputs to Collect
Before generating anything, gather these inputs (use the ask-questions tool if any are missing or ambiguous — do NOT guess). Reuse values already present in the conversation or active editor when possible. Collect the Discovery target first by itself; if the user chooses Discovery cloud service, ask the cloud workspace, project, and investigation name in the next question before asking for the objective, pattern, or output folder.
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 · 380 lines · 0 tokens per session scan A 049df94ad962
discovery-design-tasks is a skill published in the GitHub repository microsoft/discovery (267 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,721 tokens. 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…