mcs-research Skill
Use this skill to research and design an agent before building it. Reads project documents, identifies agents, researches MCS components, scores architecture, writes instructions, and generates eval sets. Use after /mcs-init, when documents change, when the user wants to analyze requirements, or when agentspec.json nee Published by microsoft in MCS-Agent-Builder.
What is mcs-research Skill?
Use this skill to research and design an agent before building it. Reads project documents, identifies agents, researches MCS components, scores architecture, writes instructions, and generates eval sets. Use after /mcs-init, when documents change, when the user wants to analyze requirements, or when agentspec.json nee Published by microsoft in MCS-Agent-Builder. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Documentation
- Data analysis
- Design and media
- Writing
- Research
Technical details
- Install or run with Copy skill directory
When to use mcs-research Skill
- Use it for documentation.
- Use it for data analysis.
- Use it for design and media.
- Use it for writing.
- Use it for research.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/MCS-Agent-Builder
- Skill file: .claude/skills/mcs-research/SKILL.md
What it does
Use this skill to research and design an agent before building it. Reads project documents, identifies agents, researches MCS components, scores architecture, writes instructions, and generates eval sets. Use after /mcs-init, when documents change, when the user wants to analyze requirements, or when agentspec.json nee
Skill instructions
MCS Research Three-phase pipeline: Fast Preview (30-90s scan) - Deep Research (3-10min enrichment) - Decisions & Build. The fast preview gives the customer a plain-language behavior contract to confirm before investing in deep research. This skill absorbs the former mcs-analyze step -- there is no separate extraction step. Input /mcs-research {projectId} {agentId} --fast Fast Preview: scan docs, extract behavior contract (30-90s) /mcs-research {projectId} Project-level: full deep research for all agents /mcs-research {projectId} {agentId} Agent-level: deep research scoped to one agent --fast Flag (Fast Preview Mode) When --fast is specified, the skill runs in preview-only mode: Runs (subset of Phase A — own step numbering, not main Phase A numbers): - Phase 0: Smart routing (full -- same as standard) - Phase A steps 1-4: Document comprehension + solution type assessment (same as standard) - Fast-A1: Extract per-agent data - write to agentspec.json - Fast-A2: Generate open questions - F
Explore related resources
Frequently asked questions
What is mcs-research?
mcs-research is a open-source AI agent skill with Copy skill directory. Use this skill to research and design an agent before building it. Reads project documents, identifies agents, researches MCS components, scores architecture, writes instructions, and generates eval sets.
Who is mcs-research best for?
mcs-research is best for reusing agent instructions, scripts, and references, documentation workflows, data analysis workflows, design and media workflows.
How do I install mcs-research?
Install or run mcs-research using Copy skill directory. Check mcs-research for the latest setup command.
Is mcs-research actively maintained?
mcs-research may need a closer maintenance check before production use.
Auto-fetched from GitHub.
