mcs-report Skill
Use this skill to generate an export from agentspec.json without running a build. Produces a single self-contained HTML file with three tabs: Brief (design state), Evaluations (test sets and results), and How-To Guide (step-by-step MCS build instructions). Use when the user wants a summary, status update, or shareable Published by microsoft in MCS-Agent-Builder.
What is mcs-report Skill?
Use this skill to generate an export from agentspec.json without running a build. Produces a single self-contained HTML file with three tabs: Brief (design state), Evaluations (test sets and results), and How-To Guide (step-by-step MCS build instructions). Use when the user wants a summary, status update, or shareable 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
- Testing
- Design and media
- Research
- Testing use cases
- Design and media use cases
Technical details
- Install or run with Copy skill directory
When to use mcs-report Skill
- Use it for testing.
- Use it for design and media.
- Use it for research.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/MCS-Agent-Builder
- Skill file: .claude/skills/mcs-report/SKILL.md
What it does
Use this skill to generate an export from agentspec.json without running a build. Produces a single self-contained HTML file with three tabs: Brief (design state), Evaluations (test sets and results), and How-To Guide (step-by-step MCS build instructions). Use when the user wants a summary, status update, or shareable
Skill instructions
MCS Report Generator Generate a combined HTML export from agentspec.json at any project stage. Read-only — never modifies agentspec.json. Input /mcs-report {projectId} {agentId} Reads from: Build-Guides/{projectId}/agents/{agentId}/agentspec.json — read-only, never modifies Writes to: Build-Guides/{projectId}/agents/{agentId}/export.html Step 1: Load and Validate agentspec.json Read agentspec.json. If missing → STOP: "No agentspec.json found. Run /mcs-research first." Check completeness — minimum required: business, agent, capabilities (at least 1). If missing → WARN (don't stop): "Some sections will be incomplete — {field} is empty." Step 2: Generate HTML Export Generate the self-contained HTML export by calling the server-side renderer: bash node -e " const path = require('path'); const { renderReport } = require('./app/lib/report'); const briefPath = path.resolve('Build-Guides/{projectId}/agents/{agentId}/agentspec.json'); const outPath = path.resolve('Build-Guides/{projectId}/agent
Explore related resources
Frequently asked questions
What is mcs-report?
mcs-report is a open-source AI agent skill with Copy skill directory. Use this skill to generate an export from agentspec.json without running a build. Produces a single self-contained HTML file with three tabs: Brief (design state), Evaluations (test sets and results), and.
Who is mcs-report best for?
mcs-report is best for reusing agent instructions, scripts, and references, testing workflows, design and media workflows, research workflows.
How do I install mcs-report?
Install or run mcs-report using Copy skill directory. Check mcs-report for the latest setup command.
Is mcs-report actively maintained?
mcs-report may need a closer maintenance check before production use.
Auto-fetched from GitHub.
