Benchmark Report

Generate a benchmark report from stress test results (registration, API performance, search concurrency). Reads JSON result files and produces a markdown report suitable for docs/benchmarks/.

1,052 stars 263 forksTesting & QA

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add agentic-community/mcp-gateway-registry --skill benchmark-report
Manual install
git clone --depth 1 https://github.com/agentic-community/mcp-gateway-registry.git /tmp/mcp-gateway-registry
mkdir -p ~/.claude/skills
cp -r /tmp/mcp-gateway-registry/.claude/skills/benchmark-report ~/.claude/skills/benchmark-report

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Benchmark Report Skill

Generate a markdown benchmark report from stress test result files. The report documents the registry's performance characteristics under load, including registration throughput, API latency, and semantic search concurrency scaling.

## Prerequisites

1. Stress test results must exist in `tests/stress/results/<backend>/size-<N>/`
2. Required files: `registration.json`, `api_perf.json`, `search_concurrency.json`
3. All JSON files should include `registry_info` (deployment configuration snapshot)

## Input

```
/benchmark-report [RESULTS_DIR] [OUTPUT_PATH]
```

- **RESULTS_DIR** - Path to the results directory (default: `tests/stress/results/documentdb/size-100`)
- **OUTPUT_PATH** - Where to write the report (default: `docs/benchmarks/benchmark-report.md`)

## Workflow

### Step 1: Run the Report Generator

```bash
/usr/bin/python3 .claude/skills/benchmark-report/generate_benchmark_report.py \
  --results-dir tests/stress/results/documentdb/size-100 \
  --output docs/benchmarks/benchmark-report.md
```

The script reads all three JSON files, extracts the key metrics, and produces a structured markdown report.

### Step 2: Review and Present

After generation:
1. Display the executive summary in the conversation
2. Tell the user the output path
3. Note any missing data (e.g., if one of the JSON files is absent)

## Report Structure

The generated report includes:
Read the full skill on GitHub

Details

Skill name
benchmark-report
Path
.claude/skills/benchmark-report/SKILL.md
License
Apache-2.0
Repo updated
18 November 2026

FAQ

What does the Benchmark Report skill do?

Generate a benchmark report from stress test results (registration, API performance, search concurrency). Reads JSON result files and produces a markdown report suitable for docs/benchmarks/.

How do I install the Benchmark Report skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add agentic-community/mcp-gateway-registry --skill benchmark-report. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Benchmark Report popular?

It lives in agentic-community/mcp-gateway-registry, which has 1,052 GitHub stars and 263 forks.

Related skills

Agentcore Register

1.1k

agentic-community/mcp-gateway-registry

Given an MCP server URL, probe the server via curl to discover its metadata and tools, then generate a markdown file with copy-pasteable content for each field in the Amazon Bedrock AgentCore "Create record" form.

AI, LLMs & Agents263

Create Milestone

1.1k

agentic-community/mcp-gateway-registry

Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.

Git & Code Review263

Debug

1.1k

agentic-community/mcp-gateway-registry

Debug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out, returning errors, or behaving unexpectedly. Forces structured root-cause analysis before any code change is proposed.

Software Development263

New Feature Design

1.1k

agentic-community/mcp-gateway-registry

Design and document new features with GitHub issue, low-level design (LLD), expert review, and testing plan. Creates structured documentation in .scratchpad/ with issue spec, technical design with diagrams and pseudo-code, multi-persona expert review, and a testing plan covering functional (curl and registry_management.py), backwards-compatibility, UX, ECS/terraform, and E2E API tests. Supports starting from a user description OR an existing GitHub issue URL. Folder naming: issue-{number}/ for existing issues, {feature-name}/ for new features.

Testing & QA263

TDD Workflow

2k

xu-xiang/everything-claude-code-zh

在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发,确保单元测试、集成测试和端到端测试的覆盖率超过80%。

Testing & QA332

Full Stack Orchestration Full Stack Feature

2k

rmyndharis/antigravity-skills

Coordinate database, backend, frontend, testing, and deployment work for a complete feature. Use when implementing changes that span multiple application layers.

Testing & QA295

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.