skills.rest
ramontramontini
ramontramontiniCOMMUNITY
Explore all skills by this author →
GitHub

gate-keeper-bench

Benchmarks GateKeeper across document types with automated per-fixture analysis and reporting.

Updated Apr 7, 2026
Search Tags:#automation#benchmarking#governance#benchmark#fixtures#gate-keeper
One-click install
npx skills add https://github.com/ramontramontini/CTEDemo --skill gate-keeper-bench
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gate-keeper-bench
Source: https://github.com/ramontramontini/CTEDemo/tree/main/.claude/skills/gate-keeper-bench
Command: npx skills add https://github.com/ramontramontini/CTEDemo --skill gate-keeper-bench

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill automates end-to-end benchmarking of Gate Keeper detection across curated fixtures to quantify accuracy, false positives, and stability.

Core Features & Use Cases

  • Automates end-to-end benchmarking of Gate Keeper across spec-review and code-review fixtures, collecting per-run verdicts and summary metrics.
  • Handles fixture loading, mode filtering, manifest validation, and deterministic 3-run evaluation per fixture with robust error handling and progress reporting.
  • Produces a comprehensive report with per-fixture results, per-mode metrics, and category-detection insights for known-bad fixtures.

Quick Start

Run the benchmark to execute three evaluations per fixture and generate the final report.

Frequently Asked Questions about gate-keeper-bench

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate benchmarking for detection accuracy across multiple test fixtures?▼

Automate detection benchmarking by loading mode-specific fixtures, validating manifests, and running three deterministic iterations per fixture to quantify accuracy, false positives, and stability.

What is a fixture-based benchmarking workflow for governance detection?▼

Fixture-based benchmarking evaluates detection performance by running curated spec-review and code-review fixtures, parsing verdicts, and aggregating per-run metrics into a structured quality report.

How do I measure false positives and stability in automated code review detection?▼

Measure false positives and stability by executing multiple benchmarking iterations against known-bad fixtures, parsing the verdicts from each run, and comparing per-fixture metrics for consistency.

Can I run benchmarking evaluations for both spec-review and code-review modes?▼

Yes, you can run benchmarking for both modes by filtering mode-specific fixtures, validating the files, and executing deterministic evaluations to produce per-mode metrics and category-detection insights.

What is the best way to generate a structured quality report from benchmark runs?▼

Generate a structured quality report by enforcing deterministic benchmarking steps, parsing responses for summaries, and aggregating per-fixture results and per-mode metrics into a comprehensive final output.

Why does my automated benchmarking workflow need manifest validation before running?▼

Manifest validation ensures fixture integrity and correct file loading before benchmarking, preventing inaccurate accuracy measurements and false positive rates caused by missing or corrupted test data.

Related Skills

Explore More Software Engineering Skills→
williabywilliaby

testing

Generate, review, and execute pytest test suites with workflow routing.

Community
Intermediate
rshelekhovrshelekhov

retro

Analyze weekly Git activity to generate engineering retrospectives with per-author metrics.

Community
Advanced
ITSpecialist111ITSpecialist111
43

rfp-gates

Coordinate three approval gates to validate RFP responses.

Community
Advanced
bigbulgogiburgerbigbulgogiburger
3

harness-score

Score merged pull requests for correctness and false positives using evidence.

Community
Intermediate