ada-code-quality-pipeline

Orchestrates a three-stage gated pipeline for verified code quality reports.

Updated Jul 23, 2026
One-click install
npx skills add https://github.com/wubing7755/Ada --skill ada-code-quality-pipeline-wubing7755
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ada-code-quality-pipeline
Source: https://github.com/wubing7755/Ada/tree/main/skills/software-development/ada-code-quality-pipeline
Command: npx skills add https://github.com/wubing7755/Ada --skill ada-code-quality-pipeline-wubing7755

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? First-draft code quality reports often contain false positives, statistical drift, and missed security issues. This Skill enforces an end-to-end gated workflow — analysis, independent verification, and a QA gate — so the report you act on has been checked against actual source code before delivery. ## Core Features & Use Cases - Three-Stage Gated Pipeline: Chains multi-dimension analysis (complexity, duplication, dead code, security, dependencies, test coverage, style), independent claim verification, and a four-check QA gate in strict order. - Blocking Quality Gates: Verification sends the report back if it finds 3 or more false positives; the QA gate blocks delivery on statistical inconsistencies or security omissions. - Use Case: Before planning a team-wide remediation, ask for a full quality audit of your repository. The pipeline produces a report where every issue is traced to concrete file:line evidence and has passed verification and QA checks. ## Quick Start Ask the agent to run a full end-to-end code quality pipeline on your repository and deliver a verified, QA-gated report.

Frequently Asked Questions about ada-code-quality-pipeline

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

FAQPage Schema
How do I get a verified code quality report for my repository?

Request a full end-to-end quality pipeline rather than a single scan. The pipeline runs multi-dimension analysis, then independently verifies each claim against source code, and finally applies a QA gate before delivering the report.

What code quality dimensions does a full audit cover?

The analysis stage covers seven dimensions: cyclomatic complexity, code duplication, dead code, security vulnerabilities, dependency health, test coverage, and code style conventions. Each finding is tied to concrete file evidence.

When should I use the full quality pipeline instead of a quick review?

Use the full pipeline for compliance audits, high-stakes remediation planning, or any report you will act on team-wide. For focused questions like a slow loop or N+1 query check, a targeted single-dimension review is more appropriate.

What happens if the verification stage finds false positives?

If verification finds three or more false positives, the report is sent back to the analysis stage for correction rather than being delivered. This blocking rule prevents inaccurate findings from reaching the final deliverable.

Why must all pipeline stages run on the same commit?

File counts and line numbers from the analysis stage drift if the codebase changes before verification runs. Running all three stages on the same commit keeps statistics consistent and evidence references valid.