qa-analyst SKILL.md skillA

qa-analyst from afonsoft/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add afonsoft/skills/qa-analyst@v1.2.0

Pins v1.2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
afonsoft/skills
Path
skills/qa-analyst/SKILL.md
Versions recorded
11
Latest version
v1.2.0, committed Oct 1, 2026
First version recorded
Sep 9, 2026
Size
14,064 bytes
Repository stars
14
License
MIT

Use when the user asks for QA analysis, test planning, test cases, or root-cause analysis of a defect. Also use for post-merge PR review analysis: auditing recent closed PRs for Devin/GitHub/security bot comments, verifying whether requested corrections were applied, and turning pending fixes into SPECs.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# QA Analyst

You act as a senior QA analyst: extreme attention to detail, critical thinking, non-confrontational communication, and empathy for the end user. Bugs are reported as observable facts, never as blame.

All questions and clarifications to the user must be in **Portuguese (pt-BR)**. Internal reasoning and documentation are in English.

**Core principle**: QA starts before code. The cheapest defect is the one never written.

**Re-validation loop**: after every fix or process change, re-run the affected test cases and regression checks before declaring done.

## When to Use

- User asks for QA review, test plan, test cases, or bug report.
- A feature is ready for verification.
- A bug needs disciplined reproduction and reporting.
- After implementation, before a PR is opened.
- The user asks to analyze recent closed PRs — review comments left by Devin, human reviewers, or security/quality bots — and verify whether the requested corrections were actually applied (e.g., "analise os últimos PRs", "review PR comments").

- User asks or mentions this skill in English (e.g., "use /qa-analyst", "run qa-analyst").
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add afonsoft/skills/qa-analyst@sha256:b7a7347cedf2aeb4

The line at the top of this page pins the label v1.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_kotmvak2jfa6csxb.svg)](https://markdownregistry.com/a/art_kotmvak2jfa6csxb)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 11 versions of this file, between Sep 9, 2026 and Oct 1, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
v1.2.0 latest2026-10-01 f215d8d 14,064 BA view · diff
v1.1.22026-09-14 f5a0f74 10,812 BA view · diff
v1.1.12026-09-12 cf88aa9 9,947 BA view · diff
v1.1.02026-09-12 f327983 9,947 BA view · diff
v1.0.12026-09-11 ba4965c 9,947 BA view · diff
v1.0.12026-09-11 1f72d60 10,259 BA view · diff
v1.0.02026-09-11 443d2e6 10,259 BA view · diff
v1.0.02026-09-10 8136228 8,774 BA view · diff
v1.0.02026-09-09 6107e4d 8,579 BA view · diff
v1.0.02026-09-09 b9b1062 6,548 BA view · diff
v1.0.02026-09-09 0562ae1 6,657 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14064 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

afonsoft/skills · 14 stars · license MIT · pushed 2026-10-27 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_kotmvak2jfa6csxb
GET https://markdownregistry.com/api/v1/resolve?ref=afonsoft/skills/qa-analyst
GET https://markdownregistry.com/api/v1/blob/b7a7347cedf2aeb49ec17222220be714c30f0f4d7c8eb46dd6435af34b54cdc9

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from afonsoft/skills

architecture SKILL.md skill
afonsoft/skills · skills/architecture/SKILL.md · Single owner of everything under docs/architecture/ — ADRs, architecture and design documents, and architecture…
v1.0.1 · audit A · 14 stars
building-mcp-servers SKILL.md skill
afonsoft/skills · skills/building-mcp-servers/SKILL.md · Use when building a new MCP server in TypeScript, Python, or C# that exposes tools to LLMs.
v1.4.0 · audit A · 14 stars
code-review-and-quality SKILL.md skill
afonsoft/skills · skills/code-review-and-quality/SKILL.md · Use when reviewing code before it merges, whether written by an agent or a human.
v1.1.1 · audit A · 14 stars
composio-mcp SKILL.md skill
afonsoft/skills · skills/composio-mcp/SKILL.md · Use when the user asks to connect an AI agent to external apps via Composio, or when Composio CLI or MCP setup fails.
v1.1.1 · audit B · 14 stars
create-agent-harness SKILL.md skill
afonsoft/skills · skills/create-agent-harness/SKILL.md · Use when initializing or migrating an AI agent harness in a repository.
v2.3.0 · audit B · 14 stars
create-issues SKILL.md skill
afonsoft/skills · skills/create-issues/SKILL.md · Use when turning approved plans, specs, PRDs, or Epics into trackable GitHub Issues.
v1.4.0 · audit B · 14 stars
create-readme SKILL.md skill
afonsoft/skills · skills/create-readme/SKILL.md · Use when generating or updating a project README.md or CHANGELOG.md.
v1.2.1 · audit A · 14 stars
design SKILL.md skill
afonsoft/skills · skills/design/SKILL.md · Use when designing, redesigning, or improving a frontend interface in Angular, React, or Blazor. Use for landing pages…
v1.1.1 · audit A · 14 stars
diagnose SKILL.md skill
afonsoft/skills · skills/diagnose/SKILL.md · Use when the user reports a hard bug, unexpected failure, or performance regression that needs root-cause analysis.
v1.5.0 · audit A · 14 stars
drawio-architecture SKILL.md skill
afonsoft/skills · skills/drawio-architecture/SKILL.md · Use when generating or editing draw.io/diagrams.net architecture diagrams via MCP or native XML.
v1.0.2 · audit A · 14 stars
execute-specs SKILL.md skill
afonsoft/skills · skills/execute-specs/SKILL.md · Use when the user asks to implement an approved SPEC SDD using test-driven development.
v1.4.0 · audit A · 14 stars
gap-analysis SKILL.md skill
afonsoft/skills · skills/gap-analysis/SKILL.md · Use when auditing a repository for evidence-backed gaps between code, SPECs, architecture, and documentation — before a…
v1.0.2 · audit B · 14 stars

Every file in afonsoft/skills

Browse by kind, by grade A, or by owner.