exploratory-testing SKILL.md skillA

exploratory-testing from marina-gajego/qa-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add marina-gajego/qa-skills/exploratory-testing@git:20261020.02a7d9d

Pins git:20261020.02a7d9d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
marina-gajego/qa-skills
Path
skills/exploratory-testing/SKILL.md
Versions recorded
2
Latest version
git:20261020.02a7d9d, committed Oct 20, 2026
First version recorded
Oct 7, 2026
Size
13,364 bytes
Repository stars
5
License
MIT

Runs a real exploratory testing session (Session-Based Test Management) on a web app, API, mobile or desktop app — actually driving the product through MCP tools (Playwright MCP by default for web, HTTP requests for APIs) with an exploratory tester's mindset — and delivers a session report with charter, (I)nformation and (R)isk notes, defects with evidence, questions, coverage gaps and next charters. Use whenever the user asks for exploratory testing, an exploratory session, bug hunting…

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

# Exploratory Testing

Do what a good exploratory tester does: **learn the product, design tests and run them at the same time**, letting each result decide the next action. There's no script. The value is in noticing what nobody wrote in a requirement.

Freedom is not randomness. What separates exploratory from ad-hoc testing is a purpose (the charter), reasoning about what to try next, and recording what you learned.

**What to read:** [references/environment-discovery.md](references/environment-discovery.md) and [references/tool-setup.md](references/tool-setup.md) always, before touching the product. Then, by target: [web-techniques.md](references/web-techniques.md) for web, [api-techniques.md](references/api-techniques.md) for APIs. [heuristics.md](references/heuristics.md) when you run out of ideas or the charter names a heuristic. [session-report.md](references/session-report.md) when writing the report, and [labels.md](references/labels.md) when it isn't in English.

## Language
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add marina-gajego/qa-skills/exploratory-testing@sha256:18ca9753a76a5721

The line at the top of this page pins the label git:20261020.02a7d9d, 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_uki3srbjegfb6lvx.svg)](https://markdownregistry.com/a/art_uki3srbjegfb6lvx)

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

Versions

The registry has recorded 2 versions of this file, between Oct 7, 2026 and Oct 20, 2026, about one every 14 days.

versioncommittedcommitsizeaudit
git:20261020.02a7d9d latest2026-10-20 02a7d9d 13,364 BA view · diff
git:20261007.0fc22032026-10-07 0fc2203 12,236 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 (13364 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

marina-gajego/qa-skills · 5 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_uki3srbjegfb6lvx
GET https://markdownregistry.com/api/v1/resolve?ref=marina-gajego/qa-skills/exploratory-testing
GET https://markdownregistry.com/api/v1/blob/18ca9753a76a57215335a5933b72ebf41fa8c814e55df6d8f9cf4729753c4c80

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 marina-gajego/qa-skills

bug-report-writer SKILL.md skill
marina-gajego/qa-skills · skills/bug-report-writer/SKILL.md · Turns bug findings (QA notes, steps performed, screenshots, logs, payloads, failed automated tests, exploratory session…
git:20261006.36a4a44 · audit A · 5 stars

Every file in marina-gajego/qa-skills

Other files named exploratory-testing

exploratory-testing SKILL.md skill
petrkindlmann/qa-skills · skills/exploratory-testing/SKILL.md · Design and execute structured exploratory testing sessions. Covers Session-Based Test Management (SBTM), charter…
v2.0 · audit A · 198 stars
exploratory-testing SKILL.md skill
fishzjp/qa-skills · skills/exploratory-testing/SKILL.md · Exploratory testing sessions when requirements are vague or docs are missing — charter-driven; outputs system…
v0.9.0 · audit A · 49 stars
exploratory-testing SKILL.md skill
cristhianzl/claude-skills-czl · configs/langflow/skills/exploratory-testing/SKILL.md · Run structured exploratory testing — write a charter, time-box a session, apply heuristics and oracles to discover bugs…
git:20260619.98096d2 · audit A · 5 stars
exploratory-testing SKILL.md skill
cristhianzl/claude-skills-czl · configs/agnostic/skills/exploratory-testing/SKILL.md · Run structured exploratory testing — write a charter, time-box a session, apply heuristics and oracles to discover bugs…
git:20260619.98096d2 · audit A · 5 stars

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