exploratory
Skill0 starsChanged 17 days agoMITView on GitHub
Create exploratory testing charters and session ideas for a feature — where to look for bugs, what to try, tours and heuristics. Use when the user wants exploratory testing ideas, a testing tour, or "what should I test" guidance for a feature.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- api-testSkill
- automateSkill
- bug-reportSkill
- mobile-testSkill
- test-casesSkill
- test-dataSkill
- test-planSkill
- test-reportSkill
The file
Files
Exploratory Testing Guide
Help the tester plan exploratory testing sessions for a feature they describe.
Output
Produce 3-6 charters, each in this format:
Charter: Explore
<area>using <resources/approach> to discover<kind of problems>Time box: 30-60 min Ideas to try: 5-10 concrete, creative things to attempt
Where to find good ideas
Apply heuristics relevant to the feature (pick what fits, don't dump all):
- CRUD tour — create, read, update, delete everything; delete things that are in use elsewhere
- Interruption tour — cancel mid-operation, refresh during save, kill network, go back button, double-click submit
- Data tour — extreme values, wrong formats, copy-paste with formatting, autofill
- State tour — expired session, second tab, concurrent edits by two users
- Permission tour — every role tries every action, including via direct URL/API
- Environment tour — small screen, slow network (throttle), different browser/locale/timezone
- History tour — upgrade with old data, previously-saved drafts, legacy records
End with a short "Most likely bug hiding spots" list — your top 3 guesses for where this specific feature will break, with reasoning.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

