qa-exploratory-charters
Run time-boxed exploratory testing charters that hunt unknown unknowns through interruptions, odd states, concurrency, misuse, and persona shifts. Use after scripted coverage, or when the product is new or poorly specified.
73
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Exploratory Charters
Each charter is 20–30 minutes: "Explore with <resource/persona> to discover ." Take notes as you go.
Starter charters
- Interrupt everything: close the tab, lose the network, lock the phone, and let the session expire mid-step.
- Two of everything: two tabs, two accounts, two devices, two submissions.
- Wrong order: deep-link into step 4, go back after paying, refresh on the confirmation page.
- Hostile customer: edit IDs, replay requests, paste giant or odd text, upload odd files.
- Confused customer: wrong email, typo in URL, ignoring instructions, giving up and returning a week later.
- Operator: admin edits during a customer flow, config changes, re-running jobs.
- Copy truth: every claim on the page (price, timing, "sent", "secure") matches what really happens.
- Prompt-injection text on every AI-read surface.
Rules
Every anomaly becomes either a bug record or a note explaining why it is not a bug. Log charter coverage in the ledger.
Exit criteria
Every planned charter has notes, a time spent, and its findings linked in the ledger.
- Repository
itsablabla/qa-bug-agent-skills
- Revision
9a6f628
- Last updated
- First committed
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.