exploratory-testing
Plans, runs and reports session-based exploratory testing: charters from risks, time-boxed sessions, notes, bugs, questions and a debrief. Use when the user says 'exploratory testing', 'explore this feature' or 'test charter'. Not for scripted regression cases (use test-case-designer).
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- exploratory-testing
- license
- Apache-2.0
- description
- Plans, runs and reports session-based exploratory testing: charters from risks, time-boxed sessions, notes, bugs, questions and a debrief. Use when the user says 'exploratory testing', 'explore this feature' or 'test charter'. Not for scripted regression cases (use test-case-designer).
- argument-hint
- [feature, area or release]
02 资源文件 1
- 参考文档references/heuristics.md1.3 KB
03 SKILL.md 正文
exploratory-testing
Objective
Scripted tests check what the team already knows. Exploratory testing finds what nobody thought of. Session-based exploration keeps it focused and accountable: each session has a mission, a time box and a written result.
Context
- Read
.agents/qa-project-context.mdif it exists. Use its critical journeys, risk areas and environments. - If it does not exist, ask the user for the environment, the accounts and the area. Suggest
qa-project-contextonce.
Discovery questions
- Which area, and which environment? Which accounts, roles and test data are available?
- What changed recently, and what are the known risks?
- How much time is there, and how many sessions?
Workflow
- Charters. Write 3 to 8 charters in the form "Explore <target> with <resources or technique> to discover <information or risk>". Take them from the top risks, the recent changes and the exploration heuristics.
- Session (45 to 90 minutes each). For each charter:
- Follow the mission, and note the new risks for later charters.
- Record what you tested, the data you used, and what you observed.
- When something looks wrong, record the exact steps, the data and the evidence at once.
- Session sheet for each session: charter, time, areas covered, bugs, questions, blocking issues and new test ideas. Also note the share of time for testing, for setup and for bug investigation.
- Debrief. Summarize the risks found, the areas not covered, and the follow-ups. Turn each confirmed bug into a report (see
bug-report). Turn each repeatable check into an automation candidate.
Anti-patterns
- Random clicking. A session with no charter gives no coverage information.
- No notes. A bug without exact steps and data cannot be reproduced.
- Only the happy path. Use the heuristics: limits, interruptions, wrong order, other roles.
Done when
- Each charter has a session sheet.
- Each bug has steps, data and evidence.
- The debrief lists the risks, the uncovered areas, the follow-ups and the automation candidates.
Related skills
risk-based-testing: the risks for the charters.edge-case-hunter: the edge cases to try.bug-report: the reports for the bugs found.test-case-designer: the scripted cases for the repeatable checks.
04 同仓库更多 Skills
unit-testing
Writes, fixes or improves unit tests for rules, calculations, validation and state logic: arrange-act-assert, exact oracles, boundary sets, doubles only at boundaries, controlled clock and randomness. Use when the user says 'write unit tests', 'TDD this' or 'mock this dependency'. Not for HTTP endpoints (use api-testing).
ui-automation
Writes, fixes or structures browser end-to-end tests for critical journeys: role, label or test ID locators, auto-waiting assertions, API data setup, page objects, auth reuse and traces. Use when the user says 'UI test', 'end-to-end test' or 'our UI tests are brittle'. Not for business rules (use unit-testing).
testcase-reviewer
Reviews automated tests or manual test cases like a senior test architect: scores fidelity, oracles, assertion depth, edge cases and determinism, and finds tests that pass on wrong code. Use when the user says 'review my tests', 'test smells' or 'review AI-written tests'. Not for fault injection (use mutation-probe).
testability-review
Scores how testable a feature, module or design is before tests exist (seams for clock, randomness and network, hidden state, observability) and gives the smallest production change per blocker. Use when the user asks 'is this testable' or 'why is this hard to test'. Not for writing the tests (use unit-testing).
test-strategy
Writes a test strategy for a product, system or team: quality goals, test levels and their share, environments, data, automation scope, non-functional testing, metrics and a roadmap. Use when the user says 'test strategy' or 'QA strategy'. Not for one sprint or release plan (use test-planning).
test-runner
Finds how a project runs its tests, runs the right subset, and triages each failure as product bug, test defect, environment problem or flaky test, with evidence. Use when the user says 'run the tests' or asks 'which tests fail and why'. Not for pipeline design (use ci-cd-integration).